[AArch64] regenerate complete test checks; NFC

llvm/test/CodeGen/AArch64/arm64-dup.ll

@@ -1,8 +1,11 @@
-; RUN: llc < %s -mtriple=arm64-eabi -aarch64-neon-syntax=apple -asm-verbose=false | FileCheck %s
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=arm64-eabi -aarch64-neon-syntax=apple | FileCheck %s
 
 define <8 x i8> @v_dup8(i8 %A) nounwind {
-;CHECK-LABEL: v_dup8:
+; CHECK-LABEL: v_dup8:
-;CHECK: dup.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.8b v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <8 x i8> zeroinitializer, i8 %A, i32 0
 	%tmp2 = insertelement <8 x i8> %tmp1, i8 %A, i32 1
 	%tmp3 = insertelement <8 x i8> %tmp2, i8 %A, i32 2
@@ -15,8 +18,10 @@ define <8 x i8> @v_dup8(i8 %A) nounwind {
 }
 
 define <4 x i16> @v_dup16(i16 %A) nounwind {
-;CHECK-LABEL: v_dup16:
+; CHECK-LABEL: v_dup16:
-;CHECK: dup.4h
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.4h v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <4 x i16> zeroinitializer, i16 %A, i32 0
 	%tmp2 = insertelement <4 x i16> %tmp1, i16 %A, i32 1
 	%tmp3 = insertelement <4 x i16> %tmp2, i16 %A, i32 2
@@ -25,24 +30,31 @@ define <4 x i16> @v_dup16(i16 %A) nounwind {
 }
 
 define <2 x i32> @v_dup32(i32 %A) nounwind {
-;CHECK-LABEL: v_dup32:
+; CHECK-LABEL: v_dup32:
-;CHECK: dup.2s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.2s v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <2 x i32> zeroinitializer, i32 %A, i32 0
 	%tmp2 = insertelement <2 x i32> %tmp1, i32 %A, i32 1
 	ret <2 x i32> %tmp2
 }
 
 define <2 x float> @v_dupfloat(float %A) nounwind {
-;CHECK-LABEL: v_dupfloat:
+; CHECK-LABEL: v_dupfloat:
-;CHECK: dup.2s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-NEXT:    dup.2s v0, v0[0]
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <2 x float> zeroinitializer, float %A, i32 0
 	%tmp2 = insertelement <2 x float> %tmp1, float %A, i32 1
 	ret <2 x float> %tmp2
 }
 
 define <16 x i8> @v_dupQ8(i8 %A) nounwind {
-;CHECK-LABEL: v_dupQ8:
+; CHECK-LABEL: v_dupQ8:
-;CHECK: dup.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.16b v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <16 x i8> zeroinitializer, i8 %A, i32 0
 	%tmp2 = insertelement <16 x i8> %tmp1, i8 %A, i32 1
 	%tmp3 = insertelement <16 x i8> %tmp2, i8 %A, i32 2
@@ -63,8 +75,10 @@ define <16 x i8> @v_dupQ8(i8 %A) nounwind {
 }
 
 define <8 x i16> @v_dupQ16(i16 %A) nounwind {
-;CHECK-LABEL: v_dupQ16:
+; CHECK-LABEL: v_dupQ16:
-;CHECK: dup.8h
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.8h v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <8 x i16> zeroinitializer, i16 %A, i32 0
 	%tmp2 = insertelement <8 x i16> %tmp1, i16 %A, i32 1
 	%tmp3 = insertelement <8 x i16> %tmp2, i16 %A, i32 2
@@ -77,8 +91,10 @@ define <8 x i16> @v_dupQ16(i16 %A) nounwind {
 }
 
 define <4 x i32> @v_dupQ32(i32 %A) nounwind {
-;CHECK-LABEL: v_dupQ32:
+; CHECK-LABEL: v_dupQ32:
-;CHECK: dup.4s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.4s v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <4 x i32> zeroinitializer, i32 %A, i32 0
 	%tmp2 = insertelement <4 x i32> %tmp1, i32 %A, i32 1
 	%tmp3 = insertelement <4 x i32> %tmp2, i32 %A, i32 2
@@ -87,8 +103,11 @@ define <4 x i32> @v_dupQ32(i32 %A) nounwind {
 }
 
