diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_abd.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_abd.c
index 25903e049070..5b5b34d2edca 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_abd.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_abd.c
@@ -428,16 +428,14 @@ svuint64_t test_svabd_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svabd_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svabd_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svabd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svabd_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svabd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svabd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svabd_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svabd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svabd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svabd_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svabd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svabd_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svabd_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svabd_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svabd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svabd_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svabd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svabd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svabd_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svabd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svabd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svabd_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svabd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svabd_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svabd_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svabd_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svabd_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svabd_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svabd_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svabd_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svabd_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svabd_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svabd_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svabd_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svabd_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svabd_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svabd_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svabd_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svabd_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svabd_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svabd_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svabd_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svabd_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svabd_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sabd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svabd_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svabd_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svabd_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svabd_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svabd_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svabd_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svabd_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svabd_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svabd_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uabd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svabd_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svabd_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svabd_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svabd_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svabd_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svabd_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1059,7 +1011,6 @@ svfloat16_t test_svabd_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2)
   return SVE_ACLE_FUNC(svabd,_f16,_x,)(pg, op1, op2);
 }
 
-//
 // CHECK-LABEL: @test_svabd_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
@@ -1097,8 +1048,7 @@ svfloat64_t test_svabd_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svabd_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1106,8 +1056,7 @@ svfloat64_t test_svabd_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1120,8 +1069,7 @@ svfloat16_t test_svabd_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svabd_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1129,8 +1077,7 @@ svfloat16_t test_svabd_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1143,8 +1090,7 @@ svfloat32_t test_svabd_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svabd_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1152,8 +1098,7 @@ svfloat32_t test_svabd_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1166,16 +1111,14 @@ svfloat64_t test_svabd_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svabd_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1187,16 +1130,14 @@ svfloat16_t test_svabd_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svabd_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1208,16 +1149,14 @@ svfloat32_t test_svabd_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svabd_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1229,16 +1168,14 @@ svfloat64_t test_svabd_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svabd_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1250,16 +1187,14 @@ svfloat16_t test_svabd_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svabd_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1271,16 +1206,14 @@ svfloat32_t test_svabd_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svabd_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabd_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acge.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acge.c
index 4342520f9fd7..791599bd74a3 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acge.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acge.c
@@ -74,8 +74,7 @@ svbool_t test_svacge_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svacge_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.facge.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -83,8 +82,7 @@ svbool_t test_svacge_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z17test_svacge_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.facge.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -97,8 +95,7 @@ svbool_t test_svacge_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svacge_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.facge.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -106,8 +103,7 @@ svbool_t test_svacge_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z17test_svacge_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.facge.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acgt.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acgt.c
index b2e0b1679354..b1297fe1cfc2 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acgt.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acgt.c
@@ -74,8 +74,7 @@ svbool_t test_svacgt_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svacgt_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.facgt.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -83,8 +82,7 @@ svbool_t test_svacgt_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z17test_svacgt_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.facgt.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -97,8 +95,7 @@ svbool_t test_svacgt_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svacgt_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.facgt.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -106,8 +103,7 @@ svbool_t test_svacgt_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z17test_svacgt_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.facgt.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acle.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acle.c
index f432984e8664..b1af88e1c225 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acle.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_acle.c
@@ -74,8 +74,7 @@ svbool_t test_svacle_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svacle_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.facge.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -83,8 +82,7 @@ svbool_t test_svacle_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z17test_svacle_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.facge.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -97,8 +95,7 @@ svbool_t test_svacle_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svacle_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.facge.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -106,8 +103,7 @@ svbool_t test_svacle_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z17test_svacle_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.facge.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_aclt.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_aclt.c
index ddeb983f6e46..4e5740b498d5 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_aclt.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_aclt.c
@@ -74,8 +74,7 @@ svbool_t test_svaclt_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svaclt_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.facgt.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -83,8 +82,7 @@ svbool_t test_svaclt_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z17test_svaclt_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.facgt.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -97,8 +95,7 @@ svbool_t test_svaclt_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svaclt_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.facgt.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -106,8 +103,7 @@ svbool_t test_svaclt_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z17test_svaclt_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.facgt.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_add.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_add.c
index 675260e51313..da95476e2d15 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_add.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_add.c
@@ -428,16 +428,14 @@ svuint64_t test_svadd_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svadd_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svadd_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svadd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svadd_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svadd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svadd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svadd_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svadd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svadd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svadd_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svadd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svadd_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svadd_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svadd_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svadd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svadd_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svadd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svadd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svadd_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svadd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svadd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svadd_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svadd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svadd_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svadd_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svadd_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svadd_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svadd_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svadd_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svadd_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svadd_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svadd_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svadd_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svadd_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svadd_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svadd_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svadd_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svadd_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svadd_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svadd_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svadd_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svadd_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svadd_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svadd_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svadd_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svadd_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svadd_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svadd_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svadd_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svadd_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svadd_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svadd_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svadd_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svadd_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svadd_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svadd_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svadd_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svadd_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svadd_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svadd_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svadd_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svadd_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svadd_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svadd_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svadd_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svadd_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svadd_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svadd_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svadd_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svadd_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svadd_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svadd_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svadd_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svadd_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svadd_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svadd_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svadd_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svadd_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svadd_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svadd_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadd_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_and.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_and.c
index 90320f7ba5a0..33d39cfc2be1 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_and.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_and.c
@@ -428,16 +428,14 @@ svuint64_t test_svand_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svand_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svand_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svand_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svand_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svand_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svand_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svand_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svand_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svand_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svand_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svand_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svand_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svand_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svand_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svand_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svand_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svand_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svand_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svand_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svand_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svand_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svand_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svand_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svand_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svand_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svand_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svand_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svand_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svand_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svand_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svand_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svand_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svand_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svand_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svand_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svand_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svand_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svand_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svand_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svand_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svand_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svand_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svand_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svand_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svand_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svand_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svand_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svand_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svand_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svand_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svand_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svand_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svand_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.and.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svand_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svand_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.and.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svand_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svand_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.and.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svand_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svand_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svand_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.and.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_asr.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_asr.c
index 3d0a6a2e6104..b4bb06a44c39 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_asr.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_asr.c
@@ -223,8 +223,7 @@ svint64_t test_svasr_s64_x(svbool_t pg, svint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svasr_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -232,8 +231,7 @@ svint64_t test_svasr_s64_x(svbool_t pg, svint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s64_zu10__SVBool_tu11__SVInt64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -246,16 +244,14 @@ svint64_t test_svasr_n_s64_z(svbool_t pg, svint64_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svasr_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s64_mu10__SVBool_tu11__SVInt64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -267,16 +263,14 @@ svint64_t test_svasr_n_s64_m(svbool_t pg, svint64_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svasr_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s64_xu10__SVBool_tu11__SVInt64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.asr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -440,16 +434,14 @@ svint32_t test_svasr_wide_s32_x(svbool_t pg, svint32_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svasr_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svasr_n_s8_zu10__SVBool_tu10__SVInt8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -462,8 +454,7 @@ svint8_t test_svasr_n_s8_z(svbool_t pg, svint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svasr_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -471,8 +462,7 @@ svint8_t test_svasr_n_s8_z(svbool_t pg, svint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s16_zu10__SVBool_tu11__SVInt16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -485,8 +475,7 @@ svint16_t test_svasr_n_s16_z(svbool_t pg, svint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svasr_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -494,8 +483,7 @@ svint16_t test_svasr_n_s16_z(svbool_t pg, svint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s32_zu10__SVBool_tu11__SVInt32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -507,15 +495,13 @@ svint32_t test_svasr_n_s32_z(svbool_t pg, svint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svasr_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svasr_n_s8_mu10__SVBool_tu10__SVInt8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -527,16 +513,14 @@ svint8_t test_svasr_n_s8_m(svbool_t pg, svint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svasr_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s16_mu10__SVBool_tu11__SVInt16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -548,16 +532,14 @@ svint16_t test_svasr_n_s16_m(svbool_t pg, svint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svasr_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s32_mu10__SVBool_tu11__SVInt32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -568,15 +550,13 @@ svint32_t test_svasr_n_s32_m(svbool_t pg, svint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svasr_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svasr_n_s8_xu10__SVBool_tu10__SVInt8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -588,16 +568,14 @@ svint8_t test_svasr_n_s8_x(svbool_t pg, svint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svasr_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s16_xu10__SVBool_tu11__SVInt16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -609,16 +587,14 @@ svint16_t test_svasr_n_s16_x(svbool_t pg, svint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svasr_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svasr_n_s32_xu10__SVBool_tu11__SVInt32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -629,15 +605,13 @@ svint32_t test_svasr_n_s32_x(svbool_t pg, svint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svasr_wide_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svasr_wide_n_s8_mu10__SVBool_tu10__SVInt8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -649,16 +623,14 @@ svint8_t test_svasr_wide_n_s8_m(svbool_t pg, svint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svasr_wide_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svasr_wide_n_s16_mu10__SVBool_tu11__SVInt16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -670,16 +642,14 @@ svint16_t test_svasr_wide_n_s16_m(svbool_t pg, svint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svasr_wide_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svasr_wide_n_s32_mu10__SVBool_tu11__SVInt32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -690,16 +660,14 @@ svint32_t test_svasr_wide_n_s32_m(svbool_t pg, svint32_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svasr_wide_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.wide.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svasr_wide_n_s8_zu10__SVBool_tu10__SVInt8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.wide.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -712,8 +680,7 @@ svint8_t test_svasr_wide_n_s8_z(svbool_t pg, svint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svasr_wide_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -721,8 +688,7 @@ svint8_t test_svasr_wide_n_s8_z(svbool_t pg, svint8_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svasr_wide_n_s16_zu10__SVBool_tu11__SVInt16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -735,8 +701,7 @@ svint16_t test_svasr_wide_n_s16_z(svbool_t pg, svint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svasr_wide_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -744,8 +709,7 @@ svint16_t test_svasr_wide_n_s16_z(svbool_t pg, svint16_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svasr_wide_n_s32_zu10__SVBool_tu11__SVInt32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -757,15 +721,13 @@ svint32_t test_svasr_wide_n_s32_z(svbool_t pg, svint32_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svasr_wide_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svasr_wide_n_s8_xu10__SVBool_tu10__SVInt8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.asr.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -777,16 +739,14 @@ svint8_t test_svasr_wide_n_s8_x(svbool_t pg, svint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svasr_wide_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svasr_wide_n_s16_xu10__SVBool_tu11__SVInt16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.asr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -798,16 +758,14 @@ svint16_t test_svasr_wide_n_s16_x(svbool_t pg, svint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svasr_wide_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svasr_wide_n_s32_xu10__SVBool_tu11__SVInt32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.asr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfdot.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfdot.c
index fc7e0ac32ed9..deab191390c0 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfdot.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfdot.c
@@ -57,15 +57,13 @@ svfloat32_t test_bfdot_lane_3_f32(svfloat32_t x, svbfloat16_t y, svbfloat16_t z)
 
 // CHECK-LABEL: @test_bfdot_n_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[Z:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.x.nxv8bf16(bfloat [[Z:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.bfdot(<vscale x 4 x float> [[X:%.*]], <vscale x 8 x bfloat> [[Y:%.*]], <vscale x 8 x bfloat> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_bfdot_n_f32u13__SVFloat32_tu14__SVBFloat16_tu6__bf16(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[Z:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.x.nxv8bf16(bfloat [[Z:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.bfdot(<vscale x 4 x float> [[X:%.*]], <vscale x 8 x bfloat> [[Y:%.*]], <vscale x 8 x bfloat> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmlalb.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmlalb.c
index dc74449d6f8a..c5733eb812e7 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmlalb.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmlalb.c
@@ -57,15 +57,13 @@ svfloat32_t test_bfmlalb_lane_7_f32(svfloat32_t x, svbfloat16_t y, svbfloat16_t
 
 // CHECK-LABEL: @test_bfmlalb_n_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[Z:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.x.nxv8bf16(bfloat [[Z:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.bfmlalb(<vscale x 4 x float> [[X:%.*]], <vscale x 8 x bfloat> [[Y:%.*]], <vscale x 8 x bfloat> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_bfmlalb_n_f32u13__SVFloat32_tu14__SVBFloat16_tu6__bf16(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[Z:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.x.nxv8bf16(bfloat [[Z:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.bfmlalb(<vscale x 4 x float> [[X:%.*]], <vscale x 8 x bfloat> [[Y:%.*]], <vscale x 8 x bfloat> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmlalt.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmlalt.c
index 564ef4f9f50d..6fdd3206fee6 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmlalt.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bfmlalt.c
@@ -57,15 +57,13 @@ svfloat32_t test_bfmlalt_lane_7_f32(svfloat32_t x, svbfloat16_t y, svbfloat16_t
 
 // CHECK-LABEL: @test_bfmlalt_n_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[Z:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.x.nxv8bf16(bfloat [[Z:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.bfmlalt(<vscale x 4 x float> [[X:%.*]], <vscale x 8 x bfloat> [[Y:%.*]], <vscale x 8 x bfloat> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_bfmlalt_n_f32u13__SVFloat32_tu14__SVBFloat16_tu6__bf16(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[Z:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.x.nxv8bf16(bfloat [[Z:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.bfmlalt(<vscale x 4 x float> [[X:%.*]], <vscale x 8 x bfloat> [[Y:%.*]], <vscale x 8 x bfloat> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bic.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bic.c
index e60921b1d688..e391d41fe795 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bic.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_bic.c
@@ -428,16 +428,14 @@ svuint64_t test_svbic_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svbic_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbic_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svbic_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svbic_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svbic_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svbic_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svbic_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svbic_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svbic_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svbic_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svbic_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svbic_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svbic_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbic_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svbic_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svbic_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svbic_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svbic_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svbic_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svbic_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svbic_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svbic_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svbic_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svbic_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svbic_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbic_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svbic_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svbic_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svbic_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svbic_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svbic_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svbic_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svbic_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svbic_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbic_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svbic_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svbic_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svbic_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svbic_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svbic_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svbic_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svbic_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svbic_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbic_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svbic_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svbic_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svbic_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svbic_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svbic_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svbic_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svbic_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svbic_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbic_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svbic_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svbic_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svbic_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svbic_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svbic_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svbic_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbic_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpeq.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpeq.c
index 5821ba47fbe2..cedd2738b7ef 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpeq.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpeq.c
@@ -161,8 +161,7 @@ svbool_t test_svcmpeq_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_s64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpeq.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -170,8 +169,7 @@ svbool_t test_svcmpeq_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_s64u10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpeq.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -184,8 +182,7 @@ svbool_t test_svcmpeq_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_u64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpeq.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -193,8 +190,7 @@ svbool_t test_svcmpeq_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_u64u10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpeq.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -259,15 +255,13 @@ svbool_t test_svcmpeq_wide_s32(svbool_t pg, svint32_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svcmpeq_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpeq.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmpeq_n_s8u10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpeq.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -279,8 +273,7 @@ svbool_t test_svcmpeq_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpeq.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -288,8 +281,7 @@ svbool_t test_svcmpeq_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_s16u10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpeq.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -302,8 +294,7 @@ svbool_t test_svcmpeq_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpeq.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -311,8 +302,7 @@ svbool_t test_svcmpeq_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_s32u10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpeq.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -324,15 +314,13 @@ svbool_t test_svcmpeq_n_s32(svbool_t pg, svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svcmpeq_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpeq.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmpeq_n_u8u10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpeq.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -344,8 +332,7 @@ svbool_t test_svcmpeq_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpeq.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -353,8 +340,7 @@ svbool_t test_svcmpeq_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_u16u10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpeq.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -367,8 +353,7 @@ svbool_t test_svcmpeq_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpeq.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -376,8 +361,7 @@ svbool_t test_svcmpeq_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_u32u10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpeq.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -447,8 +431,7 @@ svbool_t test_svcmpeq_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_f16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpeq.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -456,8 +439,7 @@ svbool_t test_svcmpeq_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_f16u10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpeq.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -470,8 +452,7 @@ svbool_t test_svcmpeq_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpeq.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -479,8 +460,7 @@ svbool_t test_svcmpeq_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpeq.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -493,8 +473,7 @@ svbool_t test_svcmpeq_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svcmpeq_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpeq.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -502,8 +481,7 @@ svbool_t test_svcmpeq_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpeq_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpeq.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -515,15 +493,13 @@ svbool_t test_svcmpeq_n_f64(svbool_t pg, svfloat64_t op1, float64_t op2)
 
 // CHECK-LABEL: @test_svcmpeq_wide_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpeq.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmpeq_wide_n_s8u10__SVBool_tu10__SVInt8_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpeq.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -535,8 +511,7 @@ svbool_t test_svcmpeq_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpeq_wide_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpeq.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -544,8 +519,7 @@ svbool_t test_svcmpeq_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpeq_wide_n_s16u10__SVBool_tu11__SVInt16_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpeq.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -558,8 +532,7 @@ svbool_t test_svcmpeq_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpeq_wide_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpeq.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -567,8 +540,7 @@ svbool_t test_svcmpeq_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpeq_wide_n_s32u10__SVBool_tu11__SVInt32_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpeq.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpge.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpge.c
index 56d020a30fe6..26ead4897ea1 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpge.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpge.c
@@ -161,8 +161,7 @@ svbool_t test_svcmpge_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svcmpge_n_s64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpge.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -170,8 +169,7 @@ svbool_t test_svcmpge_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_s64u10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpge.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -184,8 +182,7 @@ svbool_t test_svcmpge_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpge_n_u64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmphs.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -193,8 +190,7 @@ svbool_t test_svcmpge_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_u64u10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmphs.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -312,15 +308,13 @@ svbool_t test_svcmpge_wide_u32(svbool_t pg, svuint32_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svcmpge_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpge.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmpge_n_s8u10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpge.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -332,8 +326,7 @@ svbool_t test_svcmpge_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svcmpge_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpge.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -341,8 +334,7 @@ svbool_t test_svcmpge_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_s16u10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpge.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -355,8 +347,7 @@ svbool_t test_svcmpge_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svcmpge_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpge.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -364,8 +355,7 @@ svbool_t test_svcmpge_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_s32u10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpge.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -377,15 +367,13 @@ svbool_t test_svcmpge_n_s32(svbool_t pg, svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svcmpge_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphs.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmpge_n_u8u10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphs.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -397,8 +385,7 @@ svbool_t test_svcmpge_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svcmpge_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphs.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -406,8 +393,7 @@ svbool_t test_svcmpge_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_u16u10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphs.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -420,8 +406,7 @@ svbool_t test_svcmpge_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svcmpge_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphs.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -429,8 +414,7 @@ svbool_t test_svcmpge_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_u32u10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphs.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -500,8 +484,7 @@ svbool_t test_svcmpge_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svcmpge_n_f16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpge.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -509,8 +492,7 @@ svbool_t test_svcmpge_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_f16u10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpge.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -523,8 +505,7 @@ svbool_t test_svcmpge_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svcmpge_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpge.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -532,8 +513,7 @@ svbool_t test_svcmpge_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpge.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -546,8 +526,7 @@ svbool_t test_svcmpge_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svcmpge_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpge.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -555,8 +534,7 @@ svbool_t test_svcmpge_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpge_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpge.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -568,15 +546,13 @@ svbool_t test_svcmpge_n_f64(svbool_t pg, svfloat64_t op1, float64_t op2)
 
 // CHECK-LABEL: @test_svcmpge_wide_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpge.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmpge_wide_n_s8u10__SVBool_tu10__SVInt8_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpge.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -588,8 +564,7 @@ svbool_t test_svcmpge_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpge_wide_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpge.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -597,8 +572,7 @@ svbool_t test_svcmpge_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpge_wide_n_s16u10__SVBool_tu11__SVInt16_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpge.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -611,8 +585,7 @@ svbool_t test_svcmpge_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpge_wide_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpge.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -620,8 +593,7 @@ svbool_t test_svcmpge_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpge_wide_n_s32u10__SVBool_tu11__SVInt32_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpge.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -633,15 +605,13 @@ svbool_t test_svcmpge_wide_n_s32(svbool_t pg, svint32_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svcmpge_wide_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphs.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmpge_wide_n_u8u10__SVBool_tu11__SVUint8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphs.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -653,8 +623,7 @@ svbool_t test_svcmpge_wide_n_u8(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svcmpge_wide_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphs.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -662,8 +631,7 @@ svbool_t test_svcmpge_wide_n_u8(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpge_wide_n_u16u10__SVBool_tu12__SVUint16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphs.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -676,8 +644,7 @@ svbool_t test_svcmpge_wide_n_u16(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svcmpge_wide_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphs.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -685,8 +652,7 @@ svbool_t test_svcmpge_wide_n_u16(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpge_wide_n_u32u10__SVBool_tu12__SVUint32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphs.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpgt.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpgt.c
index 91abb5750ba2..a5881cb129ab 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpgt.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpgt.c
@@ -161,8 +161,7 @@ svbool_t test_svcmpgt_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_s64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpgt.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -170,8 +169,7 @@ svbool_t test_svcmpgt_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_s64u10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpgt.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -184,8 +182,7 @@ svbool_t test_svcmpgt_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_u64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmphi.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -193,8 +190,7 @@ svbool_t test_svcmpgt_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_u64u10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmphi.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -312,15 +308,13 @@ svbool_t test_svcmpgt_wide_u32(svbool_t pg, svuint32_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svcmpgt_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpgt.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmpgt_n_s8u10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpgt.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -332,8 +326,7 @@ svbool_t test_svcmpgt_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpgt.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -341,8 +334,7 @@ svbool_t test_svcmpgt_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_s16u10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpgt.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -355,8 +347,7 @@ svbool_t test_svcmpgt_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpgt.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -364,8 +355,7 @@ svbool_t test_svcmpgt_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_s32u10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpgt.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -377,15 +367,13 @@ svbool_t test_svcmpgt_n_s32(svbool_t pg, svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svcmpgt_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphi.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmpgt_n_u8u10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphi.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -397,8 +385,7 @@ svbool_t test_svcmpgt_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphi.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -406,8 +393,7 @@ svbool_t test_svcmpgt_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_u16u10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphi.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -420,8 +406,7 @@ svbool_t test_svcmpgt_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphi.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -429,8 +414,7 @@ svbool_t test_svcmpgt_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_u32u10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphi.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -500,8 +484,7 @@ svbool_t test_svcmpgt_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_f16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpgt.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -509,8 +492,7 @@ svbool_t test_svcmpgt_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_f16u10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpgt.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -523,8 +505,7 @@ svbool_t test_svcmpgt_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpgt.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -532,8 +513,7 @@ svbool_t test_svcmpgt_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpgt.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -546,8 +526,7 @@ svbool_t test_svcmpgt_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svcmpgt_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpgt.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -555,8 +534,7 @@ svbool_t test_svcmpgt_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpgt_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpgt.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -568,15 +546,13 @@ svbool_t test_svcmpgt_n_f64(svbool_t pg, svfloat64_t op1, float64_t op2)
 
