[RISCV] Support fixed vector extract element. Use VL=1 for scalable vector extract element.

I've changed to use VL=1 for slidedown and shifts to avoid extra
element processing that we don't need.

The i64 fixed vector handling on i32 isn't great if the vector type
isn't legal due to an ordering issue in type legalization. If the
vector type isn't legal, we fall back to default legalization
which will bitcast the vector to vXi32 and use two independent extracts.
Doing better will require handling several different cases by
manually inserting insert_subvector/extract_subvector to adjust the type
to a legal vector before emitting custom nodes.

Reviewed By: frasercrmck

Differential Revision: https://reviews.llvm.org/D97319

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -545,6 +545,7 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
         }
 
         setOperationAction(ISD::VECTOR_SHUFFLE, VT, Custom);
+        setOperationAction(ISD::EXTRACT_VECTOR_ELT, VT, Custom);
 
         setOperationAction(ISD::ADD, VT, Custom);
         setOperationAction(ISD::MUL, VT, Custom);
@@ -2030,12 +2031,21 @@ SDValue RISCVTargetLowering::lowerEXTRACT_VECTOR_ELT(SDValue Op,
   MVT VecVT = Vec.getSimpleValueType();
   MVT XLenVT = Subtarget.getXLenVT();
 
+  // If this is a fixed vector, we need to convert it to a scalable vector.
+  MVT ContainerVT = VecVT;
+  if (VecVT.isFixedLengthVector()) {
+    ContainerVT = getContainerForFixedLengthVector(DAG, VecVT, Subtarget);
+    Vec = convertToScalableVector(ContainerVT, Vec, DAG, Subtarget);
+  }
+
   // If the index is 0, the vector is already in the right position.
   if (!isNullConstant(Idx)) {
-    SDValue Mask, VL;
+    // Use a VL of 1 to avoid processing more elements than we need.
-    std::tie(Mask, VL) = getDefaultScalableVLOps(VecVT, DL, DAG, Subtarget);
+    SDValue VL = DAG.getConstant(1, DL, XLenVT);
-    Vec = DAG.getNode(RISCVISD::VSLIDEDOWN_VL, DL, VecVT, DAG.getUNDEF(VecVT),
+    MVT MaskVT = MVT::getVectorVT(MVT::i1, ContainerVT.getVectorElementCount());
-                      Vec, Idx, Mask, VL);
+    SDValue Mask = DAG.getNode(RISCVISD::VMSET_VL, DL, MaskVT, VL);
+    Vec = DAG.getNode(RISCVISD::VSLIDEDOWN_VL, DL, ContainerVT,
+                      DAG.getUNDEF(ContainerVT), Vec, Idx, Mask, VL);
   }
 
   if (!EltVT.isInteger()) {
@@ -2850,37 +2860,51 @@ void RISCVTargetLowering::ReplaceNodeResults(SDNode *N,
     SDLoc DL(N);
     SDValue Vec = N->getOperand(0);
     SDValue Idx = N->getOperand(1);
-    EVT VecVT = Vec.getValueType();
+
+    // The vector type hasn't been legalized yet so we can't issue target
+    // specific nodes if it needs legalization.
+    // FIXME: We would manually legalize if it's important.
+    if (!isTypeLegal(Vec.getValueType()))
+      return;
+
+    MVT VecVT = Vec.getSimpleValueType();
+
     assert(!Subtarget.is64Bit() && N->getValueType(0) == MVT::i64 &&
            VecVT.getVectorElementType() == MVT::i64 &&
            "Unexpected EXTRACT_VECTOR_ELT legalization");
 
-    if (!VecVT.isScalableVector())
+    // If this is a fixed vector, we need to convert it to a scalable vector.
-      return;
+    MVT ContainerVT = VecVT;
+    if (VecVT.isFixedLengthVector()) {
+      ContainerVT = getContainerForFixedLengthVector(DAG, VecVT, Subtarget);
+      Vec = convertToScalableVector(ContainerVT, Vec, DAG, Subtarget);
+    }
 
-    SDValue Slidedown = Vec;
     MVT XLenVT = Subtarget.getXLenVT();
+
+    // Use a VL of 1 to avoid processing more elements than we need.
+    MVT MaskVT = MVT::getVectorVT(MVT::i1, VecVT.getVectorElementCount());
+    SDValue VL = DAG.getConstant(1, DL, XLenVT);
+    SDValue Mask = DAG.getNode(RISCVISD::VMSET_VL, DL, MaskVT, VL);
+
     // Unless the index is known to be 0, we must slide the vector down to get
     // the desired element into index 0.
     if (!isNullConstant(Idx)) {
-      SDValue Mask, VL;
+      Vec = DAG.getNode(RISCVISD::VSLIDEDOWN_VL, DL, ContainerVT,
-      std::tie(Mask, VL) =
+                        DAG.getUNDEF(ContainerVT), Vec, Idx, Mask, VL);
-          getDefaultScalableVLOps(VecVT.getSimpleVT(), DL, DAG, Subtarget);
-      Slidedown = DAG.getNode(RISCVISD::VSLIDEDOWN_VL, DL, VecVT,
-                              DAG.getUNDEF(VecVT), Vec, Idx, Mask, VL);
     }
 
     // Extract the lower XLEN bits of the correct vector element.
-    SDValue EltLo = DAG.getNode(RISCVISD::VMV_X_S, DL, XLenVT, Slidedown, Idx);
+    SDValue EltLo = DAG.getNode(RISCVISD::VMV_X_S, DL, XLenVT, Vec);
 
     // To extract the upper XLEN bits of the vector element, shift the first
     // element right by 32 bits and re-extract the lower XLEN bits.
-    SDValue ThirtyTwoV =
+    SDValue ThirtyTwoV = DAG.getNode(RISCVISD::VMV_V_X_VL, DL, ContainerVT,
-        DAG.getNode(RISCVISD::SPLAT_VECTOR_I64, DL, VecVT,
+                                     DAG.getConstant(32, DL, XLenVT), VL);
-                    DAG.getConstant(32, DL, Subtarget.getXLenVT()));
+    SDValue LShr32 = DAG.getNode(RISCVISD::SRL_VL, DL, ContainerVT, Vec,
-    SDValue LShr32 = DAG.getNode(ISD::SRL, DL, VecVT, Slidedown, ThirtyTwoV);
+                                 ThirtyTwoV, Mask, VL);
 