 define <4 x float> @v_dupQfloat(float %A) nounwind {
-;CHECK-LABEL: v_dupQfloat:
+; CHECK-LABEL: v_dupQfloat:
-;CHECK: dup.4s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-NEXT:    dup.4s v0, v0[0]
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <4 x float> zeroinitializer, float %A, i32 0
 	%tmp2 = insertelement <4 x float> %tmp1, float %A, i32 1
 	%tmp3 = insertelement <4 x float> %tmp2, float %A, i32 2
@@ -99,160 +118,210 @@ define <4 x float> @v_dupQfloat(float %A) nounwind {
 ; Check to make sure it works with shuffles, too.
 
 define <8 x i8> @v_shuffledup8(i8 %A) nounwind {
-;CHECK-LABEL: v_shuffledup8:
+; CHECK-LABEL: v_shuffledup8:
-;CHECK: dup.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.8b v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <8 x i8> undef, i8 %A, i32 0
 	%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> zeroinitializer
 	ret <8 x i8> %tmp2
 }
 
 define <4 x i16> @v_shuffledup16(i16 %A) nounwind {
-;CHECK-LABEL: v_shuffledup16:
+; CHECK-LABEL: v_shuffledup16:
-;CHECK: dup.4h
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.4h v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <4 x i16> undef, i16 %A, i32 0
 	%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> zeroinitializer
 	ret <4 x i16> %tmp2
 }
 
 define <2 x i32> @v_shuffledup32(i32 %A) nounwind {
-;CHECK-LABEL: v_shuffledup32:
+; CHECK-LABEL: v_shuffledup32:
-;CHECK: dup.2s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.2s v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <2 x i32> undef, i32 %A, i32 0
 	%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
 	ret <2 x i32> %tmp2
 }
 
 define <2 x float> @v_shuffledupfloat(float %A) nounwind {
-;CHECK-LABEL: v_shuffledupfloat:
+; CHECK-LABEL: v_shuffledupfloat:
-;CHECK: dup.2s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-NEXT:    dup.2s v0, v0[0]
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <2 x float> undef, float %A, i32 0
 	%tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> zeroinitializer
 	ret <2 x float> %tmp2
 }
 
 define <16 x i8> @v_shuffledupQ8(i8 %A) nounwind {
-;CHECK-LABEL: v_shuffledupQ8:
+; CHECK-LABEL: v_shuffledupQ8:
-;CHECK: dup.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.16b v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <16 x i8> undef, i8 %A, i32 0
 	%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> zeroinitializer
 	ret <16 x i8> %tmp2
 }
 
 define <8 x i16> @v_shuffledupQ16(i16 %A) nounwind {
-;CHECK-LABEL: v_shuffledupQ16:
+; CHECK-LABEL: v_shuffledupQ16:
-;CHECK: dup.8h
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.8h v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <8 x i16> undef, i16 %A, i32 0
 	%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> zeroinitializer
 	ret <8 x i16> %tmp2
 }
 
 define <4 x i32> @v_shuffledupQ32(i32 %A) nounwind {
-;CHECK-LABEL: v_shuffledupQ32:
+; CHECK-LABEL: v_shuffledupQ32:
-;CHECK: dup.4s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.4s v0, w0
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <4 x i32> undef, i32 %A, i32 0
 	%tmp2 = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> zeroinitializer
 	ret <4 x i32> %tmp2
 }
 
 define <4 x float> @v_shuffledupQfloat(float %A) nounwind {
-;CHECK-LABEL: v_shuffledupQfloat:
+; CHECK-LABEL: v_shuffledupQfloat:
-;CHECK: dup.4s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-NEXT:    dup.4s v0, v0[0]
+; CHECK-NEXT:    ret
 	%tmp1 = insertelement <4 x float> undef, float %A, i32 0
 	%tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> zeroinitializer
 	ret <4 x float> %tmp2
 }
 
 define <8 x i8> @vduplane8(<8 x i8>* %A) nounwind {
-;CHECK-LABEL: vduplane8:
+; CHECK-LABEL: vduplane8:
-;CHECK: dup.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    dup.8b v0, v0[1]
+; CHECK-NEXT:    ret
 	%tmp1 = load <8 x i8>, <8 x i8>* %A
 	%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> < i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1 >
 	ret <8 x i8> %tmp2
 }
 