 // CHECK-LABEL: @test_svcmpgt_wide_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpgt.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmpgt_wide_n_s8u10__SVBool_tu10__SVInt8_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpgt.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -588,8 +564,7 @@ svbool_t test_svcmpgt_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpgt_wide_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpgt.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -597,8 +572,7 @@ svbool_t test_svcmpgt_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpgt_wide_n_s16u10__SVBool_tu11__SVInt16_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpgt.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -611,8 +585,7 @@ svbool_t test_svcmpgt_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpgt_wide_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpgt.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -620,8 +593,7 @@ svbool_t test_svcmpgt_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpgt_wide_n_s32u10__SVBool_tu11__SVInt32_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpgt.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -633,15 +605,13 @@ svbool_t test_svcmpgt_wide_n_s32(svbool_t pg, svint32_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svcmpgt_wide_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphi.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmpgt_wide_n_u8u10__SVBool_tu11__SVUint8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphi.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -653,8 +623,7 @@ svbool_t test_svcmpgt_wide_n_u8(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svcmpgt_wide_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphi.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -662,8 +631,7 @@ svbool_t test_svcmpgt_wide_n_u8(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpgt_wide_n_u16u10__SVBool_tu12__SVUint16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphi.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -676,8 +644,7 @@ svbool_t test_svcmpgt_wide_n_u16(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svcmpgt_wide_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphi.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -685,8 +652,7 @@ svbool_t test_svcmpgt_wide_n_u16(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpgt_wide_n_u32u10__SVBool_tu12__SVUint32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphi.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmple.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmple.c
index 20d27b227fd6..694b7c7a93af 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmple.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmple.c
@@ -161,8 +161,7 @@ svbool_t test_svcmple_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svcmple_n_s64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpge.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP1]], <vscale x 2 x i64> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -170,8 +169,7 @@ svbool_t test_svcmple_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_s64u10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpge.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP1]], <vscale x 2 x i64> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -184,8 +182,7 @@ svbool_t test_svcmple_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmple_n_u64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmphs.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP1]], <vscale x 2 x i64> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -193,8 +190,7 @@ svbool_t test_svcmple_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_u64u10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmphs.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP1]], <vscale x 2 x i64> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -312,15 +308,13 @@ svbool_t test_svcmple_wide_u32(svbool_t pg, svuint32_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svcmple_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpge.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[OP1:%.*]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmple_n_s8u10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpge.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -332,8 +326,7 @@ svbool_t test_svcmple_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svcmple_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpge.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 8 x i16> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -341,8 +334,7 @@ svbool_t test_svcmple_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_s16u10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpge.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 8 x i16> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -355,8 +347,7 @@ svbool_t test_svcmple_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svcmple_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpge.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP1]], <vscale x 4 x i32> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -364,8 +355,7 @@ svbool_t test_svcmple_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_s32u10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpge.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP1]], <vscale x 4 x i32> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -377,15 +367,13 @@ svbool_t test_svcmple_n_s32(svbool_t pg, svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svcmple_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphs.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[OP1:%.*]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmple_n_u8u10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphs.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -397,8 +385,7 @@ svbool_t test_svcmple_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svcmple_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphs.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 8 x i16> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -406,8 +393,7 @@ svbool_t test_svcmple_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_u16u10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphs.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 8 x i16> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -420,8 +406,7 @@ svbool_t test_svcmple_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svcmple_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphs.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP1]], <vscale x 4 x i32> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -429,8 +414,7 @@ svbool_t test_svcmple_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_u32u10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphs.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP1]], <vscale x 4 x i32> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -500,8 +484,7 @@ svbool_t test_svcmple_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svcmple_n_f16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpge.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -509,8 +492,7 @@ svbool_t test_svcmple_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_f16u10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpge.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -523,8 +505,7 @@ svbool_t test_svcmple_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svcmple_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpge.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -532,8 +513,7 @@ svbool_t test_svcmple_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpge.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -546,8 +526,7 @@ svbool_t test_svcmple_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svcmple_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpge.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -555,8 +534,7 @@ svbool_t test_svcmple_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmple_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpge.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -568,15 +546,13 @@ svbool_t test_svcmple_n_f64(svbool_t pg, svfloat64_t op1, float64_t op2)
 
 // CHECK-LABEL: @test_svcmple_wide_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmple.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmple_wide_n_s8u10__SVBool_tu10__SVInt8_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmple.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -588,8 +564,7 @@ svbool_t test_svcmple_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmple_wide_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmple.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -597,8 +572,7 @@ svbool_t test_svcmple_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmple_wide_n_s16u10__SVBool_tu11__SVInt16_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmple.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -611,8 +585,7 @@ svbool_t test_svcmple_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmple_wide_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmple.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -620,8 +593,7 @@ svbool_t test_svcmple_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmple_wide_n_s32u10__SVBool_tu11__SVInt32_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmple.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -633,15 +605,13 @@ svbool_t test_svcmple_wide_n_s32(svbool_t pg, svint32_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svcmple_wide_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpls.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmple_wide_n_u8u10__SVBool_tu11__SVUint8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpls.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -653,8 +623,7 @@ svbool_t test_svcmple_wide_n_u8(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svcmple_wide_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpls.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -662,8 +631,7 @@ svbool_t test_svcmple_wide_n_u8(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmple_wide_n_u16u10__SVBool_tu12__SVUint16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpls.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -676,8 +644,7 @@ svbool_t test_svcmple_wide_n_u16(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svcmple_wide_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpls.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -685,8 +652,7 @@ svbool_t test_svcmple_wide_n_u16(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmple_wide_n_u32u10__SVBool_tu12__SVUint32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpls.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmplt.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmplt.c
index f534235634ba..1ef15579ade2 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmplt.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmplt.c
@@ -161,8 +161,7 @@ svbool_t test_svcmplt_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svcmplt_n_s64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpgt.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP1]], <vscale x 2 x i64> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -170,8 +169,7 @@ svbool_t test_svcmplt_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_s64u10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpgt.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP1]], <vscale x 2 x i64> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -184,8 +182,7 @@ svbool_t test_svcmplt_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmplt_n_u64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmphi.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP1]], <vscale x 2 x i64> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -193,8 +190,7 @@ svbool_t test_svcmplt_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_u64u10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmphi.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP1]], <vscale x 2 x i64> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -312,15 +308,13 @@ svbool_t test_svcmplt_wide_u32(svbool_t pg, svuint32_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svcmplt_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpgt.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[OP1:%.*]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmplt_n_s8u10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpgt.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -332,8 +326,7 @@ svbool_t test_svcmplt_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svcmplt_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpgt.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 8 x i16> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -341,8 +334,7 @@ svbool_t test_svcmplt_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_s16u10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpgt.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 8 x i16> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -355,8 +347,7 @@ svbool_t test_svcmplt_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svcmplt_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpgt.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP1]], <vscale x 4 x i32> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -364,8 +355,7 @@ svbool_t test_svcmplt_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_s32u10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpgt.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP1]], <vscale x 4 x i32> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -377,15 +367,13 @@ svbool_t test_svcmplt_n_s32(svbool_t pg, svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svcmplt_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphi.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[OP1:%.*]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmplt_n_u8u10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmphi.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -397,8 +385,7 @@ svbool_t test_svcmplt_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svcmplt_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphi.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 8 x i16> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -406,8 +393,7 @@ svbool_t test_svcmplt_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_u16u10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmphi.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 8 x i16> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -420,8 +406,7 @@ svbool_t test_svcmplt_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svcmplt_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphi.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP1]], <vscale x 4 x i32> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -429,8 +414,7 @@ svbool_t test_svcmplt_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_u32u10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmphi.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP1]], <vscale x 4 x i32> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -500,8 +484,7 @@ svbool_t test_svcmplt_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svcmplt_n_f16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpgt.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -509,8 +492,7 @@ svbool_t test_svcmplt_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_f16u10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpgt.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 8 x half> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -523,8 +505,7 @@ svbool_t test_svcmplt_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svcmplt_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpgt.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -532,8 +513,7 @@ svbool_t test_svcmplt_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpgt.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP1]], <vscale x 4 x float> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -546,8 +526,7 @@ svbool_t test_svcmplt_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svcmplt_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpgt.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP1:%.*]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -555,8 +534,7 @@ svbool_t test_svcmplt_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmplt_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpgt.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP1]], <vscale x 2 x double> [[OP1:%.*]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -568,15 +546,13 @@ svbool_t test_svcmplt_n_f64(svbool_t pg, svfloat64_t op1, float64_t op2)
 
 // CHECK-LABEL: @test_svcmplt_wide_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmplt.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmplt_wide_n_s8u10__SVBool_tu10__SVInt8_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmplt.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -588,8 +564,7 @@ svbool_t test_svcmplt_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmplt_wide_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmplt.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -597,8 +572,7 @@ svbool_t test_svcmplt_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmplt_wide_n_s16u10__SVBool_tu11__SVInt16_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmplt.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -611,8 +585,7 @@ svbool_t test_svcmplt_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmplt_wide_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmplt.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -620,8 +593,7 @@ svbool_t test_svcmplt_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmplt_wide_n_s32u10__SVBool_tu11__SVInt32_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmplt.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -633,15 +605,13 @@ svbool_t test_svcmplt_wide_n_s32(svbool_t pg, svint32_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svcmplt_wide_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmplo.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmplt_wide_n_u8u10__SVBool_tu11__SVUint8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmplo.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -653,8 +623,7 @@ svbool_t test_svcmplt_wide_n_u8(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svcmplt_wide_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmplo.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -662,8 +631,7 @@ svbool_t test_svcmplt_wide_n_u8(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmplt_wide_n_u16u10__SVBool_tu12__SVUint16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmplo.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -676,8 +644,7 @@ svbool_t test_svcmplt_wide_n_u16(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svcmplt_wide_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmplo.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -685,8 +652,7 @@ svbool_t test_svcmplt_wide_n_u16(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmplt_wide_n_u32u10__SVBool_tu12__SVUint32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmplo.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpne.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpne.c
index bcc2f1637353..42bad6790261 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpne.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpne.c
@@ -161,8 +161,7 @@ svbool_t test_svcmpne_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svcmpne_n_s64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -170,8 +169,7 @@ svbool_t test_svcmpne_u64(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_s64u10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -184,8 +182,7 @@ svbool_t test_svcmpne_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpne_n_u64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -193,8 +190,7 @@ svbool_t test_svcmpne_n_s64(svbool_t pg, svint64_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_u64u10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -259,15 +255,13 @@ svbool_t test_svcmpne_wide_s32(svbool_t pg, svint32_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svcmpne_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmpne_n_s8u10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -279,8 +273,7 @@ svbool_t test_svcmpne_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svcmpne_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -288,8 +281,7 @@ svbool_t test_svcmpne_n_s8(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_s16u10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -302,8 +294,7 @@ svbool_t test_svcmpne_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svcmpne_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -311,8 +302,7 @@ svbool_t test_svcmpne_n_s16(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_s32u10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -324,15 +314,13 @@ svbool_t test_svcmpne_n_s32(svbool_t pg, svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svcmpne_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svcmpne_n_u8u10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -344,8 +332,7 @@ svbool_t test_svcmpne_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svcmpne_n_u16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -353,8 +340,7 @@ svbool_t test_svcmpne_n_u8(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_u16u10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -367,8 +353,7 @@ svbool_t test_svcmpne_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svcmpne_n_u32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -376,8 +361,7 @@ svbool_t test_svcmpne_n_u16(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_u32u10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -447,8 +431,7 @@ svbool_t test_svcmpne_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svcmpne_n_f16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpne.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -456,8 +439,7 @@ svbool_t test_svcmpne_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_f16u10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpne.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -470,8 +452,7 @@ svbool_t test_svcmpne_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svcmpne_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpne.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -479,8 +460,7 @@ svbool_t test_svcmpne_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpne.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -493,8 +473,7 @@ svbool_t test_svcmpne_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svcmpne_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpne.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -502,8 +481,7 @@ svbool_t test_svcmpne_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpne_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpne.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -515,15 +493,13 @@ svbool_t test_svcmpne_n_f64(svbool_t pg, svfloat64_t op1, float64_t op2)
 
 // CHECK-LABEL: @test_svcmpne_wide_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svcmpne_wide_n_s8u10__SVBool_tu10__SVInt8_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -535,8 +511,7 @@ svbool_t test_svcmpne_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpne_wide_n_s16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -544,8 +519,7 @@ svbool_t test_svcmpne_wide_n_s8(svbool_t pg, svint8_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpne_wide_n_s16u10__SVBool_tu11__SVInt16_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -558,8 +532,7 @@ svbool_t test_svcmpne_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CHECK-LABEL: @test_svcmpne_wide_n_s32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -567,8 +540,7 @@ svbool_t test_svcmpne_wide_n_s16(svbool_t pg, svint16_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svcmpne_wide_n_s32u10__SVBool_tu11__SVInt32_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpuo.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpuo.c
index 2593ff07bb55..e8742c168fb0 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpuo.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_cmpuo.c
@@ -74,8 +74,7 @@ svbool_t test_svcmpuo_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svcmpuo_n_f16(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpuo.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -83,8 +82,7 @@ svbool_t test_svcmpuo_f64(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpuo_n_f16u10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.fcmpuo.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -97,8 +95,7 @@ svbool_t test_svcmpuo_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svcmpuo_n_f32(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpuo.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -106,8 +103,7 @@ svbool_t test_svcmpuo_n_f16(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpuo_n_f32u10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.fcmpuo.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -120,8 +116,7 @@ svbool_t test_svcmpuo_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svcmpuo_n_f64(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpuo.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
@@ -129,8 +124,7 @@ svbool_t test_svcmpuo_n_f32(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svcmpuo_n_f64u10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.fcmpuo.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP2]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP3]]
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_div.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_div.c
index ab28142b91e1..4f384678c243 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_div.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_div.c
@@ -229,8 +229,7 @@ svuint64_t test_svdiv_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svdiv_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -238,8 +237,7 @@ svuint64_t test_svdiv_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -252,8 +250,7 @@ svint32_t test_svdiv_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svdiv_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -261,8 +258,7 @@ svint32_t test_svdiv_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -275,8 +271,7 @@ svint64_t test_svdiv_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svdiv_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -284,8 +279,7 @@ svint64_t test_svdiv_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -298,8 +292,7 @@ svuint32_t test_svdiv_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svdiv_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -307,8 +300,7 @@ svuint32_t test_svdiv_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -321,16 +313,14 @@ svuint64_t test_svdiv_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svdiv_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -342,16 +332,14 @@ svint32_t test_svdiv_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svdiv_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -363,16 +351,14 @@ svint64_t test_svdiv_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svdiv_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -384,16 +370,14 @@ svuint32_t test_svdiv_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svdiv_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -405,16 +389,14 @@ svuint64_t test_svdiv_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svdiv_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -426,16 +408,14 @@ svint32_t test_svdiv_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svdiv_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -447,16 +427,14 @@ svint64_t test_svdiv_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svdiv_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udiv.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -468,16 +446,14 @@ svuint32_t test_svdiv_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svdiv_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udiv.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -648,8 +624,7 @@ svfloat64_t test_svdiv_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svdiv_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -657,8 +632,7 @@ svfloat64_t test_svdiv_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -671,8 +645,7 @@ svfloat16_t test_svdiv_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svdiv_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -680,8 +653,7 @@ svfloat16_t test_svdiv_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -694,8 +666,7 @@ svfloat32_t test_svdiv_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svdiv_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -703,8 +674,7 @@ svfloat32_t test_svdiv_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -717,16 +687,14 @@ svfloat64_t test_svdiv_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svdiv_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -738,16 +706,14 @@ svfloat16_t test_svdiv_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svdiv_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -759,16 +725,14 @@ svfloat32_t test_svdiv_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svdiv_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -780,16 +744,14 @@ svfloat64_t test_svdiv_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svdiv_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -801,16 +763,14 @@ svfloat16_t test_svdiv_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svdiv_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -822,16 +782,14 @@ svfloat32_t test_svdiv_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svdiv_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdiv_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_divr.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_divr.c
index 451fa06e8a56..b703082f0b0e 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_divr.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_divr.c
@@ -229,8 +229,7 @@ svuint64_t test_svdivr_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CHECK-LABEL: @test_svdivr_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -238,8 +237,7 @@ svuint64_t test_svdivr_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -252,8 +250,7 @@ svint32_t test_svdivr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svdivr_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -261,8 +258,7 @@ svint32_t test_svdivr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -275,8 +271,7 @@ svint64_t test_svdivr_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svdivr_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -284,8 +279,7 @@ svint64_t test_svdivr_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -298,8 +292,7 @@ svuint32_t test_svdivr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svdivr_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -307,8 +300,7 @@ svuint32_t test_svdivr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -321,16 +313,14 @@ svuint64_t test_svdivr_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svdivr_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -342,16 +332,14 @@ svint32_t test_svdivr_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svdivr_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -363,16 +351,14 @@ svint64_t test_svdivr_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svdivr_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -384,16 +370,14 @@ svuint32_t test_svdivr_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svdivr_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -405,16 +389,14 @@ svuint64_t test_svdivr_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svdivr_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -426,16 +408,14 @@ svint32_t test_svdivr_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svdivr_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -447,16 +427,14 @@ svint64_t test_svdivr_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svdivr_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udivr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -468,16 +446,14 @@ svuint32_t test_svdivr_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svdivr_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udivr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -648,8 +624,7 @@ svfloat64_t test_svdivr_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svdivr_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -657,8 +632,7 @@ svfloat64_t test_svdivr_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -671,8 +645,7 @@ svfloat16_t test_svdivr_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svdivr_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -680,8 +653,7 @@ svfloat16_t test_svdivr_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -694,8 +666,7 @@ svfloat32_t test_svdivr_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svdivr_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -703,8 +674,7 @@ svfloat32_t test_svdivr_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -717,16 +687,14 @@ svfloat64_t test_svdivr_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svdivr_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -738,16 +706,14 @@ svfloat16_t test_svdivr_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svdivr_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -759,16 +725,14 @@ svfloat32_t test_svdivr_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svdivr_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -780,16 +744,14 @@ svfloat64_t test_svdivr_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svdivr_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -801,16 +763,14 @@ svfloat16_t test_svdivr_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svdivr_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -822,16 +782,14 @@ svfloat32_t test_svdivr_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svdivr_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdivr_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dot.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dot.c
index 9600d006aa41..b08c6be1529a 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dot.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dot.c
@@ -76,15 +76,13 @@ svuint64_t test_svdot_u64(svuint64_t op1, svuint16_t op2, svuint16_t op3)
 
 // CHECK-LABEL: @test_svdot_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdot.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdot_n_s32u11__SVInt32_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sdot.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -95,15 +93,13 @@ svint32_t test_svdot_n_s32(svint32_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svdot_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdot.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdot_n_s64u11__SVInt64_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sdot.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -114,15 +110,13 @@ svint64_t test_svdot_n_s64(svint64_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svdot_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udot.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdot_n_u32u12__SVUint32_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.udot.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -133,15 +127,13 @@ svuint32_t test_svdot_n_u32(svuint32_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svdot_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udot.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdot_n_u64u12__SVUint64_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.udot.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dup-bfloat.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dup-bfloat.c
index 146718d27814..b914fb6fc2cd 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dup-bfloat.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dup-bfloat.c
@@ -17,14 +17,12 @@
 
 // CHECK-LABEL: @test_svdup_n_bf16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.x.nxv8bf16(bfloat [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svdup_n_bf16u6__bf16(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x bfloat> poison, bfloat [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x bfloat> [[DOTSPLATINSERT]], <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.x.nxv8bf16(bfloat [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
 //
 svbfloat16_t test_svdup_n_bf16(bfloat16_t op) {
@@ -85,15 +83,13 @@ svbfloat16_t test_svdup_n_bf16_x(svbool_t pg, bfloat16_t op) {
 
 // CHECK-LABEL: @test_svdup_lane_bf16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.tbl.nxv8bf16(<vscale x 8 x bfloat> [[DATA:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svdup_lane_bf16u14__SVBFloat16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x bfloat> @llvm.aarch64.sve.tbl.nxv8bf16(<vscale x 8 x bfloat> [[DATA:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dup.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dup.c
index e8bdb3f0a327..a09e95262570 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dup.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dup.c
@@ -16,14 +16,12 @@
 
 // CHECK-LABEL: @test_svdup_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z15test_svdup_n_s8a(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
 //
 svint8_t test_svdup_n_s8(int8_t op)
@@ -33,14 +31,12 @@ svint8_t test_svdup_n_s8(int8_t op)
 
 // CHECK-LABEL: @test_svdup_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_s16s(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 svint16_t test_svdup_n_s16(int16_t op)
@@ -50,14 +46,12 @@ svint16_t test_svdup_n_s16(int16_t op)
 
 // CHECK-LABEL: @test_svdup_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_s32i(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 svint32_t test_svdup_n_s32(int32_t op)
@@ -67,14 +61,12 @@ svint32_t test_svdup_n_s32(int32_t op)
 
 // CHECK-LABEL: @test_svdup_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_s64l(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 svint64_t test_svdup_n_s64(int64_t op)
@@ -84,14 +76,12 @@ svint64_t test_svdup_n_s64(int64_t op)
 
 // CHECK-LABEL: @test_svdup_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z15test_svdup_n_u8h(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
 //
 svuint8_t test_svdup_n_u8(uint8_t op)
@@ -101,14 +91,12 @@ svuint8_t test_svdup_n_u8(uint8_t op)
 
 // CHECK-LABEL: @test_svdup_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_u16t(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 svuint16_t test_svdup_n_u16(uint16_t op)
@@ -118,14 +106,12 @@ svuint16_t test_svdup_n_u16(uint16_t op)
 
 // CHECK-LABEL: @test_svdup_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_u32j(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 svuint32_t test_svdup_n_u32(uint32_t op)
@@ -135,14 +121,12 @@ svuint32_t test_svdup_n_u32(uint32_t op)
 
 // CHECK-LABEL: @test_svdup_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_u64m(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 svuint64_t test_svdup_n_u64(uint64_t op)
@@ -152,14 +136,12 @@ svuint64_t test_svdup_n_u64(uint64_t op)
 
 // CHECK-LABEL: @test_svdup_n_f16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_f16Dh(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
 //
 svfloat16_t test_svdup_n_f16(float16_t op)
@@ -169,14 +151,12 @@ svfloat16_t test_svdup_n_f16(float16_t op)
 
 // CHECK-LABEL: @test_svdup_n_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_f32f(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
 //
 svfloat32_t test_svdup_n_f32(float32_t op)
@@ -186,14 +166,12 @@ svfloat32_t test_svdup_n_f32(float32_t op)
 
 // CHECK-LABEL: @test_svdup_n_f64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_f64d(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
 //
 svfloat64_t test_svdup_n_f64(float64_t op)
@@ -752,15 +730,13 @@ svfloat64_t test_svdup_n_f64_x(svbool_t pg, float64_t op)
 
 // CHECK-LABEL: @test_svdup_lane_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.tbl.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdup_lane_s8u10__SVInt8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.tbl.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -771,15 +747,13 @@ svint8_t test_svdup_lane_s8(svint8_t data, uint8_t index)
 
 // CHECK-LABEL: @test_svdup_lane_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.tbl.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_s16u11__SVInt16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.tbl.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -790,15 +764,13 @@ svint16_t test_svdup_lane_s16(svint16_t data, uint16_t index)
 
 // CHECK-LABEL: @test_svdup_lane_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.tbl.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_s32u11__SVInt32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.tbl.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -809,15 +781,13 @@ svint32_t test_svdup_lane_s32(svint32_t data, uint32_t index)
 
 // CHECK-LABEL: @test_svdup_lane_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.tbl.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_s64u11__SVInt64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.tbl.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -828,15 +798,13 @@ svint64_t test_svdup_lane_s64(svint64_t data, uint64_t index)
 
 // CHECK-LABEL: @test_svdup_lane_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.tbl.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svdup_lane_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.tbl.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -847,15 +815,13 @@ svuint8_t test_svdup_lane_u8(svuint8_t data, uint8_t index)
 
 // CHECK-LABEL: @test_svdup_lane_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.tbl.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.tbl.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -866,15 +832,13 @@ svuint16_t test_svdup_lane_u16(svuint16_t data, uint16_t index)
 
 // CHECK-LABEL: @test_svdup_lane_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.tbl.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.tbl.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -885,15 +849,13 @@ svuint32_t test_svdup_lane_u32(svuint32_t data, uint32_t index)
 
 // CHECK-LABEL: @test_svdup_lane_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.tbl.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.tbl.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -904,15 +866,13 @@ svuint64_t test_svdup_lane_u64(svuint64_t data, uint64_t index)
 
 // CHECK-LABEL: @test_svdup_lane_f16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.tbl.nxv8f16(<vscale x 8 x half> [[DATA:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_f16u13__SVFloat16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.tbl.nxv8f16(<vscale x 8 x half> [[DATA:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
 //
@@ -923,15 +883,13 @@ svfloat16_t test_svdup_lane_f16(svfloat16_t data, uint16_t index)
 