-    SDValue EltHi = DAG.getNode(RISCVISD::VMV_X_S, DL, XLenVT, LShr32, Idx);
+    SDValue EltHi = DAG.getNode(RISCVISD::VMV_X_S, DL, XLenVT, LShr32);
 
     Results.push_back(DAG.getNode(ISD::BUILD_PAIR, DL, MVT::i64, EltLo, EltHi));
     break;

llvm/test/CodeGen/RISCV/rvv/extractelt-fp-rv32.ll

@@ -15,8 +15,10 @@ define half @extractelt_nxv1f16_0(<vscale x 1 x half> %v) {
 define half @extractelt_nxv1f16_imm(<vscale x 1 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv1f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x half> %v, i32 2
@@ -26,8 +28,10 @@ define half @extractelt_nxv1f16_imm(<vscale x 1 x half> %v) {
 define half @extractelt_nxv1f16_idx(<vscale x 1 x half> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv1f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,mf4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x half> %v, i32 %idx
@@ -47,8 +51,10 @@ define half @extractelt_nxv2f16_0(<vscale x 2 x half> %v) {
 define half @extractelt_nxv2f16_imm(<vscale x 2 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv2f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x half> %v, i32 2
@@ -58,8 +64,10 @@ define half @extractelt_nxv2f16_imm(<vscale x 2 x half> %v) {
 define half @extractelt_nxv2f16_idx(<vscale x 2 x half> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv2f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x half> %v, i32 %idx
@@ -79,8 +87,10 @@ define half @extractelt_nxv4f16_0(<vscale x 4 x half> %v) {
 define half @extractelt_nxv4f16_imm(<vscale x 4 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv4f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x half> %v, i32 2
@@ -90,8 +100,10 @@ define half @extractelt_nxv4f16_imm(<vscale x 4 x half> %v) {
 define half @extractelt_nxv4f16_idx(<vscale x 4 x half> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv4f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x half> %v, i32 %idx
@@ -111,8 +123,10 @@ define half @extractelt_nxv8f16_0(<vscale x 8 x half> %v) {
 define half @extractelt_nxv8f16_imm(<vscale x 8 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv8f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x half> %v, i32 2
@@ -122,8 +136,10 @@ define half @extractelt_nxv8f16_imm(<vscale x 8 x half> %v) {
 define half @extractelt_nxv8f16_idx(<vscale x 8 x half> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv8f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x half> %v, i32 %idx
@@ -143,8 +159,10 @@ define half @extractelt_nxv16f16_0(<vscale x 16 x half> %v) {
 define half @extractelt_nxv16f16_imm(<vscale x 16 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv16f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x half> %v, i32 2
@@ -154,8 +172,10 @@ define half @extractelt_nxv16f16_imm(<vscale x 16 x half> %v) {
 define half @extractelt_nxv16f16_idx(<vscale x 16 x half> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv16f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x half> %v, i32 %idx
@@ -175,8 +195,10 @@ define half @extractelt_nxv32f16_0(<vscale x 32 x half> %v) {
 define half @extractelt_nxv32f16_imm(<vscale x 32 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv32f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x half> %v, i32 2
@@ -186,8 +208,10 @@ define half @extractelt_nxv32f16_imm(<vscale x 32 x half> %v) {
 define half @extractelt_nxv32f16_idx(<vscale x 32 x half> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv32f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x half> %v, i32 %idx
@@ -207,8 +231,10 @@ define float @extractelt_nxv1f32_0(<vscale x 1 x float> %v) {
 define float @extractelt_nxv1f32_imm(<vscale x 1 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv1f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,mf2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x float> %v, i32 2
@@ -218,8 +244,10 @@ define float @extractelt_nxv1f32_imm(<vscale x 1 x float> %v) {
 define float @extractelt_nxv1f32_idx(<vscale x 1 x float> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv1f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,mf2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x float> %v, i32 %idx
@@ -239,8 +267,10 @@ define float @extractelt_nxv2f32_0(<vscale x 2 x float> %v) {
 define float @extractelt_nxv2f32_imm(<vscale x 2 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv2f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x float> %v, i32 2
@@ -250,8 +280,10 @@ define float @extractelt_nxv2f32_imm(<vscale x 2 x float> %v) {
 define float @extractelt_nxv2f32_idx(<vscale x 2 x float> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv2f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x float> %v, i32 %idx
@@ -271,8 +303,10 @@ define float @extractelt_nxv4f32_0(<vscale x 4 x float> %v) {
 define float @extractelt_nxv4f32_imm(<vscale x 4 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv4f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x float> %v, i32 2
@@ -282,8 +316,10 @@ define float @extractelt_nxv4f32_imm(<vscale x 4 x float> %v) {
 define float @extractelt_nxv4f32_idx(<vscale x 4 x float> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv4f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x float> %v, i32 %idx
@@ -303,8 +339,10 @@ define float @extractelt_nxv8f32_0(<vscale x 8 x float> %v) {
 define float @extractelt_nxv8f32_imm(<vscale x 8 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv8f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x float> %v, i32 2
@@ -314,8 +352,10 @@ define float @extractelt_nxv8f32_imm(<vscale x 8 x float> %v) {
 define float @extractelt_nxv8f32_idx(<vscale x 8 x float> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv8f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x float> %v, i32 %idx
@@ -335,8 +375,10 @@ define float @extractelt_nxv16f32_0(<vscale x 16 x float> %v) {
 define float @extractelt_nxv16f32_imm(<vscale x 16 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv16f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x float> %v, i32 2
@@ -346,8 +388,10 @@ define float @extractelt_nxv16f32_imm(<vscale x 16 x float> %v) {
 define float @extractelt_nxv16f32_idx(<vscale x 16 x float> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv16f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x float> %v, i32 %idx
@@ -367,8 +411,10 @@ define double @extractelt_nxv1f64_0(<vscale x 1 x double> %v) {
 define double @extractelt_nxv1f64_imm(<vscale x 1 x double> %v) {
 ; CHECK-LABEL: extractelt_nxv1f64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x double> %v, i32 2
@@ -378,8 +424,10 @@ define double @extractelt_nxv1f64_imm(<vscale x 1 x double> %v) {
 define double @extractelt_nxv1f64_idx(<vscale x 1 x double> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv1f64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x double> %v, i32 %idx
@@ -399,8 +447,10 @@ define double @extractelt_nxv2f64_0(<vscale x 2 x double> %v) {
 define double @extractelt_nxv2f64_imm(<vscale x 2 x double> %v) {
 ; CHECK-LABEL: extractelt_nxv2f64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x double> %v, i32 2
@@ -410,8 +460,10 @@ define double @extractelt_nxv2f64_imm(<vscale x 2 x double> %v) {
 define double @extractelt_nxv2f64_idx(<vscale x 2 x double> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv2f64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x double> %v, i32 %idx
@@ -431,8 +483,10 @@ define double @extractelt_nxv4f64_0(<vscale x 4 x double> %v) {
 define double @extractelt_nxv4f64_imm(<vscale x 4 x double> %v) {
 ; CHECK-LABEL: extractelt_nxv4f64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x double> %v, i32 2
@@ -442,8 +496,10 @@ define double @extractelt_nxv4f64_imm(<vscale x 4 x double> %v) {
 define double @extractelt_nxv4f64_idx(<vscale x 4 x double> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv4f64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x double> %v, i32 %idx
@@ -463,8 +519,10 @@ define double @extractelt_nxv8f64_0(<vscale x 8 x double> %v) {
 define double @extractelt_nxv8f64_imm(<vscale x 8 x double> %v) {
 ; CHECK-LABEL: extractelt_nxv8f64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x double> %v, i32 2
@@ -474,8 +532,10 @@ define double @extractelt_nxv8f64_imm(<vscale x 8 x double> %v) {
 define double @extractelt_nxv8f64_idx(<vscale x 8 x double> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv8f64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x double> %v, i32 %idx