 define <4 x i16> @vduplane16(<4 x i16>* %A) nounwind {
-;CHECK-LABEL: vduplane16:
+; CHECK-LABEL: vduplane16:
-;CHECK: dup.4h
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    dup.4h v0, v0[1]
+; CHECK-NEXT:    ret
 	%tmp1 = load <4 x i16>, <4 x i16>* %A
 	%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> < i32 1, i32 1, i32 1, i32 1 >
 	ret <4 x i16> %tmp2
 }
 
 define <2 x i32> @vduplane32(<2 x i32>* %A) nounwind {
-;CHECK-LABEL: vduplane32:
+; CHECK-LABEL: vduplane32:
-;CHECK: dup.2s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    dup.2s v0, v0[1]
+; CHECK-NEXT:    ret
 	%tmp1 = load <2 x i32>, <2 x i32>* %A
 	%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> < i32 1, i32 1 >
 	ret <2 x i32> %tmp2
 }
 
 define <2 x float> @vduplanefloat(<2 x float>* %A) nounwind {
-;CHECK-LABEL: vduplanefloat:
+; CHECK-LABEL: vduplanefloat:
-;CHECK: dup.2s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    dup.2s v0, v0[1]
+; CHECK-NEXT:    ret
 	%tmp1 = load <2 x float>, <2 x float>* %A
 	%tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> < i32 1, i32 1 >
 	ret <2 x float> %tmp2
 }
 
 define <16 x i8> @vduplaneQ8(<8 x i8>* %A) nounwind {
-;CHECK-LABEL: vduplaneQ8:
+; CHECK-LABEL: vduplaneQ8:
-;CHECK: dup.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    dup.16b v0, v0[1]
+; CHECK-NEXT:    ret
 	%tmp1 = load <8 x i8>, <8 x i8>* %A
 	%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <16 x i32> < i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1 >
 	ret <16 x i8> %tmp2
 }
 
 define <8 x i16> @vduplaneQ16(<4 x i16>* %A) nounwind {
-;CHECK-LABEL: vduplaneQ16:
+; CHECK-LABEL: vduplaneQ16:
-;CHECK: dup.8h
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    dup.8h v0, v0[1]
+; CHECK-NEXT:    ret
 	%tmp1 = load <4 x i16>, <4 x i16>* %A
 	%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <8 x i32> < i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1 >
 	ret <8 x i16> %tmp2
 }
 
 define <4 x i32> @vduplaneQ32(<2 x i32>* %A) nounwind {
-;CHECK-LABEL: vduplaneQ32:
+; CHECK-LABEL: vduplaneQ32:
-;CHECK: dup.4s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    dup.4s v0, v0[1]
+; CHECK-NEXT:    ret
 	%tmp1 = load <2 x i32>, <2 x i32>* %A
 	%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <4 x i32> < i32 1, i32 1, i32 1, i32 1 >
 	ret <4 x i32> %tmp2
 }
 
 define <4 x float> @vduplaneQfloat(<2 x float>* %A) nounwind {
-;CHECK-LABEL: vduplaneQfloat:
+; CHECK-LABEL: vduplaneQfloat:
-;CHECK: dup.4s
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    dup.4s v0, v0[1]
+; CHECK-NEXT:    ret
 	%tmp1 = load <2 x float>, <2 x float>* %A
 	%tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <4 x i32> < i32 1, i32 1, i32 1, i32 1 >
 	ret <4 x float> %tmp2
 }
 
 define <2 x i64> @foo(<2 x i64> %arg0_int64x1_t) nounwind readnone {
-;CHECK-LABEL: foo:
+; CHECK-LABEL: foo:
-;CHECK: dup.2d
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    dup.2d v0, v0[1]
+; CHECK-NEXT:    ret
 entry:
   %0 = shufflevector <2 x i64> %arg0_int64x1_t, <2 x i64> undef, <2 x i32> <i32 1, i32 1>
   ret <2 x i64> %0
 }
 