 // CHECK-LABEL: @test_svdup_lane_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.tbl.nxv4f32(<vscale x 4 x float> [[DATA:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_f32u13__SVFloat32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.tbl.nxv4f32(<vscale x 4 x float> [[DATA:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
@@ -942,15 +900,13 @@ svfloat32_t test_svdup_lane_f32(svfloat32_t data, uint32_t index)
 
 // CHECK-LABEL: @test_svdup_lane_f64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[INDEX:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[INDEX:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.tbl.nxv2f64(<vscale x 2 x double> [[DATA:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svdup_lane_f64u13__SVFloat64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[INDEX:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[INDEX:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.tbl.nxv2f64(<vscale x 2 x double> [[DATA:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
 //
@@ -961,14 +917,12 @@ svfloat64_t test_svdup_lane_f64(svfloat64_t data, uint64_t index)
 
 // CHECK-LABEL: @test_svdup_n_b8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i1> poison, i1 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i1> [[DOTSPLATINSERT]], <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.dup.x.nxv16i1(i1 [[OP:%.*]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP0]]
 //
 // CPP-CHECK-LABEL: @_Z15test_svdup_n_b8b(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i1> poison, i1 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i1> [[DOTSPLATINSERT]], <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.dup.x.nxv16i1(i1 [[OP:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP0]]
 //
 svbool_t test_svdup_n_b8(bool op)
@@ -978,15 +932,13 @@ svbool_t test_svdup_n_b8(bool op)
 
 // CHECK-LABEL: @test_svdup_n_b16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i1> poison, i1 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i1> [[DOTSPLATINSERT]], <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.dup.x.nxv8i1(i1 [[OP:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_b16b(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i1> poison, i1 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i1> [[DOTSPLATINSERT]], <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.dup.x.nxv8i1(i1 [[OP:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -997,15 +949,13 @@ svbool_t test_svdup_n_b16(bool op)
 
 // CHECK-LABEL: @test_svdup_n_b32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i1> poison, i1 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i1> [[DOTSPLATINSERT]], <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.dup.x.nxv4i1(i1 [[OP:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_b32b(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i1> poison, i1 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i1> [[DOTSPLATINSERT]], <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.dup.x.nxv4i1(i1 [[OP:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
@@ -1016,15 +966,13 @@ svbool_t test_svdup_n_b32(bool op)
 
 // CHECK-LABEL: @test_svdup_n_b64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i1> poison, i1 [[OP:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i1> [[DOTSPLATINSERT]], <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.dup.x.nxv2i1(i1 [[OP:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdup_n_b64b(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i1> poison, i1 [[OP:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i1> [[DOTSPLATINSERT]], <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.dup.x.nxv2i1(i1 [[OP:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dupq.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dupq.c
index 3c13080e14f7..effd3345303f 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dupq.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_dupq.c
@@ -568,8 +568,9 @@ svfloat64_t test_svdupq_n_f64(float64_t x0, float64_t x1)
 // CHECK-NEXT:    [[TMP16:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
 // CHECK-NEXT:    [[TMP17:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[TMP15]], i64 0)
 // CHECK-NEXT:    [[TMP18:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP17]], i64 0)
-// CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> [[TMP16]], <vscale x 16 x i8> [[TMP18]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 0, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP19]]
+// CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
+// CHECK-NEXT:    [[TMP20:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> [[TMP16]], <vscale x 16 x i8> [[TMP18]], <vscale x 2 x i64> [[TMP19]])
+// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP20]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svdupq_n_b8bbbbbbbbbbbbbbbb(
 // CPP-CHECK-NEXT:  entry:
@@ -608,8 +609,9 @@ svfloat64_t test_svdupq_n_f64(float64_t x0, float64_t x1)
 // CPP-CHECK-NEXT:    [[TMP16:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
 // CPP-CHECK-NEXT:    [[TMP17:%.*]] = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[TMP15]], i64 0)
 // CPP-CHECK-NEXT:    [[TMP18:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP17]], i64 0)
-// CPP-CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> [[TMP16]], <vscale x 16 x i8> [[TMP18]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 0, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP19]]
+// CPP-CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
+// CPP-CHECK-NEXT:    [[TMP20:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> [[TMP16]], <vscale x 16 x i8> [[TMP18]], <vscale x 2 x i64> [[TMP19]])
+// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP20]]
 //
 svbool_t test_svdupq_n_b8(bool x0, bool x1, bool x2, bool x3,
                           bool x4, bool x5, bool x6, bool x7,
@@ -641,9 +643,10 @@ svbool_t test_svdupq_n_b8(bool x0, bool x1, bool x2, bool x3,
 // CHECK-NEXT:    [[TMP16:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
 // CHECK-NEXT:    [[TMP17:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[TMP15]], i64 0)
 // CHECK-NEXT:    [[TMP18:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP17]], i64 0)
-// CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> [[TMP16]], <vscale x 8 x i16> [[TMP18]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 0, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-// CHECK-NEXT:    [[TMP20:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP19]])
-// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP20]]
+// CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
+// CHECK-NEXT:    [[TMP20:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> [[TMP16]], <vscale x 8 x i16> [[TMP18]], <vscale x 2 x i64> [[TMP19]])
+// CHECK-NEXT:    [[TMP21:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP20]])
+// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP21]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svdupq_n_b16bbbbbbbb(
 // CPP-CHECK-NEXT:  entry:
@@ -666,9 +669,10 @@ svbool_t test_svdupq_n_b8(bool x0, bool x1, bool x2, bool x3,
 // CPP-CHECK-NEXT:    [[TMP16:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
 // CPP-CHECK-NEXT:    [[TMP17:%.*]] = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[TMP15]], i64 0)
 // CPP-CHECK-NEXT:    [[TMP18:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP17]], i64 0)
-// CPP-CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> [[TMP16]], <vscale x 8 x i16> [[TMP18]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 0, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-// CPP-CHECK-NEXT:    [[TMP20:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP19]])
-// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP20]]
+// CPP-CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
+// CPP-CHECK-NEXT:    [[TMP20:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> [[TMP16]], <vscale x 8 x i16> [[TMP18]], <vscale x 2 x i64> [[TMP19]])
+// CPP-CHECK-NEXT:    [[TMP21:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP20]])
+// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP21]]
 //
 svbool_t test_svdupq_n_b16(bool x0, bool x1, bool x2, bool x3,
                            bool x4, bool x5, bool x6, bool x7)
@@ -690,9 +694,10 @@ svbool_t test_svdupq_n_b16(bool x0, bool x1, bool x2, bool x3,
 // CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
 // CHECK-NEXT:    [[TMP9:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[TMP7]], i64 0)
 // CHECK-NEXT:    [[TMP10:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP9]], i64 0)
-// CHECK-NEXT:    [[TMP11:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> [[TMP8]], <vscale x 4 x i32> [[TMP10]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 0, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-// CHECK-NEXT:    [[TMP12:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP11]])
-// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP12]]
+// CHECK-NEXT:    [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
+// CHECK-NEXT:    [[TMP12:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> [[TMP8]], <vscale x 4 x i32> [[TMP10]], <vscale x 2 x i64> [[TMP11]])
+// CHECK-NEXT:    [[TMP13:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP12]])
+// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP13]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svdupq_n_b32bbbb(
 // CPP-CHECK-NEXT:  entry:
@@ -707,9 +712,10 @@ svbool_t test_svdupq_n_b16(bool x0, bool x1, bool x2, bool x3,
 // CPP-CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
 // CPP-CHECK-NEXT:    [[TMP9:%.*]] = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[TMP7]], i64 0)
 // CPP-CHECK-NEXT:    [[TMP10:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP9]], i64 0)
-// CPP-CHECK-NEXT:    [[TMP11:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> [[TMP8]], <vscale x 4 x i32> [[TMP10]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 0, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-// CPP-CHECK-NEXT:    [[TMP12:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP11]])
-// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP12]]
+// CPP-CHECK-NEXT:    [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
+// CPP-CHECK-NEXT:    [[TMP12:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> [[TMP8]], <vscale x 4 x i32> [[TMP10]], <vscale x 2 x i64> [[TMP11]])
+// CPP-CHECK-NEXT:    [[TMP13:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP12]])
+// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP13]]
 //
 svbool_t test_svdupq_n_b32(bool x0, bool x1, bool x2, bool x3)
 {
@@ -726,9 +732,10 @@ svbool_t test_svdupq_n_b32(bool x0, bool x1, bool x2, bool x3)
 // CHECK-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
 // CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[TMP3]], i64 0)
 // CHECK-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP5]], i64 0)
-// CHECK-NEXT:    [[TMP7:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP4]], <vscale x 2 x i64> [[TMP6]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 0, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-// CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP7]])
-// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP8]]
+// CHECK-NEXT:    [[TMP7:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
+// CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP4]], <vscale x 2 x i64> [[TMP6]], <vscale x 2 x i64> [[TMP7]])
+// CHECK-NEXT:    [[TMP9:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP8]])
+// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP9]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svdupq_n_b64bb(
 // CPP-CHECK-NEXT:  entry:
@@ -739,9 +746,10 @@ svbool_t test_svdupq_n_b32(bool x0, bool x1, bool x2, bool x3)
 // CPP-CHECK-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
 // CPP-CHECK-NEXT:    [[TMP5:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[TMP3]], i64 0)
 // CPP-CHECK-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP5]], i64 0)
-// CPP-CHECK-NEXT:    [[TMP7:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP4]], <vscale x 2 x i64> [[TMP6]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 0, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-// CPP-CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP7]])
-// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP8]]
+// CPP-CHECK-NEXT:    [[TMP7:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 0)
+// CPP-CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP4]], <vscale x 2 x i64> [[TMP6]], <vscale x 2 x i64> [[TMP7]])
+// CPP-CHECK-NEXT:    [[TMP9:%.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP8]])
+// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP9]]
 //
 svbool_t test_svdupq_n_b64(bool x0, bool x1)
 {
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_eor.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_eor.c
index 01aacd10839e..66704fbdcec3 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_eor.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_eor.c
@@ -428,16 +428,14 @@ svuint64_t test_sveor_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_sveor_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_sveor_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_sveor_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_sveor_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_sveor_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_sveor_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_sveor_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_sveor_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_sveor_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_sveor_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_sveor_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_sveor_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_sveor_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_sveor_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_sveor_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_sveor_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_sveor_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_sveor_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_sveor_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_sveor_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_sveor_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_sveor_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_sveor_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_sveor_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_sveor_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_sveor_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_sveor_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_sveor_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_sveor_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_sveor_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_sveor_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_sveor_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_sveor_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_sveor_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_sveor_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_sveor_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_sveor_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_sveor_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_sveor_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_sveor_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_sveor_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_sveor_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_sveor_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_sveor_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_sveor_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_sveor_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_sveor_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_sveor_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_sveor_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_sveor_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_sveor_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_sveor_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_sveor_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveor_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_lsl.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_lsl.c
index 5b76a039d52d..cb212faa0c03 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_lsl.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_lsl.c
@@ -734,15 +734,13 @@ svuint32_t test_svlsl_wide_u32_x(svbool_t pg, svuint32_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svlsl_wide_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svlsl_wide_n_s8_mu10__SVBool_tu10__SVInt8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -754,16 +752,14 @@ svint8_t test_svlsl_wide_n_s8_m(svbool_t pg, svint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsl_wide_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svlsl_wide_n_s16_mu10__SVBool_tu11__SVInt16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -775,16 +771,14 @@ svint16_t test_svlsl_wide_n_s16_m(svbool_t pg, svint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsl_wide_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svlsl_wide_n_s32_mu10__SVBool_tu11__SVInt32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -795,16 +789,14 @@ svint32_t test_svlsl_wide_n_s32_m(svbool_t pg, svint32_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svlsl_wide_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.wide.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svlsl_wide_n_s8_zu10__SVBool_tu10__SVInt8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.wide.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -817,8 +809,7 @@ svint8_t test_svlsl_wide_n_s8_z(svbool_t pg, svint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsl_wide_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -826,8 +817,7 @@ svint8_t test_svlsl_wide_n_s8_z(svbool_t pg, svint8_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svlsl_wide_n_s16_zu10__SVBool_tu11__SVInt16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -840,8 +830,7 @@ svint16_t test_svlsl_wide_n_s16_z(svbool_t pg, svint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsl_wide_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -849,8 +838,7 @@ svint16_t test_svlsl_wide_n_s16_z(svbool_t pg, svint16_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svlsl_wide_n_s32_zu10__SVBool_tu11__SVInt32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -862,15 +850,13 @@ svint32_t test_svlsl_wide_n_s32_z(svbool_t pg, svint32_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svlsl_wide_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svlsl_wide_n_s8_xu10__SVBool_tu10__SVInt8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsl.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -882,16 +868,14 @@ svint8_t test_svlsl_wide_n_s8_x(svbool_t pg, svint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsl_wide_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svlsl_wide_n_s16_xu10__SVBool_tu11__SVInt16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -903,16 +887,14 @@ svint16_t test_svlsl_wide_n_s16_x(svbool_t pg, svint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsl_wide_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svlsl_wide_n_s32_xu10__SVBool_tu11__SVInt32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsl.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_lsr.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_lsr.c
index c512f43ddbed..3dd34eabf008 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_lsr.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_lsr.c
@@ -375,15 +375,13 @@ svuint32_t test_svlsr_wide_u32_x(svbool_t pg, svuint32_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svlsr_wide_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svlsr_wide_n_u8_mu10__SVBool_tu11__SVUint8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -395,16 +393,14 @@ svuint8_t test_svlsr_wide_n_u8_m(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsr_wide_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svlsr_wide_n_u16_mu10__SVBool_tu12__SVUint16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -416,16 +412,14 @@ svuint16_t test_svlsr_wide_n_u16_m(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsr_wide_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svlsr_wide_n_u32_mu10__SVBool_tu12__SVUint32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -436,16 +430,14 @@ svuint32_t test_svlsr_wide_n_u32_m(svbool_t pg, svuint32_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svlsr_wide_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.wide.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svlsr_wide_n_u8_zu10__SVBool_tu11__SVUint8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.wide.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -458,8 +450,7 @@ svuint8_t test_svlsr_wide_n_u8_z(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsr_wide_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -467,8 +458,7 @@ svuint8_t test_svlsr_wide_n_u8_z(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svlsr_wide_n_u16_zu10__SVBool_tu12__SVUint16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -481,8 +471,7 @@ svuint16_t test_svlsr_wide_n_u16_z(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsr_wide_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -490,8 +479,7 @@ svuint16_t test_svlsr_wide_n_u16_z(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CPP-CHECK-LABEL: @_Z23test_svlsr_wide_n_u32_zu10__SVBool_tu12__SVUint32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -503,15 +491,13 @@ svuint32_t test_svlsr_wide_n_u32_z(svbool_t pg, svuint32_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svlsr_wide_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z22test_svlsr_wide_n_u8_xu10__SVBool_tu11__SVUint8_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.lsr.wide.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -523,16 +509,14 @@ svuint8_t test_svlsr_wide_n_u8_x(svbool_t pg, svuint8_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsr_wide_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svlsr_wide_n_u16_xu10__SVBool_tu12__SVUint16_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsr.wide.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -544,16 +528,14 @@ svuint16_t test_svlsr_wide_n_u16_x(svbool_t pg, svuint16_t op1, uint64_t op2)
 // CHECK-LABEL: @test_svlsr_wide_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svlsr_wide_n_u32_xu10__SVBool_tu12__SVUint32_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.lsr.wide.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mad.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mad.c
index 01a29a16e098..269d3918d026 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mad.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mad.c
@@ -428,16 +428,14 @@ svuint64_t test_svmad_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2, svuint6
 
 // CHECK-LABEL: @test_svmad_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmad_n_s8_zu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svmad_n_s8_z(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmad_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svmad_n_s8_z(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s16_zu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svmad_n_s16_z(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmad_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svmad_n_s16_z(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s32_zu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svmad_n_s32_z(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmad_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svmad_n_s32_z(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s64_zu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svmad_n_s64_z(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmad_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmad_n_u8_zu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svmad_n_u8_z(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmad_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svmad_n_u8_z(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u16_zu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svmad_n_u16_z(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmad_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svmad_n_u16_z(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u32_zu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svmad_n_u32_z(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmad_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svmad_n_u32_z(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u64_zu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svmad_n_u64_z(svbool_t pg, svuint64_t op1, svuint64_t op2, uint6
 
 // CHECK-LABEL: @test_svmad_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmad_n_s8_mu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svmad_n_s8_m(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmad_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s16_mu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svmad_n_s16_m(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmad_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s32_mu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svmad_n_s32_m(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmad_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s64_mu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svmad_n_s64_m(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmad_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmad_n_u8_mu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svmad_n_u8_m(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmad_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u16_mu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svmad_n_u16_m(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmad_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u32_mu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svmad_n_u32_m(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmad_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u64_mu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svmad_n_u64_m(svbool_t pg, svuint64_t op1, svuint64_t op2, uint6
 
 // CHECK-LABEL: @test_svmad_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmad_n_s8_xu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svmad_n_s8_x(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmad_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s16_xu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svmad_n_s16_x(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmad_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s32_xu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svmad_n_s32_x(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmad_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_s64_xu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svmad_n_s64_x(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmad_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmad_n_u8_xu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svmad_n_u8_x(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmad_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u16_xu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svmad_n_u16_x(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmad_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u32_xu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svmad_n_u32_x(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmad_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_u64_xu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svmad_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfl
 // CHECK-LABEL: @test_svmad_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svmad_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfl
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f16_zu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svmad_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmad_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svmad_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f32_zu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svmad_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmad_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svmad_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f64_zu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svmad_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, fl
 // CHECK-LABEL: @test_svmad_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f16_mu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svmad_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmad_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f32_mu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svmad_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmad_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f64_mu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svmad_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, fl
 // CHECK-LABEL: @test_svmad_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f16_xu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svmad_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmad_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f32_xu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svmad_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmad_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmad_n_f64_xu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_max.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_max.c
index 14cb35afe04f..3ba13569c178 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_max.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_max.c
@@ -428,16 +428,14 @@ svuint64_t test_svmax_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svmax_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmax_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svmax_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmax_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svmax_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svmax_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmax_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svmax_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svmax_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmax_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svmax_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svmax_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmax_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmax_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svmax_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmax_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svmax_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svmax_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmax_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svmax_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svmax_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmax_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svmax_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svmax_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svmax_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmax_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svmax_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmax_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svmax_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmax_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svmax_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmax_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svmax_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmax_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmax_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svmax_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmax_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svmax_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmax_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svmax_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmax_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svmax_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svmax_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmax_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smax.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svmax_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmax_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svmax_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmax_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svmax_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmax_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svmax_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmax_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmax_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umax.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svmax_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmax_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umax.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svmax_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmax_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umax.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svmax_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmax_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umax.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svmax_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svmax_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svmax_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svmax_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmax_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svmax_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svmax_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmax_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svmax_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svmax_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmax_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svmax_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmax_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svmax_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmax_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svmax_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmax_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svmax_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmax_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svmax_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmax_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmax_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_maxnm.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_maxnm.c
index 4759a69b7863..3ff6c42b20e2 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_maxnm.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_maxnm.c
@@ -176,8 +176,7 @@ svfloat64_t test_svmaxnm_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -185,8 +184,7 @@ svfloat64_t test_svmaxnm_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -199,8 +197,7 @@ svfloat16_t test_svmaxnm_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -208,8 +205,7 @@ svfloat16_t test_svmaxnm_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -222,8 +218,7 @@ svfloat32_t test_svmaxnm_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -231,8 +226,7 @@ svfloat32_t test_svmaxnm_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -245,16 +239,14 @@ svfloat64_t test_svmaxnm_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -266,16 +258,14 @@ svfloat16_t test_svmaxnm_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -287,16 +277,14 @@ svfloat32_t test_svmaxnm_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -308,16 +296,14 @@ svfloat64_t test_svmaxnm_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -329,16 +315,14 @@ svfloat16_t test_svmaxnm_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -350,16 +334,14 @@ svfloat32_t test_svmaxnm_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmaxnm_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svmaxnm_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_min.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_min.c
index bf4657194b88..d4c15435ba1b 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_min.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_min.c
@@ -428,16 +428,14 @@ svuint64_t test_svmin_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svmin_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmin_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svmin_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmin_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svmin_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svmin_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmin_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svmin_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svmin_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmin_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svmin_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svmin_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmin_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmin_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svmin_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmin_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svmin_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svmin_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmin_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svmin_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svmin_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmin_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svmin_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svmin_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svmin_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmin_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svmin_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmin_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svmin_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmin_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svmin_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmin_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svmin_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmin_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmin_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svmin_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmin_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svmin_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmin_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svmin_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmin_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svmin_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svmin_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmin_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smin.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svmin_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmin_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svmin_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmin_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svmin_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmin_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svmin_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmin_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmin_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umin.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svmin_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmin_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umin.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svmin_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmin_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umin.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svmin_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmin_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svmin_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svmin_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svmin_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svmin_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmin_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svmin_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svmin_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmin_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svmin_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svmin_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmin_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svmin_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmin_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svmin_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmin_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svmin_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmin_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svmin_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmin_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svmin_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmin_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmin_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_minnm.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_minnm.c
index 6807d56a122e..e1a353ea427e 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_minnm.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_minnm.c
@@ -176,8 +176,7 @@ svfloat64_t test_svminnm_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svminnm_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -185,8 +184,7 @@ svfloat64_t test_svminnm_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -199,8 +197,7 @@ svfloat16_t test_svminnm_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svminnm_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -208,8 +205,7 @@ svfloat16_t test_svminnm_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -222,8 +218,7 @@ svfloat32_t test_svminnm_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svminnm_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -231,8 +226,7 @@ svfloat32_t test_svminnm_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -245,16 +239,14 @@ svfloat64_t test_svminnm_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svminnm_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -266,16 +258,14 @@ svfloat16_t test_svminnm_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svminnm_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -287,16 +277,14 @@ svfloat32_t test_svminnm_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svminnm_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -308,16 +296,14 @@ svfloat64_t test_svminnm_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svminnm_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -329,16 +315,14 @@ svfloat16_t test_svminnm_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svminnm_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -350,16 +334,14 @@ svfloat32_t test_svminnm_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svminnm_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svminnm_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mla.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mla.c
index a7c8165ad8bc..9d16676a7bb2 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mla.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mla.c
@@ -428,16 +428,14 @@ svuint64_t test_svmla_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2, svuint6
 
 // CHECK-LABEL: @test_svmla_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmla_n_s8_zu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svmla_n_s8_z(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmla_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svmla_n_s8_z(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s16_zu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svmla_n_s16_z(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmla_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svmla_n_s16_z(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s32_zu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svmla_n_s32_z(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmla_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svmla_n_s32_z(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s64_zu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svmla_n_s64_z(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmla_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmla_n_u8_zu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svmla_n_u8_z(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmla_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svmla_n_u8_z(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u16_zu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svmla_n_u16_z(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmla_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svmla_n_u16_z(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u32_zu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svmla_n_u32_z(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmla_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svmla_n_u32_z(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u64_zu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svmla_n_u64_z(svbool_t pg, svuint64_t op1, svuint64_t op2, uint6
 
 // CHECK-LABEL: @test_svmla_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmla_n_s8_mu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svmla_n_s8_m(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmla_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s16_mu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svmla_n_s16_m(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmla_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s32_mu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svmla_n_s32_m(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmla_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s64_mu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svmla_n_s64_m(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmla_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmla_n_u8_mu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svmla_n_u8_m(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmla_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u16_mu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svmla_n_u16_m(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmla_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u32_mu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svmla_n_u32_m(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmla_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u64_mu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svmla_n_u64_m(svbool_t pg, svuint64_t op1, svuint64_t op2, uint6
 