llvm/test/CodeGen/RISCV/rvv/extractelt-fp-rv64.ll

@@ -15,8 +15,10 @@ define half @extractelt_nxv1f16_0(<vscale x 1 x half> %v) {
 define half @extractelt_nxv1f16_imm(<vscale x 1 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv1f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x half> %v, i32 2
@@ -26,8 +28,10 @@ define half @extractelt_nxv1f16_imm(<vscale x 1 x half> %v) {
 define half @extractelt_nxv1f16_idx(<vscale x 1 x half> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv1f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,mf4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x half> %v, i32 %idx
@@ -47,8 +51,10 @@ define half @extractelt_nxv2f16_0(<vscale x 2 x half> %v) {
 define half @extractelt_nxv2f16_imm(<vscale x 2 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv2f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x half> %v, i32 2
@@ -58,8 +64,10 @@ define half @extractelt_nxv2f16_imm(<vscale x 2 x half> %v) {
 define half @extractelt_nxv2f16_idx(<vscale x 2 x half> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv2f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x half> %v, i32 %idx
@@ -79,8 +87,10 @@ define half @extractelt_nxv4f16_0(<vscale x 4 x half> %v) {
 define half @extractelt_nxv4f16_imm(<vscale x 4 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv4f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x half> %v, i32 2
@@ -90,8 +100,10 @@ define half @extractelt_nxv4f16_imm(<vscale x 4 x half> %v) {
 define half @extractelt_nxv4f16_idx(<vscale x 4 x half> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv4f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x half> %v, i32 %idx
@@ -111,8 +123,10 @@ define half @extractelt_nxv8f16_0(<vscale x 8 x half> %v) {
 define half @extractelt_nxv8f16_imm(<vscale x 8 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv8f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x half> %v, i32 2
@@ -122,8 +136,10 @@ define half @extractelt_nxv8f16_imm(<vscale x 8 x half> %v) {
 define half @extractelt_nxv8f16_idx(<vscale x 8 x half> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv8f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x half> %v, i32 %idx
@@ -143,8 +159,10 @@ define half @extractelt_nxv16f16_0(<vscale x 16 x half> %v) {
 define half @extractelt_nxv16f16_imm(<vscale x 16 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv16f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x half> %v, i32 2
@@ -154,8 +172,10 @@ define half @extractelt_nxv16f16_imm(<vscale x 16 x half> %v) {
 define half @extractelt_nxv16f16_idx(<vscale x 16 x half> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv16f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x half> %v, i32 %idx
@@ -175,8 +195,10 @@ define half @extractelt_nxv32f16_0(<vscale x 32 x half> %v) {
 define half @extractelt_nxv32f16_imm(<vscale x 32 x half> %v) {
 ; CHECK-LABEL: extractelt_nxv32f16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x half> %v, i32 2
@@ -186,8 +208,10 @@ define half @extractelt_nxv32f16_imm(<vscale x 32 x half> %v) {
 define half @extractelt_nxv32f16_idx(<vscale x 32 x half> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv32f16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x half> %v, i32 %idx
@@ -207,8 +231,10 @@ define float @extractelt_nxv1f32_0(<vscale x 1 x float> %v) {
 define float @extractelt_nxv1f32_imm(<vscale x 1 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv1f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,mf2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x float> %v, i32 2
@@ -218,8 +244,10 @@ define float @extractelt_nxv1f32_imm(<vscale x 1 x float> %v) {
 define float @extractelt_nxv1f32_idx(<vscale x 1 x float> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv1f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,mf2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x float> %v, i32 %idx
@@ -239,8 +267,10 @@ define float @extractelt_nxv2f32_0(<vscale x 2 x float> %v) {
 define float @extractelt_nxv2f32_imm(<vscale x 2 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv2f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x float> %v, i32 2
@@ -250,8 +280,10 @@ define float @extractelt_nxv2f32_imm(<vscale x 2 x float> %v) {
 define float @extractelt_nxv2f32_idx(<vscale x 2 x float> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv2f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x float> %v, i32 %idx
@@ -271,8 +303,10 @@ define float @extractelt_nxv4f32_0(<vscale x 4 x float> %v) {
 define float @extractelt_nxv4f32_imm(<vscale x 4 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv4f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x float> %v, i32 2
@@ -282,8 +316,10 @@ define float @extractelt_nxv4f32_imm(<vscale x 4 x float> %v) {
 define float @extractelt_nxv4f32_idx(<vscale x 4 x float> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv4f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x float> %v, i32 %idx
@@ -303,8 +339,10 @@ define float @extractelt_nxv8f32_0(<vscale x 8 x float> %v) {
 define float @extractelt_nxv8f32_imm(<vscale x 8 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv8f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x float> %v, i32 2
@@ -314,8 +352,10 @@ define float @extractelt_nxv8f32_imm(<vscale x 8 x float> %v) {
 define float @extractelt_nxv8f32_idx(<vscale x 8 x float> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv8f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x float> %v, i32 %idx
@@ -335,8 +375,10 @@ define float @extractelt_nxv16f32_0(<vscale x 16 x float> %v) {
 define float @extractelt_nxv16f32_imm(<vscale x 16 x float> %v) {
 ; CHECK-LABEL: extractelt_nxv16f32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x float> %v, i32 2
@@ -346,8 +388,10 @@ define float @extractelt_nxv16f32_imm(<vscale x 16 x float> %v) {
 define float @extractelt_nxv16f32_idx(<vscale x 16 x float> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv16f32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x float> %v, i32 %idx
@@ -367,8 +411,10 @@ define double @extractelt_nxv1f64_0(<vscale x 1 x double> %v) {
 define double @extractelt_nxv1f64_imm(<vscale x 1 x double> %v) {
 ; CHECK-LABEL: extractelt_nxv1f64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x double> %v, i32 2
@@ -378,8 +424,10 @@ define double @extractelt_nxv1f64_imm(<vscale x 1 x double> %v) {
 define double @extractelt_nxv1f64_idx(<vscale x 1 x double> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv1f64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x double> %v, i32 %idx
@@ -399,8 +447,10 @@ define double @extractelt_nxv2f64_0(<vscale x 2 x double> %v) {
 define double @extractelt_nxv2f64_imm(<vscale x 2 x double> %v) {
 ; CHECK-LABEL: extractelt_nxv2f64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x double> %v, i32 2
@@ -410,8 +460,10 @@ define double @extractelt_nxv2f64_imm(<vscale x 2 x double> %v) {
 define double @extractelt_nxv2f64_idx(<vscale x 2 x double> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv2f64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x double> %v, i32 %idx
@@ -431,8 +483,10 @@ define double @extractelt_nxv4f64_0(<vscale x 4 x double> %v) {
 define double @extractelt_nxv4f64_imm(<vscale x 4 x double> %v) {
 ; CHECK-LABEL: extractelt_nxv4f64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x double> %v, i32 2
@@ -442,8 +496,10 @@ define double @extractelt_nxv4f64_imm(<vscale x 4 x double> %v) {
 define double @extractelt_nxv4f64_idx(<vscale x 4 x double> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv4f64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x double> %v, i32 %idx
@@ -463,8 +519,10 @@ define double @extractelt_nxv8f64_0(<vscale x 8 x double> %v) {
 define double @extractelt_nxv8f64_imm(<vscale x 8 x double> %v) {
 ; CHECK-LABEL: extractelt_nxv8f64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x double> %v, i32 2
@@ -474,8 +532,10 @@ define double @extractelt_nxv8f64_imm(<vscale x 8 x double> %v) {
 define double @extractelt_nxv8f64_idx(<vscale x 8 x double> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv8f64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vfmv.f.s fa0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x double> %v, i32 %idx