 define <2 x i64> @bar(<2 x i64> %arg0_int64x1_t) nounwind readnone {
-;CHECK-LABEL: bar:
+; CHECK-LABEL: bar:
-;CHECK: dup.2d
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    dup.2d v0, v0[0]
+; CHECK-NEXT:    ret
 entry:
   %0 = shufflevector <2 x i64> %arg0_int64x1_t, <2 x i64> undef, <2 x i32> <i32 0, i32 0>
   ret <2 x i64> %0
 }
 
 define <2 x double> @baz(<2 x double> %arg0_int64x1_t) nounwind readnone {
-;CHECK-LABEL: baz:
+; CHECK-LABEL: baz:
-;CHECK: dup.2d
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    dup.2d v0, v0[1]
+; CHECK-NEXT:    ret
 entry:
   %0 = shufflevector <2 x double> %arg0_int64x1_t, <2 x double> undef, <2 x i32> <i32 1, i32 1>
   ret <2 x double> %0
 }
 
 define <2 x double> @qux(<2 x double> %arg0_int64x1_t) nounwind readnone {
-;CHECK-LABEL: qux:
+; CHECK-LABEL: qux:
-;CHECK: dup.2d
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    dup.2d v0, v0[0]
+; CHECK-NEXT:    ret
 entry:
   %0 = shufflevector <2 x double> %arg0_int64x1_t, <2 x double> undef, <2 x i32> <i32 0, i32 0>
   ret <2 x double> %0
@@ -260,9 +329,11 @@ entry:
 
 define <2 x i32> @f(i32 %a, i32 %b) nounwind readnone  {
 ; CHECK-LABEL: f:
-; CHECK-NEXT: fmov s0, w0
+; CHECK:       // %bb.0:
-; CHECK-NEXT: mov.s v0[1], w1
+; CHECK-NEXT:    fmov s0, w0
-; CHECK-NEXT: ret
+; CHECK-NEXT:    mov.s v0[1], w1
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    ret
   %vecinit = insertelement <2 x i32> undef, i32 %a, i32 0
   %vecinit1 = insertelement <2 x i32> %vecinit, i32 %b, i32 1
   ret <2 x i32> %vecinit1
@@ -270,11 +341,12 @@ define <2 x i32> @f(i32 %a, i32 %b) nounwind readnone  {
 
 define <4 x i32> @g(i32 %a, i32 %b) nounwind readnone  {
 ; CHECK-LABEL: g:
-; CHECK-NEXT: fmov s0, w0
+; CHECK:       // %bb.0:
-; CHECK-NEXT: mov.s v0[1], w1
+; CHECK-NEXT:    fmov s0, w0
-; CHECK-NEXT: mov.s v0[2], w1
+; CHECK-NEXT:    mov.s v0[1], w1
-; CHECK-NEXT: mov.s v0[3], w0
+; CHECK-NEXT:    mov.s v0[2], w1
-; CHECK-NEXT: ret
+; CHECK-NEXT:    mov.s v0[3], w0
+; CHECK-NEXT:    ret
   %vecinit = insertelement <4 x i32> undef, i32 %a, i32 0
   %vecinit1 = insertelement <4 x i32> %vecinit, i32 %b, i32 1
   %vecinit2 = insertelement <4 x i32> %vecinit1, i32 %b, i32 2
@@ -284,9 +356,10 @@ define <4 x i32> @g(i32 %a, i32 %b) nounwind readnone  {
 