 // CHECK-LABEL: @test_svmla_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmla_n_s8_xu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svmla_n_s8_x(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmla_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s16_xu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svmla_n_s16_x(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmla_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s32_xu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svmla_n_s32_x(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmla_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_s64_xu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svmla_n_s64_x(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmla_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmla_n_u8_xu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svmla_n_u8_x(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmla_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u16_xu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svmla_n_u16_x(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmla_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u32_xu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svmla_n_u32_x(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmla_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_u64_xu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svmla_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfl
 // CHECK-LABEL: @test_svmla_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svmla_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfl
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f16_zu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svmla_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmla_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svmla_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f32_zu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svmla_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmla_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svmla_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f64_zu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svmla_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, fl
 // CHECK-LABEL: @test_svmla_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f16_mu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svmla_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmla_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f32_mu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svmla_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmla_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f64_mu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svmla_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, fl
 // CHECK-LABEL: @test_svmla_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f16_xu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svmla_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmla_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f32_xu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svmla_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmla_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmla_n_f64_xu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mls.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mls.c
index 0744c50c029f..badd6eca3660 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mls.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mls.c
@@ -428,16 +428,14 @@ svuint64_t test_svmls_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2, svuint6
 
 // CHECK-LABEL: @test_svmls_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmls_n_s8_zu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svmls_n_s8_z(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmls_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svmls_n_s8_z(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s16_zu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svmls_n_s16_z(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmls_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svmls_n_s16_z(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s32_zu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svmls_n_s32_z(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmls_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svmls_n_s32_z(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s64_zu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svmls_n_s64_z(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmls_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmls_n_u8_zu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svmls_n_u8_z(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmls_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svmls_n_u8_z(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u16_zu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svmls_n_u16_z(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmls_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svmls_n_u16_z(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u32_zu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svmls_n_u32_z(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmls_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svmls_n_u32_z(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u64_zu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svmls_n_u64_z(svbool_t pg, svuint64_t op1, svuint64_t op2, uint6
 
 // CHECK-LABEL: @test_svmls_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmls_n_s8_mu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svmls_n_s8_m(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmls_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s16_mu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svmls_n_s16_m(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmls_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s32_mu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svmls_n_s32_m(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmls_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s64_mu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svmls_n_s64_m(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmls_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmls_n_u8_mu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svmls_n_u8_m(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmls_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u16_mu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svmls_n_u16_m(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmls_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u32_mu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svmls_n_u32_m(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmls_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u64_mu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svmls_n_u64_m(svbool_t pg, svuint64_t op1, svuint64_t op2, uint6
 
 // CHECK-LABEL: @test_svmls_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmls_n_s8_xu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svmls_n_s8_x(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmls_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s16_xu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svmls_n_s16_x(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmls_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s32_xu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svmls_n_s32_x(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmls_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_s64_xu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svmls_n_s64_x(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmls_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmls_n_u8_xu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svmls_n_u8_x(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmls_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u16_xu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svmls_n_u16_x(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmls_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u32_xu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svmls_n_u32_x(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmls_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_u64_xu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svmls_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfl
 // CHECK-LABEL: @test_svmls_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svmls_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfl
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f16_zu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svmls_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmls_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svmls_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f32_zu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svmls_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmls_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svmls_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f64_zu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svmls_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, fl
 // CHECK-LABEL: @test_svmls_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f16_mu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svmls_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmls_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f32_mu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svmls_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmls_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f64_mu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svmls_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, fl
 // CHECK-LABEL: @test_svmls_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f16_xu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svmls_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmls_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f32_xu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svmls_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmls_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmls_n_f64_xu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_msb.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_msb.c
index fc5f6f4141c9..3d90b3703bbf 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_msb.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_msb.c
@@ -428,16 +428,14 @@ svuint64_t test_svmsb_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2, svuint6
 
 // CHECK-LABEL: @test_svmsb_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmsb_n_s8_zu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svmsb_n_s8_z(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmsb_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svmsb_n_s8_z(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s16_zu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svmsb_n_s16_z(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmsb_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svmsb_n_s16_z(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s32_zu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svmsb_n_s32_z(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmsb_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svmsb_n_s32_z(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s64_zu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svmsb_n_s64_z(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmsb_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmsb_n_u8_zu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svmsb_n_u8_z(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmsb_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svmsb_n_u8_z(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u16_zu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svmsb_n_u16_z(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmsb_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svmsb_n_u16_z(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u32_zu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svmsb_n_u32_z(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmsb_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svmsb_n_u32_z(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u64_zu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svmsb_n_u64_z(svbool_t pg, svuint64_t op1, svuint64_t op2, uint6
 
 // CHECK-LABEL: @test_svmsb_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmsb_n_s8_mu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svmsb_n_s8_m(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmsb_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s16_mu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svmsb_n_s16_m(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmsb_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s32_mu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svmsb_n_s32_m(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmsb_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s64_mu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svmsb_n_s64_m(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmsb_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmsb_n_u8_mu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svmsb_n_u8_m(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmsb_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u16_mu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svmsb_n_u16_m(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmsb_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u32_mu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svmsb_n_u32_m(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmsb_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u64_mu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svmsb_n_u64_m(svbool_t pg, svuint64_t op1, svuint64_t op2, uint6
 
 // CHECK-LABEL: @test_svmsb_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmsb_n_s8_xu10__SVBool_tu10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svmsb_n_s8_x(svbool_t pg, svint8_t op1, svint8_t op2, int8_t op3)
 // CHECK-LABEL: @test_svmsb_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s16_xu10__SVBool_tu11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svmsb_n_s16_x(svbool_t pg, svint16_t op1, svint16_t op2, int16_t
 // CHECK-LABEL: @test_svmsb_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s32_xu10__SVBool_tu11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svmsb_n_s32_x(svbool_t pg, svint32_t op1, svint32_t op2, int32_t
 // CHECK-LABEL: @test_svmsb_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_s64_xu10__SVBool_tu11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svmsb_n_s64_x(svbool_t pg, svint64_t op1, svint64_t op2, int64_t
 
 // CHECK-LABEL: @test_svmsb_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmsb_n_u8_xu10__SVBool_tu11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svmsb_n_u8_x(svbool_t pg, svuint8_t op1, svuint8_t op2, uint8_t o
 // CHECK-LABEL: @test_svmsb_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u16_xu10__SVBool_tu12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svmsb_n_u16_x(svbool_t pg, svuint16_t op1, svuint16_t op2, uint1
 // CHECK-LABEL: @test_svmsb_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u32_xu10__SVBool_tu12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svmsb_n_u32_x(svbool_t pg, svuint32_t op1, svuint32_t op2, uint3
 // CHECK-LABEL: @test_svmsb_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_u64_xu10__SVBool_tu12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svmsb_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfl
 // CHECK-LABEL: @test_svmsb_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svmsb_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svfl
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f16_zu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svmsb_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmsb_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svmsb_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f32_zu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svmsb_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmsb_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svmsb_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f64_zu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svmsb_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, fl
 // CHECK-LABEL: @test_svmsb_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f16_mu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svmsb_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmsb_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f32_mu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svmsb_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmsb_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f64_mu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svmsb_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, fl
 // CHECK-LABEL: @test_svmsb_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f16_xu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svmsb_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, fl
 // CHECK-LABEL: @test_svmsb_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f32_xu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svmsb_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, fl
 // CHECK-LABEL: @test_svmsb_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmsb_n_f64_xu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mul.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mul.c
index 040dfea9bda2..23d1a8789173 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mul.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mul.c
@@ -428,16 +428,14 @@ svuint64_t test_svmul_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svmul_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmul_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svmul_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmul_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svmul_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svmul_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmul_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svmul_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svmul_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmul_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svmul_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svmul_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmul_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmul_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svmul_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmul_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svmul_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svmul_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmul_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svmul_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svmul_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmul_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svmul_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svmul_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svmul_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmul_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svmul_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmul_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svmul_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmul_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svmul_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmul_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svmul_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmul_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmul_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svmul_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmul_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svmul_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmul_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svmul_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmul_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svmul_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svmul_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmul_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svmul_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmul_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svmul_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmul_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svmul_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmul_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svmul_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmul_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svmul_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.mul.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svmul_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmul_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svmul_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmul_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svmul_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmul_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svmul_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svmul_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svmul_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svmul_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmul_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svmul_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svmul_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmul_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svmul_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svmul_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmul_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svmul_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmul_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svmul_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmul_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svmul_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmul_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svmul_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmul_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svmul_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmul_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmul_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mulh.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mulh.c
index 366169ac563a..68827598b367 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mulh.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mulh.c
@@ -428,16 +428,14 @@ svuint64_t test_svmulh_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svmulh_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmulh_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svmulh_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmulh_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svmulh_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svmulh_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmulh_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svmulh_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svmulh_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmulh_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svmulh_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svmulh_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmulh_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmulh_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svmulh_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmulh_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svmulh_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svmulh_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmulh_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svmulh_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svmulh_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmulh_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svmulh_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svmulh_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svmulh_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmulh_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svmulh_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmulh_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svmulh_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmulh_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svmulh_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmulh_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svmulh_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmulh_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmulh_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svmulh_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmulh_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svmulh_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmulh_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svmulh_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmulh_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svmulh_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svmulh_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmulh_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.smulh.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svmulh_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svmulh_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svmulh_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svmulh_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svmulh_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svmulh_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svmulh_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svmulh_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmulh_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.umulh.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svmulh_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svmulh_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umulh.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svmulh_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svmulh_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umulh.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svmulh_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svmulh_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulh_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umulh.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mulx.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mulx.c
index 23879919d93e..86a972b2505e 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mulx.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_mulx.c
@@ -176,8 +176,7 @@ svfloat64_t test_svmulx_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svmulx_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -185,8 +184,7 @@ svfloat64_t test_svmulx_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -199,8 +197,7 @@ svfloat16_t test_svmulx_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmulx_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -208,8 +205,7 @@ svfloat16_t test_svmulx_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -222,8 +218,7 @@ svfloat32_t test_svmulx_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmulx_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -231,8 +226,7 @@ svfloat32_t test_svmulx_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -245,16 +239,14 @@ svfloat64_t test_svmulx_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmulx_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -266,16 +258,14 @@ svfloat16_t test_svmulx_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmulx_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -287,16 +277,14 @@ svfloat32_t test_svmulx_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmulx_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -308,16 +296,14 @@ svfloat64_t test_svmulx_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svmulx_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -329,16 +315,14 @@ svfloat16_t test_svmulx_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svmulx_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -350,16 +334,14 @@ svfloat32_t test_svmulx_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svmulx_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svmulx_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmad.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmad.c
index efe6a72d0aca..5e708bdc2604 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmad.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmad.c
@@ -176,8 +176,7 @@ svfloat64_t test_svnmad_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svf
 // CHECK-LABEL: @test_svnmad_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -185,8 +184,7 @@ svfloat64_t test_svnmad_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svf
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f16_zu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -199,8 +197,7 @@ svfloat16_t test_svnmad_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmad_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -208,8 +205,7 @@ svfloat16_t test_svnmad_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f32_zu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -222,8 +218,7 @@ svfloat32_t test_svnmad_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmad_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -231,8 +226,7 @@ svfloat32_t test_svnmad_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f64_zu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -245,16 +239,14 @@ svfloat64_t test_svnmad_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, f
 // CHECK-LABEL: @test_svnmad_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f16_mu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -266,16 +258,14 @@ svfloat16_t test_svnmad_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmad_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f32_mu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -287,16 +277,14 @@ svfloat32_t test_svnmad_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmad_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f64_mu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -308,16 +296,14 @@ svfloat64_t test_svnmad_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, f
 // CHECK-LABEL: @test_svnmad_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f16_xu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -329,16 +315,14 @@ svfloat16_t test_svnmad_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmad_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f32_xu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -350,16 +334,14 @@ svfloat32_t test_svnmad_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmad_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmad_n_f64_xu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmla.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmla.c
index 6fe517250af8..a2ed49a4633b 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmla.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmla.c
@@ -176,8 +176,7 @@ svfloat64_t test_svnmla_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svf
 // CHECK-LABEL: @test_svnmla_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -185,8 +184,7 @@ svfloat64_t test_svnmla_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svf
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f16_zu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -199,8 +197,7 @@ svfloat16_t test_svnmla_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmla_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -208,8 +205,7 @@ svfloat16_t test_svnmla_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f32_zu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -222,8 +218,7 @@ svfloat32_t test_svnmla_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmla_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -231,8 +226,7 @@ svfloat32_t test_svnmla_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f64_zu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -245,16 +239,14 @@ svfloat64_t test_svnmla_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, f
 // CHECK-LABEL: @test_svnmla_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f16_mu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -266,16 +258,14 @@ svfloat16_t test_svnmla_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmla_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f32_mu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -287,16 +277,14 @@ svfloat32_t test_svnmla_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmla_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f64_mu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -308,16 +296,14 @@ svfloat64_t test_svnmla_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, f
 // CHECK-LABEL: @test_svnmla_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f16_xu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -329,16 +315,14 @@ svfloat16_t test_svnmla_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmla_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f32_xu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -350,16 +334,14 @@ svfloat32_t test_svnmla_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmla_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmla_n_f64_xu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmls.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmls.c
index 17716efe8cce..c4698f529bdb 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmls.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmls.c
@@ -176,8 +176,7 @@ svfloat64_t test_svnmls_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svf
 // CHECK-LABEL: @test_svnmls_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -185,8 +184,7 @@ svfloat64_t test_svnmls_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svf
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f16_zu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -199,8 +197,7 @@ svfloat16_t test_svnmls_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmls_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -208,8 +205,7 @@ svfloat16_t test_svnmls_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f32_zu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -222,8 +218,7 @@ svfloat32_t test_svnmls_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmls_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -231,8 +226,7 @@ svfloat32_t test_svnmls_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f64_zu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -245,16 +239,14 @@ svfloat64_t test_svnmls_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, f
 // CHECK-LABEL: @test_svnmls_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f16_mu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -266,16 +258,14 @@ svfloat16_t test_svnmls_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmls_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f32_mu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -287,16 +277,14 @@ svfloat32_t test_svnmls_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmls_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f64_mu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -308,16 +296,14 @@ svfloat64_t test_svnmls_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, f
 // CHECK-LABEL: @test_svnmls_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f16_xu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -329,16 +315,14 @@ svfloat16_t test_svnmls_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmls_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f32_xu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -350,16 +334,14 @@ svfloat32_t test_svnmls_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmls_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmls_n_f64_xu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmsb.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmsb.c
index e0a047612b8f..c16c0cfe16b8 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmsb.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_nmsb.c
@@ -176,8 +176,7 @@ svfloat64_t test_svnmsb_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svf
 // CHECK-LABEL: @test_svnmsb_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -185,8 +184,7 @@ svfloat64_t test_svnmsb_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2, svf
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f16_zu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -199,8 +197,7 @@ svfloat16_t test_svnmsb_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmsb_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -208,8 +205,7 @@ svfloat16_t test_svnmsb_n_f16_z(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f32_zu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -222,8 +218,7 @@ svfloat32_t test_svnmsb_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmsb_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -231,8 +226,7 @@ svfloat32_t test_svnmsb_n_f32_z(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f64_zu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -245,16 +239,14 @@ svfloat64_t test_svnmsb_n_f64_z(svbool_t pg, svfloat64_t op1, svfloat64_t op2, f
 // CHECK-LABEL: @test_svnmsb_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f16_mu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -266,16 +258,14 @@ svfloat16_t test_svnmsb_n_f16_m(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmsb_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f32_mu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -287,16 +277,14 @@ svfloat32_t test_svnmsb_n_f32_m(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmsb_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f64_mu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -308,16 +296,14 @@ svfloat64_t test_svnmsb_n_f64_m(svbool_t pg, svfloat64_t op1, svfloat64_t op2, f
 // CHECK-LABEL: @test_svnmsb_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f16_xu10__SVBool_tu13__SVFloat16_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -329,16 +315,14 @@ svfloat16_t test_svnmsb_n_f16_x(svbool_t pg, svfloat16_t op1, svfloat16_t op2, f
 // CHECK-LABEL: @test_svnmsb_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f32_xu10__SVBool_tu13__SVFloat32_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[OP2:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -350,16 +334,14 @@ svfloat32_t test_svnmsb_n_f32_x(svbool_t pg, svfloat32_t op1, svfloat32_t op2, f
 // CHECK-LABEL: @test_svnmsb_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svnmsb_n_f64_xu10__SVBool_tu13__SVFloat64_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_orr.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_orr.c
index d4a63eed7f87..2a8d656a7830 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_orr.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_orr.c
@@ -428,16 +428,14 @@ svuint64_t test_svorr_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svorr_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svorr_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svorr_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svorr_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svorr_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svorr_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svorr_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svorr_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svorr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svorr_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svorr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svorr_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svorr_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svorr_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svorr_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svorr_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svorr_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svorr_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svorr_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svorr_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svorr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svorr_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svorr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svorr_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svorr_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svorr_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svorr_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svorr_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svorr_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svorr_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svorr_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svorr_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svorr_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svorr_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svorr_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svorr_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svorr_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svorr_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svorr_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svorr_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svorr_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svorr_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svorr_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svorr_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svorr_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svorr_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svorr_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svorr_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svorr_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svorr_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svorr_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svorr_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svorr_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svorr_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svorr_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svorr_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svorr_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svorr_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svorr_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svorr_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_qadd.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_qadd.c
index d60eb754077a..08e0c071952a 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_qadd.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_qadd.c
@@ -136,15 +136,13 @@ svuint64_t test_svqadd_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svqadd_n_s8u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -155,15 +153,13 @@ svint8_t test_svqadd_n_s8(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqadd_n_s16u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -174,15 +170,13 @@ svint16_t test_svqadd_n_s16(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqadd_n_s32u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -193,15 +187,13 @@ svint32_t test_svqadd_n_s32(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqadd_n_s64u11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -212,15 +204,13 @@ svint64_t test_svqadd_n_s64(svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svqadd_n_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -231,15 +221,13 @@ svuint8_t test_svqadd_n_u8(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqadd_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -250,15 +238,13 @@ svuint16_t test_svqadd_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqadd_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -269,15 +255,13 @@ svuint32_t test_svqadd_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqadd_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_qsub.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_qsub.c
index d0d477a0febe..8ec7f0f377dd 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_qsub.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_qsub.c
@@ -136,15 +136,13 @@ svuint64_t test_svqsub_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svqsub_n_s8u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -155,15 +153,13 @@ svint8_t test_svqsub_n_s8(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqsub_n_s16u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -174,15 +170,13 @@ svint16_t test_svqsub_n_s16(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqsub_n_s32u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -193,15 +187,13 @@ svint32_t test_svqsub_n_s32(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqsub_n_s64u11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -212,15 +204,13 @@ svint64_t test_svqsub_n_s64(svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svqsub_n_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -231,15 +221,13 @@ svuint8_t test_svqsub_n_u8(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqsub_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -250,15 +238,13 @@ svuint16_t test_svqsub_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqsub_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -269,15 +255,13 @@ svuint32_t test_svqsub_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svqsub_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_scale.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_scale.c
index f0e8060513dd..035adedd821e 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_scale.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_scale.c
@@ -176,8 +176,7 @@ svfloat64_t test_svscale_f64_x(svbool_t pg, svfloat64_t op1, svint64_t op2)
 // CHECK-LABEL: @test_svscale_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fscale.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -185,8 +184,7 @@ svfloat64_t test_svscale_f64_x(svbool_t pg, svfloat64_t op1, svint64_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f16_zu10__SVBool_tu13__SVFloat16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fscale.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -199,8 +197,7 @@ svfloat16_t test_svscale_n_f16_z(svbool_t pg, svfloat16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svscale_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fscale.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -208,8 +205,7 @@ svfloat16_t test_svscale_n_f16_z(svbool_t pg, svfloat16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f32_zu10__SVBool_tu13__SVFloat32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fscale.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -222,8 +218,7 @@ svfloat32_t test_svscale_n_f32_z(svbool_t pg, svfloat32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svscale_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fscale.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -231,8 +226,7 @@ svfloat32_t test_svscale_n_f32_z(svbool_t pg, svfloat32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f64_zu10__SVBool_tu13__SVFloat64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fscale.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -245,16 +239,14 @@ svfloat64_t test_svscale_n_f64_z(svbool_t pg, svfloat64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svscale_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fscale.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f16_mu10__SVBool_tu13__SVFloat16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fscale.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -266,16 +258,14 @@ svfloat16_t test_svscale_n_f16_m(svbool_t pg, svfloat16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svscale_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fscale.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f32_mu10__SVBool_tu13__SVFloat32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fscale.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -287,16 +277,14 @@ svfloat32_t test_svscale_n_f32_m(svbool_t pg, svfloat32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svscale_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fscale.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f64_mu10__SVBool_tu13__SVFloat64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fscale.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -308,16 +296,14 @@ svfloat64_t test_svscale_n_f64_m(svbool_t pg, svfloat64_t op1, int64_t op2)
 // CHECK-LABEL: @test_svscale_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fscale.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f16_xu10__SVBool_tu13__SVFloat16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fscale.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -329,16 +315,14 @@ svfloat16_t test_svscale_n_f16_x(svbool_t pg, svfloat16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svscale_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fscale.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f32_xu10__SVBool_tu13__SVFloat32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fscale.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -350,16 +334,14 @@ svfloat32_t test_svscale_n_f32_x(svbool_t pg, svfloat32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svscale_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fscale.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svscale_n_f64_xu10__SVBool_tu13__SVFloat64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fscale.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_sub.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_sub.c
index 3418a7e5523c..a6e1c7016ac6 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_sub.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_sub.c
@@ -428,16 +428,14 @@ svuint64_t test_svsub_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svsub_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svsub_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svsub_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsub_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svsub_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svsub_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsub_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svsub_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svsub_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsub_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svsub_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svsub_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svsub_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svsub_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svsub_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svsub_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svsub_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svsub_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svsub_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svsub_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svsub_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svsub_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svsub_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svsub_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svsub_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svsub_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svsub_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsub_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svsub_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsub_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svsub_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsub_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svsub_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svsub_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svsub_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svsub_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svsub_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svsub_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svsub_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svsub_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svsub_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svsub_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svsub_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svsub_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svsub_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsub_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svsub_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsub_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svsub_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsub_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svsub_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svsub_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svsub_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svsub_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svsub_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svsub_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svsub_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svsub_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svsub_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svsub_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svsub_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svsub_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svsub_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svsub_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svsub_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svsub_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svsub_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svsub_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svsub_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svsub_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svsub_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svsub_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svsub_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svsub_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svsub_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svsub_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svsub_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svsub_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svsub_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svsub_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsub_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_subr.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_subr.c
index 69d11b8d9990..218d43dcedf3 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_subr.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_subr.c
@@ -428,16 +428,14 @@ svuint64_t test_svsubr_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svsubr_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubr_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -450,8 +448,7 @@ svint8_t test_svsubr_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsubr_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -459,8 +456,7 @@ svint8_t test_svsubr_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -473,8 +469,7 @@ svint16_t test_svsubr_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsubr_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -482,8 +477,7 @@ svint16_t test_svsubr_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -496,8 +490,7 @@ svint32_t test_svsubr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsubr_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -505,8 +498,7 @@ svint32_t test_svsubr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -518,16 +510,14 @@ svint64_t test_svsubr_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svsubr_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubr_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -540,8 +530,7 @@ svuint8_t test_svsubr_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svsubr_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -549,8 +538,7 @@ svuint8_t test_svsubr_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -563,8 +551,7 @@ svuint16_t test_svsubr_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svsubr_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -572,8 +559,7 @@ svuint16_t test_svsubr_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -586,8 +572,7 @@ svuint32_t test_svsubr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svsubr_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -595,8 +580,7 @@ svuint32_t test_svsubr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,15 +592,13 @@ svuint64_t test_svsubr_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svsubr_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubr_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -628,16 +610,14 @@ svint8_t test_svsubr_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsubr_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -649,16 +629,14 @@ svint16_t test_svsubr_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsubr_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -670,16 +648,14 @@ svint32_t test_svsubr_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsubr_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -690,15 +666,13 @@ svint64_t test_svsubr_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svsubr_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubr_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -710,16 +684,14 @@ svuint8_t test_svsubr_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svsubr_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -731,16 +703,14 @@ svuint16_t test_svsubr_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svsubr_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -752,16 +722,14 @@ svuint32_t test_svsubr_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svsubr_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -772,15 +740,13 @@ svuint64_t test_svsubr_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svsubr_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubr_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -792,16 +758,14 @@ svint8_t test_svsubr_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsubr_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -813,16 +777,14 @@ svint16_t test_svsubr_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsubr_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -834,16 +796,14 @@ svint32_t test_svsubr_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsubr_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -854,15 +814,13 @@ svint64_t test_svsubr_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svsubr_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubr_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -874,16 +832,14 @@ svuint8_t test_svsubr_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svsubr_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -895,16 +851,14 @@ svuint16_t test_svsubr_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svsubr_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -916,16 +870,14 @@ svuint32_t test_svsubr_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svsubr_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -1096,8 +1048,7 @@ svfloat64_t test_svsubr_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CHECK-LABEL: @test_svsubr_n_f16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1105,8 +1056,7 @@ svfloat64_t test_svsubr_f64_x(svbool_t pg, svfloat64_t op1, svfloat64_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f16_zu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[TMP2]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP3]]
@@ -1119,8 +1069,7 @@ svfloat16_t test_svsubr_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svsubr_n_f32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1128,8 +1077,7 @@ svfloat16_t test_svsubr_n_f16_z(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f32_zu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[TMP2]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP3]]
@@ -1142,8 +1090,7 @@ svfloat32_t test_svsubr_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svsubr_n_f64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1151,8 +1098,7 @@ svfloat32_t test_svsubr_n_f32_z(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f64_zu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[TMP2]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
@@ -1165,16 +1111,14 @@ svfloat64_t test_svsubr_n_f64_z(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svsubr_n_f16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f16_mu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1186,16 +1130,14 @@ svfloat16_t test_svsubr_n_f16_m(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svsubr_n_f32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f32_mu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1207,16 +1149,14 @@ svfloat32_t test_svsubr_n_f32_m(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svsubr_n_f64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f64_mu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
@@ -1228,16 +1168,14 @@ svfloat64_t test_svsubr_n_f64_m(svbool_t pg, svfloat64_t op1, float64_t op2)
 // CHECK-LABEL: @test_svsubr_n_f16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f16_xu10__SVBool_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x half> [[OP1:%.*]], <vscale x 8 x half> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 //
@@ -1249,16 +1187,14 @@ svfloat16_t test_svsubr_n_f16_x(svbool_t pg, svfloat16_t op1, float16_t op2)
 // CHECK-LABEL: @test_svsubr_n_f32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f32_xu10__SVBool_tu13__SVFloat32_tf(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x float> poison, float [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x float> [[DOTSPLATINSERT]], <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x float> [[OP1:%.*]], <vscale x 4 x float> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 //
@@ -1270,16 +1206,14 @@ svfloat32_t test_svsubr_n_f32_x(svbool_t pg, svfloat32_t op1, float32_t op2)
 // CHECK-LABEL: @test_svsubr_n_f64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubr_n_f64_xu10__SVBool_tu13__SVFloat64_td(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x double> poison, double [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x double> [[DOTSPLATINSERT]], <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_sudot.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_sudot.c
index 7c68ba0f486b..e23bf6ce10d4 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_sudot.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_sudot.c
@@ -29,15 +29,13 @@ svint32_t test_svsudot_s32(svint32_t x, svint8_t y, svuint8_t z) {
 