llvm/test/CodeGen/RISCV/rvv/extractelt-int-rv32.ll

@@ -15,8 +15,10 @@ define signext i8 @extractelt_nxv1i8_0(<vscale x 1 x i8> %v) {
 define signext i8 @extractelt_nxv1i8_imm(<vscale x 1 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv1i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,mf8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i8> %v, i32 2
@@ -26,8 +28,10 @@ define signext i8 @extractelt_nxv1i8_imm(<vscale x 1 x i8> %v) {
 define signext i8 @extractelt_nxv1i8_idx(<vscale x 1 x i8> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv1i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,mf8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i8> %v, i32 %idx
@@ -47,8 +51,10 @@ define signext i8 @extractelt_nxv2i8_0(<vscale x 2 x i8> %v) {
 define signext i8 @extractelt_nxv2i8_imm(<vscale x 2 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv2i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,mf4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i8> %v, i32 2
@@ -58,8 +64,10 @@ define signext i8 @extractelt_nxv2i8_imm(<vscale x 2 x i8> %v) {
 define signext i8 @extractelt_nxv2i8_idx(<vscale x 2 x i8> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv2i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,mf4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i8> %v, i32 %idx
@@ -79,8 +87,10 @@ define signext i8 @extractelt_nxv4i8_0(<vscale x 4 x i8> %v) {
 define signext i8 @extractelt_nxv4i8_imm(<vscale x 4 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv4i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i8> %v, i32 2
@@ -90,8 +100,10 @@ define signext i8 @extractelt_nxv4i8_imm(<vscale x 4 x i8> %v) {
 define signext i8 @extractelt_nxv4i8_idx(<vscale x 4 x i8> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv4i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i8> %v, i32 %idx
@@ -111,8 +123,10 @@ define signext i8 @extractelt_nxv8i8_0(<vscale x 8 x i8> %v) {
 define signext i8 @extractelt_nxv8i8_imm(<vscale x 8 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv8i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i8> %v, i32 2
@@ -122,8 +136,10 @@ define signext i8 @extractelt_nxv8i8_imm(<vscale x 8 x i8> %v) {
 define signext i8 @extractelt_nxv8i8_idx(<vscale x 8 x i8> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv8i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i8> %v, i32 %idx
@@ -143,8 +159,10 @@ define signext i8 @extractelt_nxv16i8_0(<vscale x 16 x i8> %v) {
 define signext i8 @extractelt_nxv16i8_imm(<vscale x 16 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv16i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i8> %v, i32 2
@@ -154,8 +172,10 @@ define signext i8 @extractelt_nxv16i8_imm(<vscale x 16 x i8> %v) {
 define signext i8 @extractelt_nxv16i8_idx(<vscale x 16 x i8> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv16i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i8> %v, i32 %idx
@@ -175,8 +195,10 @@ define signext i8 @extractelt_nxv32i8_0(<vscale x 32 x i8> %v) {
 define signext i8 @extractelt_nxv32i8_imm(<vscale x 32 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv32i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x i8> %v, i32 2
@@ -186,8 +208,10 @@ define signext i8 @extractelt_nxv32i8_imm(<vscale x 32 x i8> %v) {
 define signext i8 @extractelt_nxv32i8_idx(<vscale x 32 x i8> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv32i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x i8> %v, i32 %idx
@@ -207,8 +231,10 @@ define signext i8 @extractelt_nxv64i8_0(<vscale x 64 x i8> %v) {
 define signext i8 @extractelt_nxv64i8_imm(<vscale x 64 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv64i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 64 x i8> %v, i32 2
@@ -218,8 +244,10 @@ define signext i8 @extractelt_nxv64i8_imm(<vscale x 64 x i8> %v) {
 define signext i8 @extractelt_nxv64i8_idx(<vscale x 64 x i8> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv64i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 64 x i8> %v, i32 %idx
@@ -239,8 +267,10 @@ define signext i16 @extractelt_nxv1i16_0(<vscale x 1 x i16> %v) {
 define signext i16 @extractelt_nxv1i16_imm(<vscale x 1 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv1i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i16> %v, i32 2
@@ -250,8 +280,10 @@ define signext i16 @extractelt_nxv1i16_imm(<vscale x 1 x i16> %v) {
 define signext i16 @extractelt_nxv1i16_idx(<vscale x 1 x i16> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv1i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,mf4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i16> %v, i32 %idx
@@ -271,8 +303,10 @@ define signext i16 @extractelt_nxv2i16_0(<vscale x 2 x i16> %v) {
 define signext i16 @extractelt_nxv2i16_imm(<vscale x 2 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv2i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i16> %v, i32 2
@@ -282,8 +316,10 @@ define signext i16 @extractelt_nxv2i16_imm(<vscale x 2 x i16> %v) {
 define signext i16 @extractelt_nxv2i16_idx(<vscale x 2 x i16> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv2i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i16> %v, i32 %idx
@@ -303,8 +339,10 @@ define signext i16 @extractelt_nxv4i16_0(<vscale x 4 x i16> %v) {