 define <2 x i64> @h(i64 %a, i64 %b) nounwind readnone  {
 ; CHECK-LABEL: h:
-; CHECK-NEXT: fmov d0, x0
+; CHECK:       // %bb.0:
-; CHECK-NEXT: mov.d v0[1], x1
+; CHECK-NEXT:    fmov d0, x0
-; CHECK-NEXT: ret
+; CHECK-NEXT:    mov.d v0[1], x1
+; CHECK-NEXT:    ret
   %vecinit = insertelement <2 x i64> undef, i64 %a, i32 0
   %vecinit1 = insertelement <2 x i64> %vecinit, i64 %b, i32 1
   ret <2 x i64> %vecinit1
@@ -301,7 +374,9 @@ define <2 x i64> @h(i64 %a, i64 %b) nounwind readnone  {
 ; *However*, it is a dup vD.4h, vN.h[2*idx].
 define <4 x i16> @test_build_illegal(<4 x i32> %in) {
 ; CHECK-LABEL: test_build_illegal:
-; CHECK: dup.4h v0, v0[6]
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.4h v0, v0[6]
+; CHECK-NEXT:    ret
   %val = extractelement <4 x i32> %in, i32 3
   %smallval = trunc i32 %val to i16
   %vec = insertelement <4x i16> undef, i16 %smallval, i32 3
@@ -314,7 +389,9 @@ define <4 x i16> @test_build_illegal(<4 x i32> %in) {
 ; the formation of an indexed-by-7 MLS.
 define <4 x i16> @test_high_splat(<4 x i16> %a, <4 x i16> %b, <8 x i16> %v) #0 {
 ; CHECK-LABEL: test_high_splat:
-; CHECK: mls.4h v0, v1, v2[7]
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    mls.4h v0, v1, v2[7]
+; CHECK-NEXT:    ret
 entry:
   %shuffle = shufflevector <8 x i16> %v, <8 x i16> undef, <4 x i32> <i32 7, i32 7, i32 7, i32 7>
   %mul = mul <4 x i16> %shuffle, %b
@@ -324,37 +401,44 @@ entry:
 
 ; Also test the DUP path in the PerfectShuffle generator.
 
-; CHECK-LABEL: test_perfectshuffle_dupext_v4i16:
-; CHECK-NEXT: dup.4h v0, v0[0]
-; CHECK-NEXT: ext.8b v0, v0, v1, #4
 define <4 x i16> @test_perfectshuffle_dupext_v4i16(<4 x i16> %a, <4 x i16> %b) nounwind {
+; CHECK-LABEL: test_perfectshuffle_dupext_v4i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    dup.4h v0, v0[0]
+; CHECK-NEXT:    ext.8b v0, v0, v1, #4
+; CHECK-NEXT:    ret
   %r = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 0, i32 4, i32 5>
   ret <4 x i16> %r
 }
 
-; CHECK-LABEL: test_perfectshuffle_dupext_v4f16:
-; CHECK-NEXT: dup.4h v0, v0[0]
-; CHECK-NEXT: ext.8b v0, v0, v1, #4
-; CHECK-NEXT: ret
 define <4 x half> @test_perfectshuffle_dupext_v4f16(<4 x half> %a, <4 x half> %b) nounwind {
+; CHECK-LABEL: test_perfectshuffle_dupext_v4f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    dup.4h v0, v0[0]
+; CHECK-NEXT:    ext.8b v0, v0, v1, #4
+; CHECK-NEXT:    ret
   %r = shufflevector <4 x half> %a, <4 x half> %b, <4 x i32> <i32 0, i32 0, i32 4, i32 5>
   ret <4 x half> %r
 }
 
-; CHECK-LABEL: test_perfectshuffle_dupext_v4i32:
-; CHECK-NEXT: dup.4s v0, v0[0]
-; CHECK-NEXT: ext.16b v0, v0, v1, #8
-; CHECK-NEXT: ret
 define <4 x i32> @test_perfectshuffle_dupext_v4i32(<4 x i32> %a, <4 x i32> %b) nounwind {
+; CHECK-LABEL: test_perfectshuffle_dupext_v4i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.4s v0, v0[0]
+; CHECK-NEXT:    ext.16b v0, v0, v1, #8
+; CHECK-NEXT:    ret
   %r = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 0, i32 4, i32 5>
   ret <4 x i32> %r
 }
 
-; CHECK-LABEL: test_perfectshuffle_dupext_v4f32:
-; CHECK-NEXT: dup.4s v0, v0[0]
-; CHECK-NEXT: ext.16b v0, v0, v1, #8
-; CHECK-NEXT: ret
 define <4 x float> @test_perfectshuffle_dupext_v4f32(<4 x float> %a, <4 x float> %b) nounwind {
+; CHECK-LABEL: test_perfectshuffle_dupext_v4f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    dup.4s v0, v0[0]
+; CHECK-NEXT:    ext.16b v0, v0, v1, #8
+; CHECK-NEXT:    ret
   %r = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 0, i32 4, i32 5>
   ret <4 x float> %r
 }