 // CHECK-LABEL: @test_svsudot_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[Z:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[Z:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usdot.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[Y:%.*]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsudot_n_s32u11__SVInt32_tu10__SVInt8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[Z:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[Z:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usdot.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[TMP0]], <vscale x 16 x i8> [[Y:%.*]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_usdot.c b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_usdot.c
index 27fb914abc14..0eefd34b490b 100644
--- a/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_usdot.c
+++ b/clang/test/CodeGen/aarch64-sve-intrinsics/acle_sve_usdot.c
@@ -29,15 +29,13 @@ svint32_t test_svusdot_s32(svint32_t x, svuint8_t y, svint8_t z) {
 
 // CHECK-LABEL: @test_svusdot_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[Z:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[Z:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usdot.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[Y:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svusdot_n_s32u11__SVInt32_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[Z:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[Z:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usdot.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[Y:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aba.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aba.c
index 3069226f00a0..64b2a1434652 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aba.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aba.c
@@ -153,15 +153,13 @@ svuint64_t test_svaba_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svaba_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.saba.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z15test_svaba_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.saba.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_svaba_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svaba_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saba.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svaba_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saba.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_svaba_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svaba_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saba.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svaba_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saba.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_svaba_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svaba_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saba.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svaba_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saba.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_svaba_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svaba_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uaba.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z15test_svaba_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uaba.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_svaba_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svaba_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaba.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svaba_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaba.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_svaba_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svaba_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaba.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svaba_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaba.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_svaba_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svaba_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaba.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svaba_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaba.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abalb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abalb.c
index a7aa9485dde5..fcb0eedd6be4 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abalb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abalb.c
@@ -119,15 +119,13 @@ svuint64_t test_svabalb_u64(svuint64_t op1, svuint32_t op2, svuint32_t op3)
 
 // CHECK-LABEL: @test_svabalb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalb_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svabalb_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svabalb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalb_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svabalb_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svabalb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalb_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svabalb_n_s64(svint64_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svabalb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalb_n_u16u12__SVUint16_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svabalb_n_u16(svuint16_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svabalb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalb_n_u32u12__SVUint32_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svabalb_n_u32(svuint32_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svabalb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalb_n_u64u12__SVUint64_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abalt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abalt.c
index 6d8520d76dbd..246f84b2273b 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abalt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abalt.c
@@ -119,15 +119,13 @@ svuint64_t test_svabalt_u64(svuint64_t op1, svuint32_t op2, svuint32_t op3)
 
 // CHECK-LABEL: @test_svabalt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalt_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svabalt_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svabalt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalt_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svabalt_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svabalt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalt_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svabalt_n_s64(svint64_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svabalt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalt_n_u16u12__SVUint16_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svabalt_n_u16(svuint16_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svabalt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalt_n_u32u12__SVUint32_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svabalt_n_u32(svuint32_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svabalt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabalt_n_u64u12__SVUint64_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abdlb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abdlb.c
index b8ae4b1b14d5..d91398c81dec 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abdlb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abdlb.c
@@ -119,15 +119,13 @@ svuint64_t test_svabdlb_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svabdlb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabdlb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlb_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabdlb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svabdlb_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svabdlb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabdlb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlb_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabdlb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svabdlb_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svabdlb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabdlb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlb_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabdlb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svabdlb_n_s64(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svabdlb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabdlb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlb_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabdlb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svabdlb_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svabdlb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabdlb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlb_n_u32u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabdlb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svabdlb_n_u32(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svabdlb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabdlb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlb_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabdlb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abdlt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abdlt.c
index 39e201deb7ab..491ac415dde2 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abdlt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_abdlt.c
@@ -119,15 +119,13 @@ svuint64_t test_svabdlt_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svabdlt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabdlt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlt_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sabdlt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svabdlt_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svabdlt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabdlt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlt_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sabdlt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svabdlt_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svabdlt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabdlt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlt_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sabdlt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svabdlt_n_s64(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svabdlt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabdlt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlt_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uabdlt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svabdlt_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svabdlt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabdlt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlt_n_u32u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uabdlt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svabdlt_n_u32(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svabdlt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabdlt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svabdlt_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uabdlt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_adclb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_adclb.c
index 4f415faf596f..dc9bfbc58e50 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_adclb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_adclb.c
@@ -51,15 +51,13 @@ svuint64_t test_svadclb_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svadclb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.adclb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadclb_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.adclb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -72,15 +70,13 @@ svuint32_t test_svadclb_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svadclb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.adclb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadclb_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.adclb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_adclt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_adclt.c
index 335f3a444918..a42ac072e13e 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_adclt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_adclt.c
@@ -51,15 +51,13 @@ svuint64_t test_svadclt_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svadclt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.adclt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadclt_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.adclt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -72,15 +70,13 @@ svuint32_t test_svadclt_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svadclt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.adclt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svadclt_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.adclt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addhnb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addhnb.c
index e28b6168dc98..070fc493b9ee 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addhnb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addhnb.c
@@ -119,15 +119,13 @@ svuint32_t test_svaddhnb_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svaddhnb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.addhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnb_n_s16u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.addhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint8_t test_svaddhnb_n_s16(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svaddhnb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.addhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnb_n_s32u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.addhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint16_t test_svaddhnb_n_s32(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svaddhnb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.addhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnb_n_s64u11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.addhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint32_t test_svaddhnb_n_s64(svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svaddhnb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.addhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnb_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.addhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint8_t test_svaddhnb_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svaddhnb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.addhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnb_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.addhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint16_t test_svaddhnb_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svaddhnb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.addhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnb_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.addhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addhnt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addhnt.c
index c07d3cd46424..8bc757ec9356 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addhnt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addhnt.c
@@ -119,15 +119,13 @@ svuint32_t test_svaddhnt_u64(svuint32_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svaddhnt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.addhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnt_n_s16u10__SVInt8_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.addhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint8_t test_svaddhnt_n_s16(svint8_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svaddhnt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.addhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnt_n_s32u11__SVInt16_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.addhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint16_t test_svaddhnt_n_s32(svint16_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svaddhnt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.addhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnt_n_s64u11__SVInt32_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.addhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint32_t test_svaddhnt_n_s64(svint32_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svaddhnt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.addhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnt_n_u16u11__SVUint8_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.addhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint8_t test_svaddhnt_n_u16(svuint8_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svaddhnt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.addhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnt_n_u32u12__SVUint16_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.addhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint16_t test_svaddhnt_n_u32(svuint16_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svaddhnt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.addhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddhnt_n_u64u12__SVUint32_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.addhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlb.c
index fe0c618dc412..8eed03d66bee 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlb.c
@@ -119,15 +119,13 @@ svuint64_t test_svaddlb_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svaddlb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddlb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlb_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddlb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svaddlb_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svaddlb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddlb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlb_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddlb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svaddlb_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svaddlb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddlb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlb_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddlb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svaddlb_n_s64(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svaddlb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaddlb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlb_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaddlb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svaddlb_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svaddlb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaddlb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlb_n_u32u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaddlb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svaddlb_n_u32(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svaddlb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaddlb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlb_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaddlb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlbt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlbt.c
index 6ef71a7dee8e..adbc91e18669 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlbt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlbt.c
@@ -68,15 +68,13 @@ svint64_t test_svaddlbt_s64(svint32_t op1, svint32_t op2)
 
 // CHECK-LABEL: @test_svaddlbt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddlbt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddlbt_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddlbt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svaddlbt_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svaddlbt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddlbt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddlbt_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddlbt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svaddlbt_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svaddlbt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddlbt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svaddlbt_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddlbt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlt.c
index cdbf46403ef8..80bbcec99e8c 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addlt.c
@@ -119,15 +119,13 @@ svuint64_t test_svaddlt_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svaddlt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddlt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlt_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddlt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svaddlt_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svaddlt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddlt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlt_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddlt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svaddlt_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svaddlt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddlt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlt_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddlt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svaddlt_n_s64(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svaddlt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaddlt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlt_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaddlt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svaddlt_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svaddlt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaddlt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlt_n_u32u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaddlt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svaddlt_n_u32(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svaddlt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaddlt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddlt_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaddlt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addwb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addwb.c
index 3b1c29055cec..dd0fecaf0fcd 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addwb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addwb.c
@@ -119,15 +119,13 @@ svuint64_t test_svaddwb_u64(svuint64_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svaddwb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddwb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwb_n_s16u11__SVInt16_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddwb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svaddwb_n_s16(svint16_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svaddwb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddwb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwb_n_s32u11__SVInt32_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddwb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svaddwb_n_s32(svint32_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svaddwb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddwb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwb_n_s64u11__SVInt64_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddwb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svaddwb_n_s64(svint64_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svaddwb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaddwb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwb_n_u16u12__SVUint16_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaddwb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svaddwb_n_u16(svuint16_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svaddwb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaddwb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwb_n_u32u12__SVUint32_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaddwb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svaddwb_n_u32(svuint32_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svaddwb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaddwb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwb_n_u64u12__SVUint64_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaddwb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addwt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addwt.c
index 7645b5c53b70..b059f5c698ab 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addwt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_addwt.c
@@ -119,15 +119,13 @@ svuint64_t test_svaddwt_u64(svuint64_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svaddwt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddwt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwt_n_s16u11__SVInt16_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.saddwt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svaddwt_n_s16(svint16_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svaddwt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddwt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwt_n_s32u11__SVInt32_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.saddwt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svaddwt_n_s32(svint32_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svaddwt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddwt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwt_n_s64u11__SVInt64_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.saddwt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svaddwt_n_s64(svint64_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svaddwt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaddwt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwt_n_u16u12__SVUint16_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uaddwt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svaddwt_n_u16(svuint16_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svaddwt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaddwt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwt_n_u32u12__SVUint32_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uaddwt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svaddwt_n_u32(svuint32_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svaddwt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaddwt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svaddwt_n_u64u12__SVUint64_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uaddwt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bcax.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bcax.c
index 9d9caf733053..7d68aef34a44 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bcax.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bcax.c
@@ -153,15 +153,13 @@ svuint64_t test_svbcax_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svbcax_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bcax.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbcax_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bcax.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_svbcax_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svbcax_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bcax.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbcax_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bcax.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_svbcax_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svbcax_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bcax.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbcax_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bcax.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_svbcax_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svbcax_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bcax.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbcax_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bcax.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_svbcax_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svbcax_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bcax.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbcax_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bcax.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_svbcax_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svbcax_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bcax.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbcax_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bcax.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_svbcax_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svbcax_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bcax.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbcax_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bcax.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_svbcax_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svbcax_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bcax.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbcax_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bcax.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bdep.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bdep.c
index 5f541e99625e..feb02c035e30 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bdep.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bdep.c
@@ -85,15 +85,13 @@ svuint64_t test_svbdep_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svbdep_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bdep.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbdep_n_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bdep.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -106,15 +104,13 @@ svuint8_t test_svbdep_n_u8(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svbdep_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bdep.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbdep_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bdep.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -127,15 +123,13 @@ svuint16_t test_svbdep_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svbdep_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bdep.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbdep_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bdep.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -148,15 +142,13 @@ svuint32_t test_svbdep_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svbdep_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bdep.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbdep_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bdep.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bext.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bext.c
index d213e375ec14..2e351c65b83a 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bext.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bext.c
@@ -85,15 +85,13 @@ svuint64_t test_svbext_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svbext_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bext.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbext_n_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bext.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -106,15 +104,13 @@ svuint8_t test_svbext_n_u8(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svbext_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bext.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbext_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bext.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -127,15 +123,13 @@ svuint16_t test_svbext_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svbext_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bext.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbext_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bext.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -148,15 +142,13 @@ svuint32_t test_svbext_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svbext_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bext.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbext_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bext.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bgrp.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bgrp.c
index cbc03653ff6f..88d2abb04808 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bgrp.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bgrp.c
@@ -85,15 +85,13 @@ svuint64_t test_svbgrp_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svbgrp_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bgrp.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbgrp_n_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bgrp.x.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -106,15 +104,13 @@ svuint8_t test_svbgrp_n_u8(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svbgrp_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bgrp.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbgrp_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bgrp.x.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -127,15 +123,13 @@ svuint16_t test_svbgrp_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svbgrp_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bgrp.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbgrp_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bgrp.x.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -148,15 +142,13 @@ svuint32_t test_svbgrp_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svbgrp_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bgrp.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbgrp_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bgrp.x.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl.c
index 8888a4ea174b..dc75f24ecc99 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl.c
@@ -153,15 +153,13 @@ svuint64_t test_svbsl_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svbsl_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z15test_svbsl_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_svbsl_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svbsl_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbsl_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_svbsl_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svbsl_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbsl_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_svbsl_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svbsl_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbsl_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_svbsl_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svbsl_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z15test_svbsl_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_svbsl_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svbsl_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbsl_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_svbsl_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svbsl_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbsl_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_svbsl_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svbsl_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svbsl_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl1n.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl1n.c
index f1616f758579..b3661c2c0690 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl1n.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl1n.c
@@ -153,15 +153,13 @@ svuint64_t test_svbsl1n_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svbsl1n_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl1n.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbsl1n_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl1n.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_svbsl1n_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svbsl1n_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl1n.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl1n_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl1n.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_svbsl1n_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svbsl1n_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl1n.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl1n_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl1n.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_svbsl1n_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svbsl1n_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl1n.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl1n_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl1n.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_svbsl1n_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svbsl1n_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl1n.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbsl1n_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl1n.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_svbsl1n_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svbsl1n_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl1n.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl1n_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl1n.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_svbsl1n_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svbsl1n_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl1n.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl1n_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl1n.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_svbsl1n_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svbsl1n_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl1n.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl1n_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl1n.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl2n.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl2n.c
index 1c4701a620f3..1fc3dce061c7 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl2n.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_bsl2n.c
@@ -153,15 +153,13 @@ svuint64_t test_svbsl2n_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svbsl2n_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl2n.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbsl2n_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl2n.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_svbsl2n_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svbsl2n_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl2n.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl2n_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl2n.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_svbsl2n_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svbsl2n_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl2n.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl2n_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl2n.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_svbsl2n_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svbsl2n_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl2n.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl2n_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl2n.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_svbsl2n_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svbsl2n_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl2n.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svbsl2n_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.bsl2n.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_svbsl2n_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svbsl2n_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl2n.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl2n_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.bsl2n.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_svbsl2n_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svbsl2n_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl2n.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl2n_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.bsl2n.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_svbsl2n_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svbsl2n_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl2n.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svbsl2n_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.bsl2n.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eor3.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eor3.c
index ab2bf5bed995..bcb020225ad2 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eor3.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eor3.c
@@ -153,15 +153,13 @@ svuint64_t test_sveor3_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_sveor3_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor3.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_sveor3_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor3.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_sveor3_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_sveor3_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor3.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor3_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor3.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_sveor3_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_sveor3_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor3.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor3_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor3.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_sveor3_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_sveor3_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor3.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor3_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor3.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_sveor3_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_sveor3_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor3.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_sveor3_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eor3.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_sveor3_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_sveor3_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor3.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor3_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eor3.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_sveor3_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_sveor3_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor3.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor3_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eor3.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_sveor3_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_sveor3_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor3.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveor3_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eor3.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eorbt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eorbt.c
index 01e8f4ee1a39..c813ebc049ea 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eorbt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eorbt.c
@@ -153,15 +153,13 @@ svuint64_t test_sveorbt_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_sveorbt_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eorbt.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveorbt_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eorbt.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_sveorbt_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_sveorbt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eorbt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveorbt_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eorbt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_sveorbt_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_sveorbt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eorbt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveorbt_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eorbt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_sveorbt_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_sveorbt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eorbt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveorbt_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eorbt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_sveorbt_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_sveorbt_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eorbt.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveorbt_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eorbt.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_sveorbt_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_sveorbt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eorbt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveorbt_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eorbt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_sveorbt_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_sveorbt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eorbt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveorbt_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eorbt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_sveorbt_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_sveorbt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eorbt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveorbt_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eorbt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eortb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eortb.c
index 810f32230fbf..fdcac8f2edd2 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eortb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_eortb.c
@@ -153,15 +153,13 @@ svuint64_t test_sveortb_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_sveortb_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eortb.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveortb_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eortb.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_sveortb_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_sveortb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eortb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveortb_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eortb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_sveortb_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_sveortb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eortb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveortb_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eortb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_sveortb_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_sveortb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eortb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveortb_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eortb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_sveortb_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_sveortb_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eortb.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_sveortb_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.eortb.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_sveortb_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_sveortb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eortb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveortb_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.eortb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_sveortb_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_sveortb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eortb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveortb_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.eortb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_sveortb_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_sveortb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eortb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_sveortb_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.eortb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hadd.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hadd.c
index 2a8f19e75c23..bdcc297bbe84 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hadd.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hadd.c
@@ -166,15 +166,13 @@ svuint64_t test_svhadd_u64_m(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svhadd_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhadd_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -188,16 +186,14 @@ svint8_t test_svhadd_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhadd_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -211,16 +207,14 @@ svint16_t test_svhadd_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhadd_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -234,16 +228,14 @@ svint32_t test_svhadd_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhadd_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -256,15 +248,13 @@ svint64_t test_svhadd_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhadd_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhadd_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -278,16 +268,14 @@ svuint8_t test_svhadd_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhadd_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -301,16 +289,14 @@ svuint16_t test_svhadd_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhadd_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -324,16 +310,14 @@ svuint32_t test_svhadd_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhadd_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -511,16 +495,14 @@ svuint64_t test_svhadd_u64_z(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svhadd_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhadd_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -535,8 +517,7 @@ svint8_t test_svhadd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhadd_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -544,8 +525,7 @@ svint8_t test_svhadd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -560,8 +540,7 @@ svint16_t test_svhadd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhadd_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -569,8 +548,7 @@ svint16_t test_svhadd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -585,8 +563,7 @@ svint32_t test_svhadd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhadd_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -594,8 +571,7 @@ svint32_t test_svhadd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -609,16 +585,14 @@ svint64_t test_svhadd_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhadd_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhadd_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -633,8 +607,7 @@ svuint8_t test_svhadd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhadd_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -642,8 +615,7 @@ svuint8_t test_svhadd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -658,8 +630,7 @@ svuint16_t test_svhadd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhadd_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -667,8 +638,7 @@ svuint16_t test_svhadd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -683,8 +653,7 @@ svuint32_t test_svhadd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhadd_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -692,8 +661,7 @@ svuint32_t test_svhadd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -856,15 +824,13 @@ svuint64_t test_svhadd_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svhadd_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhadd_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -878,16 +844,14 @@ svint8_t test_svhadd_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhadd_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -901,16 +865,14 @@ svint16_t test_svhadd_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhadd_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -924,16 +886,14 @@ svint32_t test_svhadd_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhadd_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -946,15 +906,13 @@ svint64_t test_svhadd_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhadd_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhadd_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -968,16 +926,14 @@ svuint8_t test_svhadd_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhadd_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -991,16 +947,14 @@ svuint16_t test_svhadd_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhadd_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1014,16 +968,14 @@ svuint32_t test_svhadd_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhadd_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhadd_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hsub.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hsub.c
index 450ad0db7ebb..47bdeea57837 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hsub.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hsub.c
@@ -477,16 +477,14 @@ svuint64_t test_svhsub_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svhsub_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhsub_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -501,8 +499,7 @@ svint8_t test_svhsub_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhsub_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -510,8 +507,7 @@ svint8_t test_svhsub_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -526,8 +522,7 @@ svint16_t test_svhsub_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhsub_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -535,8 +530,7 @@ svint16_t test_svhsub_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -551,8 +545,7 @@ svint32_t test_svhsub_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhsub_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -560,8 +553,7 @@ svint32_t test_svhsub_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -575,16 +567,14 @@ svint64_t test_svhsub_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhsub_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhsub_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -599,8 +589,7 @@ svuint8_t test_svhsub_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhsub_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -608,8 +597,7 @@ svuint8_t test_svhsub_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -624,8 +612,7 @@ svuint16_t test_svhsub_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhsub_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -633,8 +620,7 @@ svuint16_t test_svhsub_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -649,8 +635,7 @@ svuint32_t test_svhsub_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhsub_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -658,8 +643,7 @@ svuint32_t test_svhsub_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -673,15 +657,13 @@ svuint64_t test_svhsub_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svhsub_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhsub_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -695,16 +677,14 @@ svint8_t test_svhsub_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhsub_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -718,16 +698,14 @@ svint16_t test_svhsub_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhsub_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -741,16 +719,14 @@ svint32_t test_svhsub_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhsub_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -763,15 +739,13 @@ svint64_t test_svhsub_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhsub_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhsub_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -785,16 +759,14 @@ svuint8_t test_svhsub_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhsub_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -808,16 +780,14 @@ svuint16_t test_svhsub_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhsub_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -831,16 +801,14 @@ svuint32_t test_svhsub_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhsub_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -853,15 +821,13 @@ svuint64_t test_svhsub_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svhsub_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhsub_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -875,16 +841,14 @@ svint8_t test_svhsub_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhsub_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -898,16 +862,14 @@ svint16_t test_svhsub_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhsub_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -921,16 +883,14 @@ svint32_t test_svhsub_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhsub_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -943,15 +903,13 @@ svint64_t test_svhsub_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhsub_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svhsub_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -965,16 +923,14 @@ svuint8_t test_svhsub_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhsub_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -988,16 +944,14 @@ svuint16_t test_svhsub_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhsub_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1011,16 +965,14 @@ svuint32_t test_svhsub_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhsub_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsub_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hsubr.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hsubr.c
index 74520c0328c3..823cfd868175 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hsubr.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_hsubr.c
@@ -477,16 +477,14 @@ svuint64_t test_svhsubr_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svhsubr_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsubr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsubr_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsubr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -501,8 +499,7 @@ svint8_t test_svhsubr_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -510,8 +507,7 @@ svint8_t test_svhsubr_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -526,8 +522,7 @@ svint16_t test_svhsubr_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -535,8 +530,7 @@ svint16_t test_svhsubr_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -551,8 +545,7 @@ svint32_t test_svhsubr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -560,8 +553,7 @@ svint32_t test_svhsubr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -575,16 +567,14 @@ svint64_t test_svhsubr_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhsubr_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsubr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsubr_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsubr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -599,8 +589,7 @@ svuint8_t test_svhsubr_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -608,8 +597,7 @@ svuint8_t test_svhsubr_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -624,8 +612,7 @@ svuint16_t test_svhsubr_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -633,8 +620,7 @@ svuint16_t test_svhsubr_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -649,8 +635,7 @@ svuint32_t test_svhsubr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -658,8 +643,7 @@ svuint32_t test_svhsubr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -673,15 +657,13 @@ svuint64_t test_svhsubr_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svhsubr_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsubr_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -695,16 +677,14 @@ svint8_t test_svhsubr_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -718,16 +698,14 @@ svint16_t test_svhsubr_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -741,16 +719,14 @@ svint32_t test_svhsubr_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -763,15 +739,13 @@ svint64_t test_svhsubr_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhsubr_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsubr_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -785,16 +759,14 @@ svuint8_t test_svhsubr_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -808,16 +780,14 @@ svuint16_t test_svhsubr_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -831,16 +801,14 @@ svuint32_t test_svhsubr_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -853,15 +821,13 @@ svuint64_t test_svhsubr_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svhsubr_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsubr_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.shsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -875,16 +841,14 @@ svint8_t test_svhsubr_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.shsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -898,16 +862,14 @@ svint16_t test_svhsubr_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.shsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -921,16 +883,14 @@ svint32_t test_svhsubr_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svhsubr_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.shsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -943,15 +903,13 @@ svint64_t test_svhsubr_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svhsubr_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svhsubr_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uhsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -965,16 +923,14 @@ svuint8_t test_svhsubr_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uhsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -988,16 +944,14 @@ svuint16_t test_svhsubr_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uhsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1011,16 +965,14 @@ svuint32_t test_svhsubr_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svhsubr_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svhsubr_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uhsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlalb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlalb.c
index 0d9e6634f761..f3385a540816 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlalb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlalb.c
@@ -119,15 +119,13 @@ svuint64_t test_svmlalb_u64(svuint64_t op1, svuint32_t op2, svuint32_t op3)
 