 define signext i16 @extractelt_nxv4i16_imm(<vscale x 4 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv4i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i16> %v, i32 2
@@ -314,8 +352,10 @@ define signext i16 @extractelt_nxv4i16_imm(<vscale x 4 x i16> %v) {
 define signext i16 @extractelt_nxv4i16_idx(<vscale x 4 x i16> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv4i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i16> %v, i32 %idx
@@ -335,8 +375,10 @@ define signext i16 @extractelt_nxv8i16_0(<vscale x 8 x i16> %v) {
 define signext i16 @extractelt_nxv8i16_imm(<vscale x 8 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv8i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i16> %v, i32 2
@@ -346,8 +388,10 @@ define signext i16 @extractelt_nxv8i16_imm(<vscale x 8 x i16> %v) {
 define signext i16 @extractelt_nxv8i16_idx(<vscale x 8 x i16> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv8i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i16> %v, i32 %idx
@@ -367,8 +411,10 @@ define signext i16 @extractelt_nxv16i16_0(<vscale x 16 x i16> %v) {
 define signext i16 @extractelt_nxv16i16_imm(<vscale x 16 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv16i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i16> %v, i32 2
@@ -378,8 +424,10 @@ define signext i16 @extractelt_nxv16i16_imm(<vscale x 16 x i16> %v) {
 define signext i16 @extractelt_nxv16i16_idx(<vscale x 16 x i16> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv16i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i16> %v, i32 %idx
@@ -399,8 +447,10 @@ define signext i16 @extractelt_nxv32i16_0(<vscale x 32 x i16> %v) {
 define signext i16 @extractelt_nxv32i16_imm(<vscale x 32 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv32i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x i16> %v, i32 2
@@ -410,8 +460,10 @@ define signext i16 @extractelt_nxv32i16_imm(<vscale x 32 x i16> %v) {
 define signext i16 @extractelt_nxv32i16_idx(<vscale x 32 x i16> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv32i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x i16> %v, i32 %idx
@@ -431,8 +483,10 @@ define i32 @extractelt_nxv1i32_0(<vscale x 1 x i32> %v) {
 define i32 @extractelt_nxv1i32_imm(<vscale x 1 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv1i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i32> %v, i32 2
@@ -442,8 +496,10 @@ define i32 @extractelt_nxv1i32_imm(<vscale x 1 x i32> %v) {
 define i32 @extractelt_nxv1i32_idx(<vscale x 1 x i32> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv1i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i32> %v, i32 %idx
@@ -463,8 +519,10 @@ define i32 @extractelt_nxv2i32_0(<vscale x 2 x i32> %v) {
 define i32 @extractelt_nxv2i32_imm(<vscale x 2 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv2i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i32> %v, i32 2
@@ -474,8 +532,10 @@ define i32 @extractelt_nxv2i32_imm(<vscale x 2 x i32> %v) {
 define i32 @extractelt_nxv2i32_idx(<vscale x 2 x i32> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv2i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i32> %v, i32 %idx
@@ -495,8 +555,10 @@ define i32 @extractelt_nxv4i32_0(<vscale x 4 x i32> %v) {
 define i32 @extractelt_nxv4i32_imm(<vscale x 4 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv4i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i32> %v, i32 2
@@ -506,8 +568,10 @@ define i32 @extractelt_nxv4i32_imm(<vscale x 4 x i32> %v) {
 define i32 @extractelt_nxv4i32_idx(<vscale x 4 x i32> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv4i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i32> %v, i32 %idx
@@ -527,8 +591,10 @@ define i32 @extractelt_nxv8i32_0(<vscale x 8 x i32> %v) {
 define i32 @extractelt_nxv8i32_imm(<vscale x 8 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv8i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i32> %v, i32 2
@@ -538,8 +604,10 @@ define i32 @extractelt_nxv8i32_imm(<vscale x 8 x i32> %v) {
 define i32 @extractelt_nxv8i32_idx(<vscale x 8 x i32> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv8i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i32> %v, i32 %idx
@@ -559,8 +627,10 @@ define i32 @extractelt_nxv16i32_0(<vscale x 16 x i32> %v) {
 define i32 @extractelt_nxv16i32_imm(<vscale x 16 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv16i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i32> %v, i32 2
@@ -570,8 +640,10 @@ define i32 @extractelt_nxv16i32_imm(<vscale x 16 x i32> %v) {
 define i32 @extractelt_nxv16i32_idx(<vscale x 16 x i32> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv16i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i32> %v, i32 %idx
@@ -581,9 +653,11 @@ define i32 @extractelt_nxv16i32_idx(<vscale x 16 x i32> %v, i32 %idx) {
 define i64 @extractelt_nxv1i64_0(<vscale x 1 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv1i64_0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi a0, zero, 32
+; CHECK-NEXT:    addi a0, zero, 1
-; CHECK-NEXT:    vsetvli a1, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v8, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
@@ -594,11 +668,15 @@ define i64 @extractelt_nxv1i64_0(<vscale x 1 x i64> %v) {
 define i64 @extractelt_nxv1i64_imm(<vscale x 1 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv1i64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a0, a1, e64,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i64> %v, i32 2
@@ -608,11 +686,15 @@ define i64 @extractelt_nxv1i64_imm(<vscale x 1 x i64> %v) {
 define i64 @extractelt_nxv1i64_idx(<vscale x 1 x i64> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv1i64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a2, a1, e64,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i64> %v, i32 %idx
@@ -622,9 +704,11 @@ define i64 @extractelt_nxv1i64_idx(<vscale x 1 x i64> %v, i32 %idx) {
 define i64 @extractelt_nxv2i64_0(<vscale x 2 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv2i64_0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi a0, zero, 32
+; CHECK-NEXT:    addi a0, zero, 1
-; CHECK-NEXT:    vsetvli a1, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 32
-; CHECK-NEXT:    vsrl.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
+; CHECK-NEXT:    vsrl.vx v26, v8, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v26
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
@@ -635,11 +719,15 @@ define i64 @extractelt_nxv2i64_0(<vscale x 2 x i64> %v) {
 define i64 @extractelt_nxv2i64_imm(<vscale x 2 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv2i64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a0, a1, e64,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v26, v26, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
+; CHECK-NEXT:    vsrl.vx v26, v26, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i64> %v, i32 2
@@ -649,11 +737,15 @@ define i64 @extractelt_nxv2i64_imm(<vscale x 2 x i64> %v) {
 define i64 @extractelt_nxv2i64_idx(<vscale x 2 x i64> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv2i64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a2, a1, e64,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v26, v26, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
+; CHECK-NEXT:    vsrl.vx v26, v26, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i64> %v, i32 %idx
@@ -663,9 +755,11 @@ define i64 @extractelt_nxv2i64_idx(<vscale x 2 x i64> %v, i32 %idx) {
 define i64 @extractelt_nxv4i64_0(<vscale x 4 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv4i64_0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi a0, zero, 32
+; CHECK-NEXT:    addi a0, zero, 1
-; CHECK-NEXT:    vsetvli a1, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 32
-; CHECK-NEXT:    vsrl.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
+; CHECK-NEXT:    vsrl.vx v28, v8, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v28
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
@@ -676,11 +770,15 @@ define i64 @extractelt_nxv4i64_0(<vscale x 4 x i64> %v) {
 define i64 @extractelt_nxv4i64_imm(<vscale x 4 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv4i64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a0, a1, e64,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v28, v28, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
+; CHECK-NEXT:    vsrl.vx v28, v28, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i64> %v, i32 2
@@ -690,11 +788,15 @@ define i64 @extractelt_nxv4i64_imm(<vscale x 4 x i64> %v) {
 define i64 @extractelt_nxv4i64_idx(<vscale x 4 x i64> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv4i64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a2, a1, e64,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v28, v28, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
+; CHECK-NEXT:    vsrl.vx v28, v28, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i64> %v, i32 %idx
@@ -704,9 +806,11 @@ define i64 @extractelt_nxv4i64_idx(<vscale x 4 x i64> %v, i32 %idx) {
 define i64 @extractelt_nxv8i64_0(<vscale x 8 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv8i64_0:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi a0, zero, 32
+; CHECK-NEXT:    addi a0, zero, 1
-; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 32
-; CHECK-NEXT:    vsrl.vx v16, v8, a0
+; CHECK-NEXT:    vsetvli a0, a0, e64,m8,ta,mu
+; CHECK-NEXT:    vsrl.vx v16, v8, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v16
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
@@ -717,11 +821,15 @@ define i64 @extractelt_nxv8i64_0(<vscale x 8 x i64> %v) {
 define i64 @extractelt_nxv8i64_imm(<vscale x 8 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv8i64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a0, a1, e64,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v8, v8, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vsrl.vx v8, v8, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i64> %v, i32 2
@@ -731,11 +839,15 @@ define i64 @extractelt_nxv8i64_imm(<vscale x 8 x i64> %v) {
 define i64 @extractelt_nxv8i64_idx(<vscale x 8 x i64> %v, i32 %idx) {
 ; CHECK-LABEL: extractelt_nxv8i64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a2, a1, e64,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v8, v8, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m8,ta,mu
+; CHECK-NEXT:    vsrl.vx v8, v8, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i64> %v, i32 %idx