 // CHECK-LABEL: @test_svmlalb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smlalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalb_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smlalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svmlalb_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svmlalb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smlalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalb_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smlalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svmlalb_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svmlalb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smlalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalb_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smlalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svmlalb_n_s64(svint64_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svmlalb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umlalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalb_n_u16u12__SVUint16_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umlalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svmlalb_n_u16(svuint16_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svmlalb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umlalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalb_n_u32u12__SVUint32_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umlalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svmlalb_n_u32(svuint32_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svmlalb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umlalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalb_n_u64u12__SVUint64_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umlalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -398,15 +386,13 @@ svfloat32_t test_svmlalb_f32(svfloat32_t op1, svfloat16_t op2, svfloat16_t op3)
 
 // CHECK-LABEL: @test_svmlalb_n_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmlalb.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalb_n_f32u13__SVFloat32_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmlalb.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlalt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlalt.c
index b6ff5769e6ac..a5c75f811a7d 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlalt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlalt.c
@@ -119,15 +119,13 @@ svuint64_t test_svmlalt_u64(svuint64_t op1, svuint32_t op2, svuint32_t op3)
 
 // CHECK-LABEL: @test_svmlalt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smlalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalt_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smlalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svmlalt_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svmlalt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smlalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalt_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smlalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svmlalt_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svmlalt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smlalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalt_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smlalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svmlalt_n_s64(svint64_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svmlalt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umlalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalt_n_u16u12__SVUint16_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umlalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svmlalt_n_u16(svuint16_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svmlalt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umlalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalt_n_u32u12__SVUint32_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umlalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svmlalt_n_u32(svuint32_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svmlalt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umlalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalt_n_u64u12__SVUint64_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umlalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -398,15 +386,13 @@ svfloat32_t test_svmlalt_f32(svfloat32_t op1, svfloat16_t op2, svfloat16_t op3)
 
 // CHECK-LABEL: @test_svmlalt_n_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmlalt.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlalt_n_f32u13__SVFloat32_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmlalt.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlslb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlslb.c
index 37db5d3f06f0..457abe252c3f 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlslb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlslb.c
@@ -119,15 +119,13 @@ svuint64_t test_svmlslb_u64(svuint64_t op1, svuint32_t op2, svuint32_t op3)
 
 // CHECK-LABEL: @test_svmlslb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smlslb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslb_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smlslb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svmlslb_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svmlslb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smlslb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslb_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smlslb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svmlslb_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svmlslb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smlslb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslb_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smlslb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svmlslb_n_s64(svint64_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svmlslb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umlslb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslb_n_u16u12__SVUint16_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umlslb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svmlslb_n_u16(svuint16_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svmlslb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umlslb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslb_n_u32u12__SVUint32_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umlslb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svmlslb_n_u32(svuint32_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svmlslb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umlslb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslb_n_u64u12__SVUint64_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umlslb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -398,15 +386,13 @@ svfloat32_t test_svmlslb_f32(svfloat32_t op1, svfloat16_t op2, svfloat16_t op3)
 
 // CHECK-LABEL: @test_svmlslb_n_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmlslb.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslb_n_f32u13__SVFloat32_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmlslb.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlslt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlslt.c
index 628b3723925a..66ee032b91b1 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlslt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mlslt.c
@@ -119,15 +119,13 @@ svuint64_t test_svmlslt_u64(svuint64_t op1, svuint32_t op2, svuint32_t op3)
 
 // CHECK-LABEL: @test_svmlslt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smlslt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslt_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smlslt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svmlslt_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svmlslt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smlslt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslt_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smlslt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svmlslt_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svmlslt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smlslt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslt_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smlslt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svmlslt_n_s64(svint64_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svmlslt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umlslt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslt_n_u16u12__SVUint16_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umlslt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svmlslt_n_u16(svuint16_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svmlslt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umlslt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslt_n_u32u12__SVUint32_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umlslt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svmlslt_n_u32(svuint32_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svmlslt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umlslt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslt_n_u64u12__SVUint64_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umlslt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -398,15 +386,13 @@ svfloat32_t test_svmlslt_f32(svfloat32_t op1, svfloat16_t op2, svfloat16_t op3)
 
 // CHECK-LABEL: @test_svmlslt_n_f32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmlslt.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmlslt_n_f32u13__SVFloat32_tu13__SVFloat16_tDh(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x half> poison, half [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x half> [[DOTSPLATINSERT]], <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmlslt.nxv4f32(<vscale x 4 x float> [[OP1:%.*]], <vscale x 8 x half> [[OP2:%.*]], <vscale x 8 x half> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mullb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mullb.c
index 9e438e9aba92..70723deb57bf 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mullb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mullb.c
@@ -119,15 +119,13 @@ svuint64_t test_svmullb_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svmullb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smullb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullb_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smullb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svmullb_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svmullb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smullb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullb_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smullb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svmullb_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svmullb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smullb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullb_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smullb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svmullb_n_s64(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svmullb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umullb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullb_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umullb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svmullb_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svmullb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umullb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullb_n_u32u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umullb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svmullb_n_u32(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svmullb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umullb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullb_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umullb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mullt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mullt.c
index 9b48f926499b..b02989e681e5 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mullt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_mullt.c
@@ -119,15 +119,13 @@ svuint64_t test_svmullt_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svmullt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smullt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullt_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.smullt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svmullt_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svmullt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smullt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullt_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.smullt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svmullt_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svmullt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smullt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullt_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.smullt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svmullt_n_s64(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svmullt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umullt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullt_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.umullt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svmullt_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svmullt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umullt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullt_n_u32u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.umullt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svmullt_n_u32(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svmullt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umullt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svmullt_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.umullt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_nbsl.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_nbsl.c
index 7bd7ed03c91f..54e5a9314a2a 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_nbsl.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_nbsl.c
@@ -153,15 +153,13 @@ svuint64_t test_svnbsl_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svnbsl_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.nbsl.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svnbsl_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.nbsl.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -174,15 +172,13 @@ svint8_t test_svnbsl_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svnbsl_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.nbsl.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svnbsl_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.nbsl.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -195,15 +191,13 @@ svint16_t test_svnbsl_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svnbsl_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.nbsl.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svnbsl_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.nbsl.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -216,15 +210,13 @@ svint32_t test_svnbsl_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svnbsl_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.nbsl.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svnbsl_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.nbsl.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -237,15 +229,13 @@ svint64_t test_svnbsl_n_s64(svint64_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svnbsl_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.nbsl.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svnbsl_n_u8u11__SVUint8_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.nbsl.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -258,15 +248,13 @@ svuint8_t test_svnbsl_n_u8(svuint8_t op1, svuint8_t op2, uint8_t op3)
 
 // CHECK-LABEL: @test_svnbsl_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.nbsl.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svnbsl_n_u16u12__SVUint16_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.nbsl.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -279,15 +267,13 @@ svuint16_t test_svnbsl_n_u16(svuint16_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svnbsl_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.nbsl.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svnbsl_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.nbsl.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -300,15 +286,13 @@ svuint32_t test_svnbsl_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svnbsl_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.nbsl.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z17test_svnbsl_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.nbsl.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmul.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmul.c
index c4a1722ad4f2..9e85b316b120 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmul.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmul.c
@@ -34,15 +34,13 @@ svuint8_t test_svpmul_u8(svuint8_t op1, svuint8_t op2)
 
 // CHECK-LABEL: @test_svpmul_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmul.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z16test_svpmul_n_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmul.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb.c
index 0c7c9914dfb7..767f4ff1fdb6 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb.c
@@ -51,15 +51,13 @@ svuint32_t test_svpmullb_pair_u32(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svpmullb_pair_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svpmullb_pair_n_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -72,15 +70,13 @@ svuint8_t test_svpmullb_pair_n_u8(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svpmullb_pair_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z24test_svpmullb_pair_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -131,16 +127,14 @@ svuint64_t test_svpmullb_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svpmullb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    [[TMP2:%.*]] = bitcast <vscale x 16 x i8> [[TMP1]] to <vscale x 8 x i16>
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svpmullb_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = bitcast <vscale x 16 x i8> [[TMP1]] to <vscale x 8 x i16>
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
@@ -154,16 +148,14 @@ svuint16_t test_svpmullb_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svpmullb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    [[TMP2:%.*]] = bitcast <vscale x 4 x i32> [[TMP1]] to <vscale x 2 x i64>
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svpmullb_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = bitcast <vscale x 4 x i32> [[TMP1]] to <vscale x 2 x i64>
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb_128.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb_128.c
index 23330318b883..43b3f0d27166 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb_128.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb_128.c
@@ -34,15 +34,13 @@ svuint64_t test_svpmullb_pair_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svpmullb_pair_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.pmullb.pair.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z24test_svpmullb_pair_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.pmullb.pair.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt.c
index 7fb32951d284..355a6ddafe7a 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt.c
@@ -51,15 +51,13 @@ svuint32_t test_svpmullt_pair_u32(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svpmullt_pair_n_u8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmullt.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z23test_svpmullt_pair_n_u8u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmullt.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -72,15 +70,13 @@ svuint8_t test_svpmullt_pair_n_u8(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svpmullt_pair_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.pmullt.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z24test_svpmullt_pair_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.pmullt.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -131,16 +127,14 @@ svuint64_t test_svpmullt_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svpmullt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmullt.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    [[TMP2:%.*]] = bitcast <vscale x 16 x i8> [[TMP1]] to <vscale x 8 x i16>
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svpmullt_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.pmullt.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = bitcast <vscale x 16 x i8> [[TMP1]] to <vscale x 8 x i16>
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
@@ -154,16 +148,14 @@ svuint16_t test_svpmullt_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svpmullt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.pmullt.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    [[TMP2:%.*]] = bitcast <vscale x 4 x i32> [[TMP1]] to <vscale x 2 x i64>
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svpmullt_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.pmullt.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = bitcast <vscale x 4 x i32> [[TMP1]] to <vscale x 2 x i64>
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt_128.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt_128.c
index 4c002df63f6a..298073adb321 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt_128.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt_128.c
@@ -34,15 +34,13 @@ svuint64_t test_svpmullt_pair_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svpmullt_pair_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.pmullt.pair.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z24test_svpmullt_pair_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.pmullt.pair.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qadd.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qadd.c
index 169c41462c2f..b6f35b2e7ff1 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qadd.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qadd.c
@@ -166,15 +166,13 @@ svuint64_t test_svqadd_u64_m(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqadd_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -188,16 +186,14 @@ svint8_t test_svqadd_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqadd_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -211,16 +207,14 @@ svint16_t test_svqadd_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqadd_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -234,16 +228,14 @@ svint32_t test_svqadd_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqadd_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -256,15 +248,13 @@ svint64_t test_svqadd_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqadd_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -278,16 +268,14 @@ svuint8_t test_svqadd_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqadd_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -301,16 +289,14 @@ svuint16_t test_svqadd_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqadd_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -324,16 +310,14 @@ svuint32_t test_svqadd_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqadd_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -511,16 +495,14 @@ svuint64_t test_svqadd_u64_z(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqadd_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -535,8 +517,7 @@ svint8_t test_svqadd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqadd_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -544,8 +525,7 @@ svint8_t test_svqadd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -560,8 +540,7 @@ svint16_t test_svqadd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqadd_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -569,8 +548,7 @@ svint16_t test_svqadd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -585,8 +563,7 @@ svint32_t test_svqadd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqadd_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -594,8 +571,7 @@ svint32_t test_svqadd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -609,16 +585,14 @@ svint64_t test_svqadd_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqadd_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -633,8 +607,7 @@ svuint8_t test_svqadd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqadd_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -642,8 +615,7 @@ svuint8_t test_svqadd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -658,8 +630,7 @@ svuint16_t test_svqadd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqadd_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -667,8 +638,7 @@ svuint16_t test_svqadd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -683,8 +653,7 @@ svuint32_t test_svqadd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqadd_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -692,8 +661,7 @@ svuint32_t test_svqadd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -856,15 +824,13 @@ svuint64_t test_svqadd_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqadd_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -878,16 +844,14 @@ svint8_t test_svqadd_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqadd_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -901,16 +865,14 @@ svint16_t test_svqadd_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqadd_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -924,16 +886,14 @@ svint32_t test_svqadd_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqadd_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -946,15 +906,13 @@ svint64_t test_svqadd_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqadd_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqadd_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -968,16 +926,14 @@ svuint8_t test_svqadd_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqadd_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -991,16 +947,14 @@ svuint16_t test_svqadd_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqadd_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1014,16 +968,14 @@ svuint32_t test_svqadd_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqadd_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqadd_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalb.c
index 767a55736f5c..b9b5e3cc23d1 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalb.c
@@ -68,15 +68,13 @@ svint64_t test_svqdmlalb_s64(svint64_t op1, svint32_t op2, svint32_t op3)
 
 // CHECK-LABEL: @test_svqdmlalb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlalb_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlalb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svqdmlalb_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svqdmlalb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlalb_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlalb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svqdmlalb_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svqdmlalb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlalb_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlalb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalbt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalbt.c
index 5d3a9f4c5219..8d323d689706 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalbt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalbt.c
@@ -68,15 +68,13 @@ svint64_t test_svqdmlalbt_s64(svint64_t op1, svint32_t op2, svint32_t op3)
 
 // CHECK-LABEL: @test_svqdmlalbt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlalbt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z21test_svqdmlalbt_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlalbt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svqdmlalbt_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svqdmlalbt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlalbt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z21test_svqdmlalbt_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlalbt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svqdmlalbt_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svqdmlalbt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlalbt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z21test_svqdmlalbt_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlalbt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalt.c
index a7d8e9cb8591..7a1691303e83 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlalt.c
@@ -68,15 +68,13 @@ svint64_t test_svqdmlalt_s64(svint64_t op1, svint32_t op2, svint32_t op3)
 
 // CHECK-LABEL: @test_svqdmlalt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlalt_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlalt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svqdmlalt_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svqdmlalt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlalt_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlalt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svqdmlalt_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svqdmlalt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlalt_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlalt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslb.c
index b3648d57d37a..e4fd60422eba 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslb.c
@@ -68,15 +68,13 @@ svint64_t test_svqdmlslb_s64(svint64_t op1, svint32_t op2, svint32_t op3)
 
 // CHECK-LABEL: @test_svqdmlslb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlslb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlslb_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlslb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svqdmlslb_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svqdmlslb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlslb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlslb_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlslb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svqdmlslb_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svqdmlslb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlslb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlslb_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlslb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslbt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslbt.c
index b08c034f7a51..56a5fe1a1788 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslbt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslbt.c
@@ -68,15 +68,13 @@ svint64_t test_svqdmlslbt_s64(svint64_t op1, svint32_t op2, svint32_t op3)
 
 // CHECK-LABEL: @test_svqdmlslbt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlslbt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z21test_svqdmlslbt_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlslbt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svqdmlslbt_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svqdmlslbt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlslbt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z21test_svqdmlslbt_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlslbt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svqdmlslbt_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svqdmlslbt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlslbt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z21test_svqdmlslbt_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlslbt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslt.c
index 12ff62bf0a01..30444905ac21 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmlslt.c
@@ -68,15 +68,13 @@ svint64_t test_svqdmlslt_s64(svint64_t op1, svint32_t op2, svint32_t op3)
 
 // CHECK-LABEL: @test_svqdmlslt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlslt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlslt_n_s16u11__SVInt16_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmlslt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svqdmlslt_n_s16(svint16_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svqdmlslt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlslt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlslt_n_s32u11__SVInt32_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmlslt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svqdmlslt_n_s32(svint32_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svqdmlslt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlslt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmlslt_n_s64u11__SVInt64_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmlslt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmulh.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmulh.c
index e74bb27802c7..ad3279d67ecc 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmulh.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmulh.c
@@ -85,15 +85,13 @@ svint64_t test_svqdmulh_s64(svint64_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svqdmulh_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqdmulh.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqdmulh_n_s8u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqdmulh.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -106,15 +104,13 @@ svint8_t test_svqdmulh_n_s8(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svqdmulh_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmulh.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqdmulh_n_s16u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmulh.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -127,15 +123,13 @@ svint16_t test_svqdmulh_n_s16(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svqdmulh_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmulh.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqdmulh_n_s32u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmulh.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -148,15 +142,13 @@ svint32_t test_svqdmulh_n_s32(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svqdmulh_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmulh.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqdmulh_n_s64u11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmulh.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmullb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmullb.c
index 829d9888651c..61fedbfc0bb3 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmullb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmullb.c
@@ -68,15 +68,13 @@ svint64_t test_svqdmullb_s64(svint32_t op1, svint32_t op2)
 
 // CHECK-LABEL: @test_svqdmullb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmullb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmullb_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmullb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svqdmullb_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svqdmullb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmullb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmullb_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmullb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svqdmullb_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svqdmullb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmullb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmullb_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmullb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmullt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmullt.c
index adca0c6534c5..d14c758274cd 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmullt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qdmullt.c
@@ -68,15 +68,13 @@ svint64_t test_svqdmullt_s64(svint32_t op1, svint32_t op2)
 
 // CHECK-LABEL: @test_svqdmullt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmullt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmullt_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqdmullt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svqdmullt_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svqdmullt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmullt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmullt_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqdmullt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svqdmullt_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svqdmullt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmullt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqdmullt_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqdmullt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmlah.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmlah.c
index 3512532cd472..af000b628402 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmlah.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmlah.c
@@ -85,15 +85,13 @@ svint64_t test_svqrdmlah_s64(svint64_t op1, svint64_t op2, svint64_t op3)
 
 // CHECK-LABEL: @test_svqrdmlah_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrdmlah.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrdmlah_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrdmlah.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -106,15 +104,13 @@ svint8_t test_svqrdmlah_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svqrdmlah_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrdmlah.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmlah_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrdmlah.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -127,15 +123,13 @@ svint16_t test_svqrdmlah_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svqrdmlah_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrdmlah.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmlah_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrdmlah.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -148,15 +142,13 @@ svint32_t test_svqrdmlah_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svqrdmlah_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrdmlah.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmlah_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrdmlah.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmlsh.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmlsh.c
index 747876bf444c..07b36721bf3b 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmlsh.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmlsh.c
@@ -85,15 +85,13 @@ svint64_t test_svqrdmlsh_s64(svint64_t op1, svint64_t op2, svint64_t op3)
 
 // CHECK-LABEL: @test_svqrdmlsh_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrdmlsh.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrdmlsh_n_s8u10__SVInt8_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrdmlsh.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -106,15 +104,13 @@ svint8_t test_svqrdmlsh_n_s8(svint8_t op1, svint8_t op2, int8_t op3)
 