llvm/test/CodeGen/RISCV/rvv/extractelt-int-rv64.ll

@@ -15,8 +15,10 @@ define signext i8 @extractelt_nxv1i8_0(<vscale x 1 x i8> %v) {
 define signext i8 @extractelt_nxv1i8_imm(<vscale x 1 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv1i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,mf8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i8> %v, i32 2
@@ -26,8 +28,10 @@ define signext i8 @extractelt_nxv1i8_imm(<vscale x 1 x i8> %v) {
 define signext i8 @extractelt_nxv1i8_idx(<vscale x 1 x i8> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv1i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,mf8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i8> %v, i32 %idx
@@ -47,8 +51,10 @@ define signext i8 @extractelt_nxv2i8_0(<vscale x 2 x i8> %v) {
 define signext i8 @extractelt_nxv2i8_imm(<vscale x 2 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv2i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,mf4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i8> %v, i32 2
@@ -58,8 +64,10 @@ define signext i8 @extractelt_nxv2i8_imm(<vscale x 2 x i8> %v) {
 define signext i8 @extractelt_nxv2i8_idx(<vscale x 2 x i8> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv2i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,mf4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i8> %v, i32 %idx
@@ -79,8 +87,10 @@ define signext i8 @extractelt_nxv4i8_0(<vscale x 4 x i8> %v) {
 define signext i8 @extractelt_nxv4i8_imm(<vscale x 4 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv4i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i8> %v, i32 2
@@ -90,8 +100,10 @@ define signext i8 @extractelt_nxv4i8_imm(<vscale x 4 x i8> %v) {
 define signext i8 @extractelt_nxv4i8_idx(<vscale x 4 x i8> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv4i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i8> %v, i32 %idx
@@ -111,8 +123,10 @@ define signext i8 @extractelt_nxv8i8_0(<vscale x 8 x i8> %v) {
 define signext i8 @extractelt_nxv8i8_imm(<vscale x 8 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv8i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i8> %v, i32 2
@@ -122,8 +136,10 @@ define signext i8 @extractelt_nxv8i8_imm(<vscale x 8 x i8> %v) {
 define signext i8 @extractelt_nxv8i8_idx(<vscale x 8 x i8> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv8i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i8> %v, i32 %idx
@@ -143,8 +159,10 @@ define signext i8 @extractelt_nxv16i8_0(<vscale x 16 x i8> %v) {
 define signext i8 @extractelt_nxv16i8_imm(<vscale x 16 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv16i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i8> %v, i32 2
@@ -154,8 +172,10 @@ define signext i8 @extractelt_nxv16i8_imm(<vscale x 16 x i8> %v) {
 define signext i8 @extractelt_nxv16i8_idx(<vscale x 16 x i8> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv16i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i8> %v, i32 %idx
@@ -175,8 +195,10 @@ define signext i8 @extractelt_nxv32i8_0(<vscale x 32 x i8> %v) {
 define signext i8 @extractelt_nxv32i8_imm(<vscale x 32 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv32i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x i8> %v, i32 2
@@ -186,8 +208,10 @@ define signext i8 @extractelt_nxv32i8_imm(<vscale x 32 x i8> %v) {
 define signext i8 @extractelt_nxv32i8_idx(<vscale x 32 x i8> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv32i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x i8> %v, i32 %idx
@@ -207,8 +231,10 @@ define signext i8 @extractelt_nxv64i8_0(<vscale x 64 x i8> %v) {
 define signext i8 @extractelt_nxv64i8_imm(<vscale x 64 x i8> %v) {
 ; CHECK-LABEL: extractelt_nxv64i8_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e8,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e8,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e8,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 64 x i8> %v, i32 2
@@ -218,8 +244,10 @@ define signext i8 @extractelt_nxv64i8_imm(<vscale x 64 x i8> %v) {
 define signext i8 @extractelt_nxv64i8_idx(<vscale x 64 x i8> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv64i8_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e8,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e8,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 64 x i8> %v, i32 %idx
@@ -239,8 +267,10 @@ define signext i16 @extractelt_nxv1i16_0(<vscale x 1 x i16> %v) {
 define signext i16 @extractelt_nxv1i16_imm(<vscale x 1 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv1i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,mf4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i16> %v, i32 2
@@ -250,8 +280,10 @@ define signext i16 @extractelt_nxv1i16_imm(<vscale x 1 x i16> %v) {
 define signext i16 @extractelt_nxv1i16_idx(<vscale x 1 x i16> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv1i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,mf4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i16> %v, i32 %idx
@@ -271,8 +303,10 @@ define signext i16 @extractelt_nxv2i16_0(<vscale x 2 x i16> %v) {
 define signext i16 @extractelt_nxv2i16_imm(<vscale x 2 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv2i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i16> %v, i32 2
@@ -282,8 +316,10 @@ define signext i16 @extractelt_nxv2i16_imm(<vscale x 2 x i16> %v) {
 define signext i16 @extractelt_nxv2i16_idx(<vscale x 2 x i16> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv2i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i16> %v, i32 %idx
@@ -303,8 +339,10 @@ define signext i16 @extractelt_nxv4i16_0(<vscale x 4 x i16> %v) {
 define signext i16 @extractelt_nxv4i16_imm(<vscale x 4 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv4i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i16> %v, i32 2
@@ -314,8 +352,10 @@ define signext i16 @extractelt_nxv4i16_imm(<vscale x 4 x i16> %v) {
 define signext i16 @extractelt_nxv4i16_idx(<vscale x 4 x i16> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv4i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i16> %v, i32 %idx
@@ -335,8 +375,10 @@ define signext i16 @extractelt_nxv8i16_0(<vscale x 8 x i16> %v) {
 define signext i16 @extractelt_nxv8i16_imm(<vscale x 8 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv8i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i16> %v, i32 2
@@ -346,8 +388,10 @@ define signext i16 @extractelt_nxv8i16_imm(<vscale x 8 x i16> %v) {
 define signext i16 @extractelt_nxv8i16_idx(<vscale x 8 x i16> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv8i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i16> %v, i32 %idx
@@ -367,8 +411,10 @@ define signext i16 @extractelt_nxv16i16_0(<vscale x 16 x i16> %v) {
 define signext i16 @extractelt_nxv16i16_imm(<vscale x 16 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv16i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i16> %v, i32 2
@@ -378,8 +424,10 @@ define signext i16 @extractelt_nxv16i16_imm(<vscale x 16 x i16> %v) {
 define signext i16 @extractelt_nxv16i16_idx(<vscale x 16 x i16> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv16i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i16> %v, i32 %idx
@@ -399,8 +447,10 @@ define signext i16 @extractelt_nxv32i16_0(<vscale x 32 x i16> %v) {
 define signext i16 @extractelt_nxv32i16_imm(<vscale x 32 x i16> %v) {
 ; CHECK-LABEL: extractelt_nxv32i16_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e16,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e16,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e16,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x i16> %v, i32 2
@@ -410,8 +460,10 @@ define signext i16 @extractelt_nxv32i16_imm(<vscale x 32 x i16> %v) {