 // CHECK-LABEL: @test_svqrdmlsh_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrdmlsh.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmlsh_n_s16u11__SVInt16_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrdmlsh.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -127,15 +123,13 @@ svint16_t test_svqrdmlsh_n_s16(svint16_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svqrdmlsh_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrdmlsh.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmlsh_n_s32u11__SVInt32_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrdmlsh.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -148,15 +142,13 @@ svint32_t test_svqrdmlsh_n_s32(svint32_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svqrdmlsh_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrdmlsh.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmlsh_n_s64u11__SVInt64_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrdmlsh.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmulh.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmulh.c
index 00883724a35f..0a5727d8599f 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmulh.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrdmulh.c
@@ -85,15 +85,13 @@ svint64_t test_svqrdmulh_s64(svint64_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svqrdmulh_n_s8(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrdmulh.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrdmulh_n_s8u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrdmulh.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -106,15 +104,13 @@ svint8_t test_svqrdmulh_n_s8(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svqrdmulh_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrdmulh.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmulh_n_s16u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrdmulh.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -127,15 +123,13 @@ svint16_t test_svqrdmulh_n_s16(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svqrdmulh_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrdmulh.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmulh_n_s32u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrdmulh.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -148,15 +142,13 @@ svint32_t test_svqrdmulh_n_s32(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svqrdmulh_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrdmulh.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrdmulh_n_s64u11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrdmulh.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrshl.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrshl.c
index 64476a17ab62..38c6dbf5816e 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrshl.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qrshl.c
@@ -477,16 +477,14 @@ svuint64_t test_svqrshl_u64_x(svbool_t pg, svuint64_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svqrshl_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrshl_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -501,8 +499,7 @@ svint8_t test_svqrshl_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -510,8 +507,7 @@ svint8_t test_svqrshl_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -526,8 +522,7 @@ svint16_t test_svqrshl_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -535,8 +530,7 @@ svint16_t test_svqrshl_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -551,8 +545,7 @@ svint32_t test_svqrshl_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -560,8 +553,7 @@ svint32_t test_svqrshl_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -575,16 +567,14 @@ svint64_t test_svqrshl_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqrshl_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqrshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrshl_n_u8_zu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqrshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -599,8 +589,7 @@ svuint8_t test_svqrshl_n_u8_z(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -608,8 +597,7 @@ svuint8_t test_svqrshl_n_u8_z(svbool_t pg, svuint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u16_zu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -624,8 +612,7 @@ svuint16_t test_svqrshl_n_u16_z(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -633,8 +620,7 @@ svuint16_t test_svqrshl_n_u16_z(svbool_t pg, svuint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u32_zu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -649,8 +635,7 @@ svuint32_t test_svqrshl_n_u32_z(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -658,8 +643,7 @@ svuint32_t test_svqrshl_n_u32_z(svbool_t pg, svuint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u64_zu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -673,15 +657,13 @@ svuint64_t test_svqrshl_n_u64_z(svbool_t pg, svuint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqrshl_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrshl_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -695,16 +677,14 @@ svint8_t test_svqrshl_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -718,16 +698,14 @@ svint16_t test_svqrshl_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -741,16 +719,14 @@ svint32_t test_svqrshl_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -763,15 +739,13 @@ svint64_t test_svqrshl_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqrshl_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqrshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrshl_n_u8_mu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqrshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -785,16 +759,14 @@ svuint8_t test_svqrshl_n_u8_m(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u16_mu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -808,16 +780,14 @@ svuint16_t test_svqrshl_n_u16_m(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u32_mu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -831,16 +801,14 @@ svuint32_t test_svqrshl_n_u32_m(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u64_mu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -853,15 +821,13 @@ svuint64_t test_svqrshl_n_u64_m(svbool_t pg, svuint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqrshl_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrshl_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqrshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -875,16 +841,14 @@ svint8_t test_svqrshl_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -898,16 +862,14 @@ svint16_t test_svqrshl_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -921,16 +883,14 @@ svint32_t test_svqrshl_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqrshl_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -943,15 +903,13 @@ svint64_t test_svqrshl_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqrshl_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqrshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqrshl_n_u8_xu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqrshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -965,16 +923,14 @@ svuint8_t test_svqrshl_n_u8_x(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u16_xu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqrshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -988,16 +944,14 @@ svuint16_t test_svqrshl_n_u16_x(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u32_xu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqrshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1011,16 +965,14 @@ svuint32_t test_svqrshl_n_u32_x(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqrshl_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqrshl_n_u64_xu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqrshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qshl.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qshl.c
index 52a21545a04e..3fde6854a1b4 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qshl.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qshl.c
@@ -477,16 +477,14 @@ svuint64_t test_svqshl_u64_x(svbool_t pg, svuint64_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svqshl_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqshl_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -501,8 +499,7 @@ svint8_t test_svqshl_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqshl_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -510,8 +507,7 @@ svint8_t test_svqshl_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -526,8 +522,7 @@ svint16_t test_svqshl_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqshl_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -535,8 +530,7 @@ svint16_t test_svqshl_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -551,8 +545,7 @@ svint32_t test_svqshl_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqshl_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -560,8 +553,7 @@ svint32_t test_svqshl_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -575,16 +567,14 @@ svint64_t test_svqshl_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqshl_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqshl_n_u8_zu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -599,8 +589,7 @@ svuint8_t test_svqshl_n_u8_z(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqshl_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -608,8 +597,7 @@ svuint8_t test_svqshl_n_u8_z(svbool_t pg, svuint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u16_zu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -624,8 +612,7 @@ svuint16_t test_svqshl_n_u16_z(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqshl_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -633,8 +620,7 @@ svuint16_t test_svqshl_n_u16_z(svbool_t pg, svuint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u32_zu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -649,8 +635,7 @@ svuint32_t test_svqshl_n_u32_z(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqshl_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -658,8 +643,7 @@ svuint32_t test_svqshl_n_u32_z(svbool_t pg, svuint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u64_zu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -673,15 +657,13 @@ svuint64_t test_svqshl_n_u64_z(svbool_t pg, svuint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqshl_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqshl_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -695,16 +677,14 @@ svint8_t test_svqshl_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqshl_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -718,16 +698,14 @@ svint16_t test_svqshl_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqshl_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -741,16 +719,14 @@ svint32_t test_svqshl_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqshl_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -763,15 +739,13 @@ svint64_t test_svqshl_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqshl_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqshl_n_u8_mu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -785,16 +759,14 @@ svuint8_t test_svqshl_n_u8_m(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqshl_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u16_mu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -808,16 +780,14 @@ svuint16_t test_svqshl_n_u16_m(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqshl_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u32_mu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -831,16 +801,14 @@ svuint32_t test_svqshl_n_u32_m(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqshl_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u64_mu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -853,15 +821,13 @@ svuint64_t test_svqshl_n_u64_m(svbool_t pg, svuint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqshl_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqshl_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -875,16 +841,14 @@ svint8_t test_svqshl_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqshl_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -898,16 +862,14 @@ svint16_t test_svqshl_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqshl_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -921,16 +883,14 @@ svint32_t test_svqshl_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqshl_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -943,15 +903,13 @@ svint64_t test_svqshl_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqshl_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqshl_n_u8_xu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -965,16 +923,14 @@ svuint8_t test_svqshl_n_u8_x(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqshl_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u16_xu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -988,16 +944,14 @@ svuint16_t test_svqshl_n_u16_x(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqshl_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u32_xu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1011,16 +965,14 @@ svuint32_t test_svqshl_n_u32_x(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqshl_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqshl_n_u64_xu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qsub.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qsub.c
index e8cde005e098..f669fd9d2cba 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qsub.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qsub.c
@@ -477,16 +477,14 @@ svuint64_t test_svqsub_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqsub_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -501,8 +499,7 @@ svint8_t test_svqsub_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqsub_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -510,8 +507,7 @@ svint8_t test_svqsub_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -526,8 +522,7 @@ svint16_t test_svqsub_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqsub_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -535,8 +530,7 @@ svint16_t test_svqsub_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -551,8 +545,7 @@ svint32_t test_svqsub_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqsub_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -560,8 +553,7 @@ svint32_t test_svqsub_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -575,16 +567,14 @@ svint64_t test_svqsub_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqsub_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -599,8 +589,7 @@ svuint8_t test_svqsub_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqsub_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -608,8 +597,7 @@ svuint8_t test_svqsub_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -624,8 +612,7 @@ svuint16_t test_svqsub_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqsub_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -633,8 +620,7 @@ svuint16_t test_svqsub_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -649,8 +635,7 @@ svuint32_t test_svqsub_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqsub_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -658,8 +643,7 @@ svuint32_t test_svqsub_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -673,15 +657,13 @@ svuint64_t test_svqsub_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqsub_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -695,16 +677,14 @@ svint8_t test_svqsub_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqsub_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -718,16 +698,14 @@ svint16_t test_svqsub_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqsub_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -741,16 +719,14 @@ svint32_t test_svqsub_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqsub_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -763,15 +739,13 @@ svint64_t test_svqsub_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqsub_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -785,16 +759,14 @@ svuint8_t test_svqsub_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqsub_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -808,16 +780,14 @@ svuint16_t test_svqsub_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqsub_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -831,16 +801,14 @@ svuint32_t test_svqsub_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqsub_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -853,15 +821,13 @@ svuint64_t test_svqsub_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqsub_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -875,16 +841,14 @@ svint8_t test_svqsub_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqsub_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -898,16 +862,14 @@ svint16_t test_svqsub_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqsub_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -921,16 +883,14 @@ svint32_t test_svqsub_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqsub_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -943,15 +903,13 @@ svint64_t test_svqsub_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqsub_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svqsub_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsub.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -965,16 +923,14 @@ svuint8_t test_svqsub_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqsub_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsub.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -988,16 +944,14 @@ svuint16_t test_svqsub_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqsub_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsub.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1011,16 +965,14 @@ svuint32_t test_svqsub_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqsub_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsub_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsub.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qsubr.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qsubr.c
index 4e2174cbf652..69784968550f 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qsubr.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_qsubr.c
@@ -477,16 +477,14 @@ svuint64_t test_svqsubr_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svqsubr_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsubr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsubr_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsubr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -501,8 +499,7 @@ svint8_t test_svqsubr_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -510,8 +507,7 @@ svint8_t test_svqsubr_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -526,8 +522,7 @@ svint16_t test_svqsubr_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -535,8 +530,7 @@ svint16_t test_svqsubr_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -551,8 +545,7 @@ svint32_t test_svqsubr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -560,8 +553,7 @@ svint32_t test_svqsubr_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -575,16 +567,14 @@ svint64_t test_svqsubr_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqsubr_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsubr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsubr_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsubr.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -599,8 +589,7 @@ svuint8_t test_svqsubr_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -608,8 +597,7 @@ svuint8_t test_svqsubr_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -624,8 +612,7 @@ svuint16_t test_svqsubr_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -633,8 +620,7 @@ svuint16_t test_svqsubr_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -649,8 +635,7 @@ svuint32_t test_svqsubr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -658,8 +643,7 @@ svuint32_t test_svqsubr_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -673,15 +657,13 @@ svuint64_t test_svqsubr_n_u64_z(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svqsubr_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsubr_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -695,16 +677,14 @@ svint8_t test_svqsubr_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -718,16 +698,14 @@ svint16_t test_svqsubr_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -741,16 +719,14 @@ svint32_t test_svqsubr_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -763,15 +739,13 @@ svint64_t test_svqsubr_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqsubr_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsubr_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -785,16 +759,14 @@ svuint8_t test_svqsubr_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -808,16 +780,14 @@ svuint16_t test_svqsubr_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -831,16 +801,14 @@ svuint32_t test_svqsubr_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -853,15 +821,13 @@ svuint64_t test_svqsubr_n_u64_m(svbool_t pg, svuint64_t op1, uint64_t op2)
 
 // CHECK-LABEL: @test_svqsubr_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsubr_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sqsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -875,16 +841,14 @@ svint8_t test_svqsubr_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -898,16 +862,14 @@ svint16_t test_svqsubr_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -921,16 +883,14 @@ svint32_t test_svqsubr_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svqsubr_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -943,15 +903,13 @@ svint64_t test_svqsubr_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svqsubr_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svqsubr_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.uqsubr.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -965,16 +923,14 @@ svuint8_t test_svqsubr_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.uqsubr.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -988,16 +944,14 @@ svuint16_t test_svqsubr_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.uqsubr.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1011,16 +965,14 @@ svuint32_t test_svqsubr_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svqsubr_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svqsubr_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.uqsubr.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_raddhnb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_raddhnb.c
index b6b45303707f..af12457ee479 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_raddhnb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_raddhnb.c
@@ -119,15 +119,13 @@ svuint32_t test_svraddhnb_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svraddhnb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.raddhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnb_n_s16u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.raddhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint8_t test_svraddhnb_n_s16(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svraddhnb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.raddhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnb_n_s32u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.raddhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint16_t test_svraddhnb_n_s32(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svraddhnb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.raddhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnb_n_s64u11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.raddhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint32_t test_svraddhnb_n_s64(svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svraddhnb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.raddhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnb_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.raddhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint8_t test_svraddhnb_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svraddhnb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.raddhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnb_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.raddhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint16_t test_svraddhnb_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svraddhnb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.raddhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnb_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.raddhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_raddhnt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_raddhnt.c
index 3a9ff1fd3038..8d4207176208 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_raddhnt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_raddhnt.c
@@ -119,15 +119,13 @@ svuint32_t test_svraddhnt_u64(svuint32_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svraddhnt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.raddhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnt_n_s16u10__SVInt8_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.raddhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint8_t test_svraddhnt_n_s16(svint8_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svraddhnt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.raddhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnt_n_s32u11__SVInt16_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.raddhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint16_t test_svraddhnt_n_s32(svint16_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svraddhnt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.raddhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnt_n_s64u11__SVInt32_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.raddhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint32_t test_svraddhnt_n_s64(svint32_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svraddhnt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.raddhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnt_n_u16u11__SVUint8_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.raddhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint8_t test_svraddhnt_n_u16(svuint8_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svraddhnt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.raddhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnt_n_u32u12__SVUint16_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.raddhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint16_t test_svraddhnt_n_u32(svuint16_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svraddhnt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.raddhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svraddhnt_n_u64u12__SVUint32_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.raddhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rhadd.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rhadd.c
index a603a0995689..d37487073a7e 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rhadd.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rhadd.c
@@ -165,15 +165,13 @@ svuint64_t test_svrhadd_u64_m(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svrhadd_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrhadd_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -187,16 +185,14 @@ svint8_t test_svrhadd_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -210,16 +206,14 @@ svint16_t test_svrhadd_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -233,16 +227,14 @@ svint32_t test_svrhadd_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -255,15 +247,13 @@ svint64_t test_svrhadd_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrhadd_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrhadd_n_u8_mu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -277,16 +267,14 @@ svuint8_t test_svrhadd_n_u8_m(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u16_mu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -300,16 +288,14 @@ svuint16_t test_svrhadd_n_u16_m(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u32_mu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -323,16 +309,14 @@ svuint32_t test_svrhadd_n_u32_m(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u64_mu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -510,16 +494,14 @@ svuint64_t test_svrhadd_u64_z(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svrhadd_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srhadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrhadd_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srhadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -534,8 +516,7 @@ svint8_t test_svrhadd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -543,8 +524,7 @@ svint8_t test_svrhadd_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -559,8 +539,7 @@ svint16_t test_svrhadd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -568,8 +547,7 @@ svint16_t test_svrhadd_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -584,8 +562,7 @@ svint32_t test_svrhadd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -593,8 +570,7 @@ svint32_t test_svrhadd_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -608,16 +584,14 @@ svint64_t test_svrhadd_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrhadd_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urhadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrhadd_n_u8_zu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urhadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -632,8 +606,7 @@ svuint8_t test_svrhadd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -641,8 +614,7 @@ svuint8_t test_svrhadd_n_u8_z(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u16_zu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -657,8 +629,7 @@ svuint16_t test_svrhadd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -666,8 +637,7 @@ svuint16_t test_svrhadd_n_u16_z(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u32_zu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -682,8 +652,7 @@ svuint32_t test_svrhadd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -691,8 +660,7 @@ svuint32_t test_svrhadd_n_u32_z(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u64_zu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -855,15 +823,13 @@ svuint64_t test_svrhadd_u64_x(svbool_t pg, svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svrhadd_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrhadd_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -877,16 +843,14 @@ svint8_t test_svrhadd_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -900,16 +864,14 @@ svint16_t test_svrhadd_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -923,16 +885,14 @@ svint32_t test_svrhadd_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrhadd_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -945,15 +905,13 @@ svint64_t test_svrhadd_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrhadd_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrhadd_n_u8_xu10__SVBool_tu11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urhadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -967,16 +925,14 @@ svuint8_t test_svrhadd_n_u8_x(svbool_t pg, svuint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u16_xu10__SVBool_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urhadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -990,16 +946,14 @@ svuint16_t test_svrhadd_n_u16_x(svbool_t pg, svuint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u32_xu10__SVBool_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urhadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1013,16 +967,14 @@ svuint32_t test_svrhadd_n_u32_x(svbool_t pg, svuint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svrhadd_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrhadd_n_u64_xu10__SVBool_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urhadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rshl.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rshl.c
index 439c791f20ae..6df89c4aace8 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rshl.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rshl.c
@@ -477,16 +477,14 @@ svuint64_t test_svrshl_u64_x(svbool_t pg, svuint64_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svrshl_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svrshl_n_s8_zu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -501,8 +499,7 @@ svint8_t test_svrshl_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrshl_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -510,8 +507,7 @@ svint8_t test_svrshl_n_s8_z(svbool_t pg, svint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s16_zu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -526,8 +522,7 @@ svint16_t test_svrshl_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrshl_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -535,8 +530,7 @@ svint16_t test_svrshl_n_s16_z(svbool_t pg, svint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s32_zu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -551,8 +545,7 @@ svint32_t test_svrshl_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrshl_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -560,8 +553,7 @@ svint32_t test_svrshl_n_s32_z(svbool_t pg, svint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s64_zu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -575,16 +567,14 @@ svint64_t test_svrshl_n_s64_z(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrshl_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svrshl_n_u8_zu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urshl.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -599,8 +589,7 @@ svuint8_t test_svrshl_n_u8_z(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrshl_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -608,8 +597,7 @@ svuint8_t test_svrshl_n_u8_z(svbool_t pg, svuint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u16_zu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -624,8 +612,7 @@ svuint16_t test_svrshl_n_u16_z(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrshl_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -633,8 +620,7 @@ svuint16_t test_svrshl_n_u16_z(svbool_t pg, svuint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u32_zu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -649,8 +635,7 @@ svuint32_t test_svrshl_n_u32_z(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrshl_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -658,8 +643,7 @@ svuint32_t test_svrshl_n_u32_z(svbool_t pg, svuint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u64_zu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -673,15 +657,13 @@ svuint64_t test_svrshl_n_u64_z(svbool_t pg, svuint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrshl_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svrshl_n_s8_mu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -695,16 +677,14 @@ svint8_t test_svrshl_n_s8_m(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrshl_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s16_mu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -718,16 +698,14 @@ svint16_t test_svrshl_n_s16_m(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrshl_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s32_mu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -741,16 +719,14 @@ svint32_t test_svrshl_n_s32_m(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrshl_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s64_mu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -763,15 +739,13 @@ svint64_t test_svrshl_n_s64_m(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrshl_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svrshl_n_u8_mu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -785,16 +759,14 @@ svuint8_t test_svrshl_n_u8_m(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrshl_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u16_mu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -808,16 +780,14 @@ svuint16_t test_svrshl_n_u16_m(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrshl_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u32_mu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -831,16 +801,14 @@ svuint32_t test_svrshl_n_u32_m(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrshl_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u64_mu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -853,15 +821,13 @@ svuint64_t test_svrshl_n_u64_m(svbool_t pg, svuint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrshl_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svrshl_n_s8_xu10__SVBool_tu10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.srshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -875,16 +841,14 @@ svint8_t test_svrshl_n_s8_x(svbool_t pg, svint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrshl_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s16_xu10__SVBool_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -898,16 +862,14 @@ svint16_t test_svrshl_n_s16_x(svbool_t pg, svint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrshl_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s32_xu10__SVBool_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.srshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -921,16 +883,14 @@ svint32_t test_svrshl_n_s32_x(svbool_t pg, svint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrshl_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_s64_xu10__SVBool_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.srshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -943,15 +903,13 @@ svint64_t test_svrshl_n_s64_x(svbool_t pg, svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrshl_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svrshl_n_u8_xu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.urshl.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -965,16 +923,14 @@ svuint8_t test_svrshl_n_u8_x(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svrshl_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u16_xu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.urshl.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -988,16 +944,14 @@ svuint16_t test_svrshl_n_u16_x(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svrshl_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u32_xu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.urshl.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -1011,16 +965,14 @@ svuint32_t test_svrshl_n_u32_x(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svrshl_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svrshl_n_u64_xu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.urshl.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rsubhnb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rsubhnb.c
index c2fd636f315a..10f81f0e6553 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rsubhnb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rsubhnb.c
@@ -119,15 +119,13 @@ svuint32_t test_svrsubhnb_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svrsubhnb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.rsubhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnb_n_s16u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.rsubhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint8_t test_svrsubhnb_n_s16(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svrsubhnb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.rsubhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnb_n_s32u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.rsubhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint16_t test_svrsubhnb_n_s32(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svrsubhnb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.rsubhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnb_n_s64u11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.rsubhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint32_t test_svrsubhnb_n_s64(svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svrsubhnb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.rsubhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnb_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.rsubhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint8_t test_svrsubhnb_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svrsubhnb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.rsubhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnb_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.rsubhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint16_t test_svrsubhnb_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svrsubhnb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.rsubhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnb_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.rsubhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rsubhnt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rsubhnt.c
index d4dcba10f372..27084aaba0d8 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rsubhnt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_rsubhnt.c
@@ -119,15 +119,13 @@ svuint32_t test_svrsubhnt_u64(svuint32_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svrsubhnt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.rsubhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnt_n_s16u10__SVInt8_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.rsubhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint8_t test_svrsubhnt_n_s16(svint8_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svrsubhnt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.rsubhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnt_n_s32u11__SVInt16_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.rsubhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint16_t test_svrsubhnt_n_s32(svint16_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svrsubhnt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.rsubhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnt_n_s64u11__SVInt32_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.rsubhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint32_t test_svrsubhnt_n_s64(svint32_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svrsubhnt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.rsubhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnt_n_u16u11__SVUint8_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.rsubhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint8_t test_svrsubhnt_n_u16(svuint8_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svrsubhnt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.rsubhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnt_n_u32u12__SVUint16_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.rsubhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint16_t test_svrsubhnt_n_u32(svuint16_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svrsubhnt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.rsubhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svrsubhnt_n_u64u12__SVUint32_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.rsubhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sbclb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sbclb.c
index e2adafb09373..821bb94873fe 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sbclb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sbclb.c
@@ -51,15 +51,13 @@ svuint64_t test_svsbclb_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svsbclb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sbclb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsbclb_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sbclb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -72,15 +70,13 @@ svuint32_t test_svsbclb_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svsbclb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sbclb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsbclb_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sbclb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sbclt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sbclt.c
index fe1fea129ef1..85d62531288c 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sbclt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sbclt.c
@@ -51,15 +51,13 @@ svuint64_t test_svsbclt_u64(svuint64_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svsbclt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sbclt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsbclt_n_u32u12__SVUint32_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sbclt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -72,15 +70,13 @@ svuint32_t test_svsbclt_n_u32(svuint32_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svsbclt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sbclt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsbclt_n_u64u12__SVUint64_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sbclt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sqadd.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sqadd.c
index 936193d8d236..bf162093c7de 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sqadd.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sqadd.c
@@ -91,15 +91,13 @@ svuint64_t test_svsqadd_u64_m(svbool_t pg, svuint64_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svsqadd_n_u8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.usqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsqadd_n_u8_mu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.usqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -113,16 +111,14 @@ svuint8_t test_svsqadd_n_u8_m(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u16_mu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -136,16 +132,14 @@ svuint16_t test_svsqadd_n_u16_m(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u32_mu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -159,16 +153,14 @@ svuint32_t test_svsqadd_n_u32_m(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u64_mu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -263,16 +255,14 @@ svuint64_t test_svsqadd_u64_z(svbool_t pg, svuint64_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svsqadd_n_u8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.usqadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsqadd_n_u8_zu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.usqadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -287,8 +277,7 @@ svuint8_t test_svsqadd_n_u8_z(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -296,8 +285,7 @@ svuint8_t test_svsqadd_n_u8_z(svbool_t pg, svuint8_t op1, int8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u16_zu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -312,8 +300,7 @@ svuint16_t test_svsqadd_n_u16_z(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -321,8 +308,7 @@ svuint16_t test_svsqadd_n_u16_z(svbool_t pg, svuint16_t op1, int16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u32_zu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -337,8 +323,7 @@ svuint32_t test_svsqadd_n_u32_z(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -346,8 +331,7 @@ svuint32_t test_svsqadd_n_u32_z(svbool_t pg, svuint32_t op1, int32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u64_zu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -436,15 +420,13 @@ svuint64_t test_svsqadd_u64_x(svbool_t pg, svuint64_t op1, svint64_t op2)
 
 // CHECK-LABEL: @test_svsqadd_n_u8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.usqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsqadd_n_u8_xu10__SVBool_tu11__SVUint8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.usqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -458,16 +440,14 @@ svuint8_t test_svsqadd_n_u8_x(svbool_t pg, svuint8_t op1, int8_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u16_xu10__SVBool_tu12__SVUint16_ts(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -481,16 +461,14 @@ svuint16_t test_svsqadd_n_u16_x(svbool_t pg, svuint16_t op1, int16_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u32_xu10__SVBool_tu12__SVUint32_ti(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -504,16 +482,14 @@ svuint32_t test_svsqadd_n_u32_x(svbool_t pg, svuint32_t op1, int32_t op2)
 // CHECK-LABEL: @test_svsqadd_n_u64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svsqadd_n_u64_xu10__SVBool_tu12__SVUint64_tl(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subhnb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subhnb.c
index 6451de1d8845..6aac7783901e 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subhnb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subhnb.c
@@ -119,15 +119,13 @@ svuint32_t test_svsubhnb_u64(svuint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svsubhnb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnb_n_s16u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint8_t test_svsubhnb_n_s16(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svsubhnb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnb_n_s32u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint16_t test_svsubhnb_n_s32(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svsubhnb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnb_n_s64u11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint32_t test_svsubhnb_n_s64(svint64_t op1, int64_t op2)
 
 // CHECK-LABEL: @test_svsubhnb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnb_n_u16u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subhnb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint8_t test_svsubhnb_n_u16(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svsubhnb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnb_n_u32u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subhnb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint16_t test_svsubhnb_n_u32(svuint32_t op1, uint32_t op2)
 
 // CHECK-LABEL: @test_svsubhnb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnb_n_u64u12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subhnb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subhnt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subhnt.c
index e834f0365c3d..8a00938b6aab 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subhnt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subhnt.c
@@ -119,15 +119,13 @@ svuint32_t test_svsubhnt_u64(svuint32_t op1, svuint64_t op2, svuint64_t op3)
 
 // CHECK-LABEL: @test_svsubhnt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnt_n_s16u10__SVInt8_tu11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint8_t test_svsubhnt_n_s16(svint8_t op1, svint16_t op2, int16_t op3)
 
 // CHECK-LABEL: @test_svsubhnt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnt_n_s32u11__SVInt16_tu11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint16_t test_svsubhnt_n_s32(svint16_t op1, svint32_t op2, int32_t op3)
 
 // CHECK-LABEL: @test_svsubhnt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnt_n_s64u11__SVInt32_tu11__SVInt64_tl(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint32_t test_svsubhnt_n_s64(svint32_t op1, svint64_t op2, int64_t op3)
 
 // CHECK-LABEL: @test_svsubhnt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnt_n_u16u11__SVUint8_tu12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.subhnt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint8_t test_svsubhnt_n_u16(svuint8_t op1, svuint16_t op2, uint16_t op3)
 
 // CHECK-LABEL: @test_svsubhnt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnt_n_u32u12__SVUint16_tu12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.subhnt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint16_t test_svsubhnt_n_u32(svuint16_t op1, svuint32_t op2, uint32_t op3)
 
 // CHECK-LABEL: @test_svsubhnt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubhnt_n_u64u12__SVUint32_tu12__SVUint64_tm(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP3:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP3:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.subhnt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], <vscale x 2 x i64> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublb.c
index 8c70fd21535e..93845fcbf760 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublb.c
@@ -119,15 +119,13 @@ svuint64_t test_svsublb_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svsublb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssublb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublb_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssublb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svsublb_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svsublb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssublb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublb_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssublb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svsublb_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svsublb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssublb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublb_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssublb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svsublb_n_s64(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svsublb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usublb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublb_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usublb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svsublb_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svsublb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usublb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublb_n_u32u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usublb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svsublb_n_u32(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svsublb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usublb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublb_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usublb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublbt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublbt.c
index 3d33afd20009..674b2f7c64b5 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublbt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublbt.c
@@ -68,15 +68,13 @@ svint64_t test_svsublbt_s64(svint32_t op1, svint32_t op2)
 
 // CHECK-LABEL: @test_svsublbt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssublbt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsublbt_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssublbt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svsublbt_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svsublbt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssublbt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsublbt_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssublbt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svsublbt_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svsublbt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssublbt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsublbt_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssublbt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublt.c
index 895dfad667f7..25742e28ff14 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_sublt.c
@@ -119,15 +119,13 @@ svuint64_t test_svsublt_u64(svuint32_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svsublt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssublt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublt_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssublt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svsublt_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svsublt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssublt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublt_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssublt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svsublt_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svsublt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssublt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublt_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssublt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svsublt_n_s64(svint32_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svsublt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usublt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublt_n_u16u11__SVUint8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usublt.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svsublt_n_u16(svuint8_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svsublt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usublt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublt_n_u32u12__SVUint16_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usublt.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svsublt_n_u32(svuint16_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svsublt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usublt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsublt_n_u64u12__SVUint32_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usublt.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subltb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subltb.c
index 184e82970ff2..89cb511ca668 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subltb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subltb.c
@@ -68,15 +68,13 @@ svint64_t test_svsubltb_s64(svint32_t op1, svint32_t op2)
 
 // CHECK-LABEL: @test_svsubltb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssubltb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubltb_n_s16u10__SVInt8_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssubltb.nxv8i16(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -89,15 +87,13 @@ svint16_t test_svsubltb_n_s16(svint8_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svsubltb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssubltb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubltb_n_s32u11__SVInt16_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssubltb.nxv4i32(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -110,15 +106,13 @@ svint32_t test_svsubltb_n_s32(svint16_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svsubltb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssubltb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svsubltb_n_s64u11__SVInt32_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssubltb.nxv2i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subwb.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subwb.c
index 1531b0729245..b3519e4110b2 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subwb.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subwb.c
@@ -119,15 +119,13 @@ svuint64_t test_svsubwb_u64(svuint64_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svsubwb_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssubwb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwb_n_s16u11__SVInt16_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssubwb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svsubwb_n_s16(svint16_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svsubwb_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssubwb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwb_n_s32u11__SVInt32_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssubwb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svsubwb_n_s32(svint32_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svsubwb_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssubwb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwb_n_s64u11__SVInt64_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssubwb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svsubwb_n_s64(svint64_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svsubwb_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usubwb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwb_n_u16u12__SVUint16_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usubwb.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svsubwb_n_u16(svuint16_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svsubwb_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usubwb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwb_n_u32u12__SVUint32_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usubwb.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svsubwb_n_u32(svuint32_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svsubwb_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usubwb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwb_n_u64u12__SVUint64_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usubwb.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subwt.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subwt.c
index a8e793c2f23b..3b2a2da7710c 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subwt.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_subwt.c
@@ -119,15 +119,13 @@ svuint64_t test_svsubwt_u64(svuint64_t op1, svuint32_t op2)
 
 // CHECK-LABEL: @test_svsubwt_n_s16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssubwt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwt_n_s16u11__SVInt16_ta(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.ssubwt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -140,15 +138,13 @@ svint16_t test_svsubwt_n_s16(svint16_t op1, int8_t op2)
 
 // CHECK-LABEL: @test_svsubwt_n_s32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssubwt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwt_n_s32u11__SVInt32_ts(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.ssubwt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -161,15 +157,13 @@ svint32_t test_svsubwt_n_s32(svint32_t op1, int16_t op2)
 
 // CHECK-LABEL: @test_svsubwt_n_s64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssubwt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwt_n_s64u11__SVInt64_ti(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.ssubwt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
@@ -182,15 +176,13 @@ svint64_t test_svsubwt_n_s64(svint64_t op1, int32_t op2)
 
 // CHECK-LABEL: @test_svsubwt_n_u16(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usubwt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwt_n_u16u12__SVUint16_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.usubwt.nxv8i16(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 //
@@ -203,15 +195,13 @@ svuint16_t test_svsubwt_n_u16(svuint16_t op1, uint8_t op2)
 
 // CHECK-LABEL: @test_svsubwt_n_u32(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usubwt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwt_n_u32u12__SVUint32_tt(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.usubwt.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
 //
@@ -224,15 +214,13 @@ svuint32_t test_svsubwt_n_u32(svuint32_t op1, uint16_t op2)
 
 // CHECK-LABEL: @test_svsubwt_n_u64(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usubwt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z18test_svsubwt_n_u64u12__SVUint64_tj(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.usubwt.nxv2i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
 //
diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_uqadd.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_uqadd.c
index 2bd892934b93..35fc04b81191 100644
--- a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_uqadd.c
+++ b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_uqadd.c
@@ -91,15 +91,13 @@ svint64_t test_svuqadd_u64_m(svbool_t pg, svint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svuqadd_n_s8_m(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.suqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svuqadd_n_s8_mu10__SVBool_tu10__SVInt8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.suqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -113,16 +111,14 @@ svint8_t test_svuqadd_n_s8_m(svbool_t pg, svint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s16_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.suqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s16_mu10__SVBool_tu11__SVInt16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.suqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -136,16 +132,14 @@ svint16_t test_svuqadd_n_s16_m(svbool_t pg, svint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s32_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.suqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s32_mu10__SVBool_tu11__SVInt32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.suqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -159,16 +153,14 @@ svint32_t test_svuqadd_n_s32_m(svbool_t pg, svint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s64_m(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.suqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s64_mu10__SVBool_tu11__SVInt64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.suqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
@@ -263,16 +255,14 @@ svint64_t test_svuqadd_u64_z(svbool_t pg, svint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svuqadd_n_s8_z(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.suqadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svuqadd_n_s8_zu10__SVBool_tu10__SVInt8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.suqadd.nxv16i8(<vscale x 16 x i1> [[PG]], <vscale x 16 x i8> [[TMP1]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP2]]
@@ -287,8 +277,7 @@ svint8_t test_svuqadd_n_s8_z(svbool_t pg, svint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s16_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.suqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -296,8 +285,7 @@ svint8_t test_svuqadd_n_s8_z(svbool_t pg, svint8_t op1, uint8_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s16_zu10__SVBool_tu11__SVInt16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.suqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[TMP2]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP3]]
@@ -312,8 +300,7 @@ svint16_t test_svuqadd_n_s16_z(svbool_t pg, svint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s32_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.suqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -321,8 +308,7 @@ svint16_t test_svuqadd_n_s16_z(svbool_t pg, svint16_t op1, uint16_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s32_zu10__SVBool_tu11__SVInt32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.suqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[TMP2]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP3]]
@@ -337,8 +323,7 @@ svint32_t test_svuqadd_n_s32_z(svbool_t pg, svint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s64_z(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.suqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -346,8 +331,7 @@ svint32_t test_svuqadd_n_s32_z(svbool_t pg, svint32_t op1, uint32_t op2)
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s64_zu10__SVBool_tu11__SVInt64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> zeroinitializer)
 // CPP-CHECK-NEXT:    [[TMP3:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.suqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[TMP2]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
@@ -436,15 +420,13 @@ svint64_t test_svuqadd_u64_x(svbool_t pg, svint64_t op1, svuint64_t op2)
 
 // CHECK-LABEL: @test_svuqadd_n_s8_x(
 // CHECK-NEXT:  entry:
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.suqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
 // CPP-CHECK-LABEL: @_Z19test_svuqadd_n_s8_xu10__SVBool_tu10__SVInt8_th(
 // CPP-CHECK-NEXT:  entry:
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.suqadd.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[TMP0]])
 // CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
 //
@@ -458,16 +440,14 @@ svint8_t test_svuqadd_n_s8_x(svbool_t pg, svint8_t op1, uint8_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s16_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.suqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s16_xu10__SVBool_tu11__SVInt16_tt(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i16> poison, i16 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 8 x i16> [[DOTSPLATINSERT]], <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.suqadd.nxv8i16(<vscale x 8 x i1> [[TMP0]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 //
@@ -481,16 +461,14 @@ svint16_t test_svuqadd_n_s16_x(svbool_t pg, svint16_t op1, uint16_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s32_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.suqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s32_xu10__SVBool_tu11__SVInt32_tj(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.suqadd.nxv4i32(<vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 //
@@ -504,16 +482,14 @@ svint32_t test_svuqadd_n_s32_x(svbool_t pg, svint32_t op1, uint32_t op2)
 // CHECK-LABEL: @test_svuqadd_n_s64_x(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.suqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
 // CPP-CHECK-LABEL: @_Z20test_svuqadd_n_s64_xu10__SVBool_tu11__SVInt64_tm(
 // CPP-CHECK-NEXT:  entry:
 // CPP-CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
-// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[OP2:%.*]], i32 0
-// CPP-CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 [[OP2:%.*]])
 // CPP-CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.suqadd.nxv2i64(<vscale x 2 x i1> [[TMP0]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[TMP1]])
 // CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 //
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index f12854af9ab2..6abc8caaab81 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -438,18 +438,6 @@ static Optional<Instruction *> instCombineSVEDup(InstCombiner &IC,
   return IC.replaceInstUsesWith(II, Insert);
 }
 
-static Optional<Instruction *> instCombineSVEDupX(InstCombiner &IC,
-                                                  IntrinsicInst &II) {
-  // Replace DupX with a regular IR splat.
-  IRBuilder<> Builder(II.getContext());
-  Builder.SetInsertPoint(&II);
-  auto *RetTy = cast<ScalableVectorType>(II.getType());
-  Value *Splat =
-      Builder.CreateVectorSplat(RetTy->getElementCount(), II.getArgOperand(0));
-  Splat->takeName(&II);
-  return IC.replaceInstUsesWith(II, Splat);
-}
-
 static Optional<Instruction *> instCombineSVECmpNE(InstCombiner &IC,
                                                    IntrinsicInst &II) {
   LLVMContext &Ctx = II.getContext();
@@ -467,9 +455,12 @@ static Optional<Instruction *> instCombineSVECmpNE(InstCombiner &IC,
     return None;
 
   // Check that we have a compare of zero..
-  auto *SplatValue =
-      dyn_cast_or_null<ConstantInt>(getSplatValue(II.getArgOperand(2)));
-  if (!SplatValue || !SplatValue->isZero())
+  auto *DupX = dyn_cast<IntrinsicInst>(II.getArgOperand(2));
+  if (!DupX || DupX->getIntrinsicID() != Intrinsic::aarch64_sve_dup_x)
+    return None;
+
+  auto *DupXArg = dyn_cast<ConstantInt>(DupX->getArgOperand(0));
+  if (!DupXArg || !DupXArg->isZero())
     return None;
 
   // ..against a dupq
@@ -702,11 +693,14 @@ static Optional<Instruction *> instCombineSVEVectorMul(InstCombiner &IC,
   IRBuilder<> Builder(II.getContext());
   Builder.SetInsertPoint(&II);
 
-  // Return true if a given instruction is a unit splat value, false otherwise.
-  auto IsUnitSplat = [](auto *I) {
-    auto *SplatValue = getSplatValue(I);
-    if (!SplatValue)
+  // Return true if a given instruction is an aarch64_sve_dup_x intrinsic call
+  // with a unit splat value, false otherwise.
+  auto IsUnitDupX = [](auto *I) {
+    auto *IntrI = dyn_cast<IntrinsicInst>(I);
+    if (!IntrI || IntrI->getIntrinsicID() != Intrinsic::aarch64_sve_dup_x)
       return false;
+
+    auto *SplatValue = IntrI->getOperand(0);
     return match(SplatValue, m_FPOne()) || match(SplatValue, m_One());
   };
 
@@ -723,10 +717,10 @@ static Optional<Instruction *> instCombineSVEVectorMul(InstCombiner &IC,
 
   // The OpMultiplier variable should always point to the dup (if any), so
   // swap if necessary.
-  if (IsUnitDup(OpMultiplicand) || IsUnitSplat(OpMultiplicand))
+  if (IsUnitDup(OpMultiplicand) || IsUnitDupX(OpMultiplicand))
     std::swap(OpMultiplier, OpMultiplicand);
 
-  if (IsUnitSplat(OpMultiplier)) {
+  if (IsUnitDupX(OpMultiplier)) {
     // [f]mul pg (dupx 1) %n => %n
     OpMultiplicand->takeName(&II);
     return IC.replaceInstUsesWith(II, OpMultiplicand);
@@ -773,9 +767,13 @@ static Optional<Instruction *> instCombineSVETBL(InstCombiner &IC,
   auto *OpIndices = II.getOperand(1);
   VectorType *VTy = cast<VectorType>(II.getType());
 
-  // Check whether OpIndices is a constant splat value < minimal element count
-  // of result.
-  auto *SplatValue = dyn_cast_or_null<ConstantInt>(getSplatValue(OpIndices));
+  // Check whether OpIndices is an aarch64_sve_dup_x intrinsic call with
+  // constant splat value < minimal element count of result.
+  auto *DupXIntrI = dyn_cast<IntrinsicInst>(OpIndices);
+  if (!DupXIntrI || DupXIntrI->getIntrinsicID() != Intrinsic::aarch64_sve_dup_x)
+    return None;
+
+  auto *SplatValue = dyn_cast<ConstantInt>(DupXIntrI->getOperand(0));
   if (!SplatValue ||
       SplatValue->getValue().uge(VTy->getElementCount().getKnownMinValue()))
     return None;
@@ -803,8 +801,6 @@ AArch64TTIImpl::instCombineIntrinsic(InstCombiner &IC,
     return instCombineConvertFromSVBool(IC, II);
   case Intrinsic::aarch64_sve_dup:
     return instCombineSVEDup(IC, II);
-  case Intrinsic::aarch64_sve_dup_x:
-    return instCombineSVEDupX(IC, II);
   case Intrinsic::aarch64_sve_cmpne:
   case Intrinsic::aarch64_sve_cmpne_wide:
     return instCombineSVECmpNE(IC, II);
diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
index 9bc48d877795..d13f76c2be30 100644
--- a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-fmul-idempotency.ll
@@ -53,7 +53,8 @@ define <vscale x 8 x half> @idempotent_fmul_two_dups(<vscale x 8 x i1> %pg, <vsc
   ; Edge case -- make sure that the case where we're fmultiplying two dups
   ; together is sane.
 ; CHECK-LABEL: @idempotent_fmul_two_dups(
-; CHECK-NEXT:    ret <vscale x 8 x half> shufflevector (<vscale x 8 x half> insertelement (<vscale x 8 x half> poison, half 0xH3C00, i32 0), <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 0xH3C00)
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
 ;
   %1 = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 1.0)
   %2 = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 1.0)
@@ -64,8 +65,9 @@ define <vscale x 8 x half> @idempotent_fmul_two_dups(<vscale x 8 x i1> %pg, <vsc
 ; Non-idempotent fmuls -- we don't expect these to be optimised out.
 define <vscale x 8 x half> @non_idempotent_fmul_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) #0 {
 ; CHECK-LABEL: @non_idempotent_fmul_f16(
-; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> shufflevector (<vscale x 8 x half> insertelement (<vscale x 8 x half> poison, half 0xH4000, i32 0), <vscale x 8 x half> poison, <vscale x 8 x i32> zeroinitializer))
-; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 0xH4000)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x half> [[A:%.*]], <vscale x 8 x half> [[TMP1]])
+; CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
 ;
   %1 = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 2.0)
   %2 = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %1)
@@ -74,8 +76,9 @@ define <vscale x 8 x half> @non_idempotent_fmul_f16(<vscale x 8 x i1> %pg, <vsca
 
 define <vscale x 4 x float> @non_idempotent_fmul_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) #0 {
 ; CHECK-LABEL: @non_idempotent_fmul_f32(
-; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[PG:%.*]], <vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 2.000000e+00, i32 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer))
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float 2.000000e+00)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[PG:%.*]], <vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[TMP1]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP2]]
 ;
   %1 = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float 2.0)
   %2 = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %1)
@@ -84,8 +87,9 @@ define <vscale x 4 x float> @non_idempotent_fmul_f32(<vscale x 4 x i1> %pg, <vsc
 
 define <vscale x 2 x double> @non_idempotent_fmul_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) #0 {
 ; CHECK-LABEL: @non_idempotent_fmul_f64(
-; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> shufflevector (<vscale x 2 x double> insertelement (<vscale x 2 x double> poison, double 2.000000e+00, i32 0), <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer))
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double 2.000000e+00)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[TMP1]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP2]]
 ;
   %1 = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double 2.0)
   %2 = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %1)
diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
index e07fa9263a35..8e10050714a6 100644
--- a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-mul-idempotency.ll
@@ -53,7 +53,8 @@ define <vscale x 8 x i16> @idempotent_mul_two_dups(<vscale x 8 x i1> %pg, <vscal
   ; Edge case -- make sure that the case where we're multiplying two dups
   ; together is sane.
 ; CHECK-LABEL: @idempotent_mul_two_dups(
-; CHECK-NEXT:    ret <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 1, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 1)
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
 ;
   %1 = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 1)
   %2 = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 1)
@@ -64,8 +65,9 @@ define <vscale x 8 x i16> @idempotent_mul_two_dups(<vscale x 8 x i1> %pg, <vscal
 ; Non-idempotent muls -- we don't expect these to be optimised out.
 define <vscale x 8 x i16> @non_idempotent_mul_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a) #0 {
 ; CHECK-LABEL: @non_idempotent_mul_i16(
-; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
-; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]], <vscale x 8 x i16> [[TMP1]])
+; CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
 ;
   %1 = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
   %2 = call <vscale x 8 x i16> @llvm.aarch64.sve.mul.nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %1)
@@ -74,8 +76,9 @@ define <vscale x 8 x i16> @non_idempotent_mul_i16(<vscale x 8 x i1> %pg, <vscale
 
 define <vscale x 4 x i32> @non_idempotent_mul_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a) #0 {
 ; CHECK-LABEL: @non_idempotent_mul_i32(
-; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[PG:%.*]], <vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 2, i32 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer))
-; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 2)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> [[PG:%.*]], <vscale x 4 x i32> [[A:%.*]], <vscale x 4 x i32> [[TMP1]])
+; CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP2]]
 ;
   %1 = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 2)
   %2 = call <vscale x 4 x i32> @llvm.aarch64.sve.mul.nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %1)
@@ -84,8 +87,9 @@ define <vscale x 4 x i32> @non_idempotent_mul_i32(<vscale x 4 x i1> %pg, <vscale
 
 define <vscale x 2 x i64> @non_idempotent_mul_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) #0 {
 ; CHECK-LABEL: @non_idempotent_mul_i64(
-; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 2, i32 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer))
-; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 2)
+; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x i64> [[A:%.*]], <vscale x 2 x i64> [[TMP1]])
+; CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP2]]
 ;
   %1 = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 2)
   %2 = call <vscale x 2 x i64> @llvm.aarch64.sve.mul.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %1)
diff --git a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-opts-dup.ll b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-opts-dup.ll
index 668946f9eda4..add9cfb56f1e 100644
--- a/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-opts-dup.ll
+++ b/llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-opts-dup.ll
@@ -40,17 +40,6 @@ define <vscale x 8 x i16> @dup_insertelement_0_convert(<vscale x 8 x i16> %v, i1
   ret <vscale x 8 x i16> %insert
 }
 
-define <vscale x 8 x i16> @dupx_splat_convert(i16 %s) #0 {
-; CHECK-LABEL: @dupx_splat_convert(
-; CHECK-NEXT: %.splatinsert = insertelement <vscale x 8 x i16> poison, i16 %s, i32 0
-; CHECK-NEXT: %splat = shufflevector <vscale x 8 x i16> %.splatinsert, <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT: ret <vscale x 8 x i16> %splat
-  %splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 %s)
-  ret <vscale x 8 x i16> %splat
-}
-
-declare <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16)
-
 declare <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i1>, i8)
 declare <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, i16)