 define signext i16 @extractelt_nxv32i16_idx(<vscale x 32 x i16> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv32i16_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e16,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e16,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e16,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 32 x i16> %v, i32 %idx
@@ -431,8 +483,10 @@ define signext i32 @extractelt_nxv1i32_0(<vscale x 1 x i32> %v) {
 define signext i32 @extractelt_nxv1i32_imm(<vscale x 1 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv1i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,mf2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i32> %v, i32 2
@@ -442,8 +496,10 @@ define signext i32 @extractelt_nxv1i32_imm(<vscale x 1 x i32> %v) {
 define signext i32 @extractelt_nxv1i32_idx(<vscale x 1 x i32> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv1i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,mf2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,mf2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,mf2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i32> %v, i32 %idx
@@ -463,8 +519,10 @@ define signext i32 @extractelt_nxv2i32_0(<vscale x 2 x i32> %v) {
 define signext i32 @extractelt_nxv2i32_imm(<vscale x 2 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv2i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i32> %v, i32 2
@@ -474,8 +532,10 @@ define signext i32 @extractelt_nxv2i32_imm(<vscale x 2 x i32> %v) {
 define signext i32 @extractelt_nxv2i32_idx(<vscale x 2 x i32> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv2i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i32> %v, i32 %idx
@@ -495,8 +555,10 @@ define signext i32 @extractelt_nxv4i32_0(<vscale x 4 x i32> %v) {
 define signext i32 @extractelt_nxv4i32_imm(<vscale x 4 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv4i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i32> %v, i32 2
@@ -506,8 +568,10 @@ define signext i32 @extractelt_nxv4i32_imm(<vscale x 4 x i32> %v) {
 define signext i32 @extractelt_nxv4i32_idx(<vscale x 4 x i32> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv4i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i32> %v, i32 %idx
@@ -527,8 +591,10 @@ define signext i32 @extractelt_nxv8i32_0(<vscale x 8 x i32> %v) {
 define signext i32 @extractelt_nxv8i32_imm(<vscale x 8 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv8i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i32> %v, i32 2
@@ -538,8 +604,10 @@ define signext i32 @extractelt_nxv8i32_imm(<vscale x 8 x i32> %v) {
 define signext i32 @extractelt_nxv8i32_idx(<vscale x 8 x i32> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv8i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i32> %v, i32 %idx
@@ -559,8 +627,10 @@ define signext i32 @extractelt_nxv16i32_0(<vscale x 16 x i32> %v) {
 define signext i32 @extractelt_nxv16i32_imm(<vscale x 16 x i32> %v) {
 ; CHECK-LABEL: extractelt_nxv16i32_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e32,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e32,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i32> %v, i32 2
@@ -570,8 +640,10 @@ define signext i32 @extractelt_nxv16i32_imm(<vscale x 16 x i32> %v) {
 define signext i32 @extractelt_nxv16i32_idx(<vscale x 16 x i32> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv16i32_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e32,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e32,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 16 x i32> %v, i32 %idx
@@ -591,8 +663,10 @@ define i64 @extractelt_nxv1i64_0(<vscale x 1 x i64> %v) {
 define i64 @extractelt_nxv1i64_imm(<vscale x 1 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv1i64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v25, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i64> %v, i32 2
@@ -602,8 +676,10 @@ define i64 @extractelt_nxv1i64_imm(<vscale x 1 x i64> %v) {
 define i64 @extractelt_nxv1i64_idx(<vscale x 1 x i64> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv1i64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v25, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 1 x i64> %v, i32 %idx
@@ -623,8 +699,10 @@ define i64 @extractelt_nxv2i64_0(<vscale x 2 x i64> %v) {
 define i64 @extractelt_nxv2i64_imm(<vscale x 2 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv2i64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v26, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i64> %v, i32 2
@@ -634,8 +712,10 @@ define i64 @extractelt_nxv2i64_imm(<vscale x 2 x i64> %v) {
 define i64 @extractelt_nxv2i64_idx(<vscale x 2 x i64> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv2i64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m2,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v26, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v26
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 2 x i64> %v, i32 %idx
@@ -655,8 +735,10 @@ define i64 @extractelt_nxv4i64_0(<vscale x 4 x i64> %v) {
 define i64 @extractelt_nxv4i64_imm(<vscale x 4 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv4i64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v28, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i64> %v, i32 2
@@ -666,8 +748,10 @@ define i64 @extractelt_nxv4i64_imm(<vscale x 4 x i64> %v) {
 define i64 @extractelt_nxv4i64_idx(<vscale x 4 x i64> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv4i64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m4,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m4,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v28, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m4,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v28
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 4 x i64> %v, i32 %idx
@@ -687,8 +771,10 @@ define i64 @extractelt_nxv8i64_0(<vscale x 8 x i64> %v) {
 define i64 @extractelt_nxv8i64_imm(<vscale x 8 x i64> %v) {
 ; CHECK-LABEL: extractelt_nxv8i64_imm:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a0, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a0, zero, 1
+; CHECK-NEXT:    vsetvli a0, a0, e64,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vi v8, v8, 2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i64> %v, i32 2
@@ -698,8 +784,10 @@ define i64 @extractelt_nxv8i64_imm(<vscale x 8 x i64> %v) {
 define i64 @extractelt_nxv8i64_idx(<vscale x 8 x i64> %v, i32 signext %idx) {
 ; CHECK-LABEL: extractelt_nxv8i64_idx:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vsetvli a1, zero, e64,m8,ta,mu
+; CHECK-NEXT:    addi a1, zero, 1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m8,ta,mu
 ; CHECK-NEXT:    vslidedown.vx v8, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e64,m8,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v8
 ; CHECK-NEXT:    ret
   %r = extractelement <vscale x 8 x i64> %v, i32 %idx

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-extract.ll

@@ -2,45 +2,237 @@
 ; RUN: llc -mtriple=riscv32 -target-abi=ilp32d -mattr=+experimental-v,+experimental-zfh,+f,+d -verify-machineinstrs -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=RV32
 ; RUN: llc -mtriple=riscv64 -target-abi=lp64d -mattr=+experimental-v,+experimental-zfh,+f,+d -verify-machineinstrs -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=RV64
 
-; FIXME: This codegen needs to be improved. These tests previously asserted in
+define i8 @extractelt_v16i8(<16 x i8>* %x) nounwind {
-; ReplaceNodeResults on RV32.
+; RV32-LABEL: extractelt_v16i8:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi a1, zero, 16
+; RV32-NEXT:    vsetvli a1, a1, e8,m1,ta,mu
+; RV32-NEXT:    vle8.v v25, (a0)
+; RV32-NEXT:    addi a0, zero, 1
+; RV32-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; RV32-NEXT:    vslidedown.vi v25, v25, 7
+; RV32-NEXT:    vsetvli zero, zero, e8,m1,ta,mu
+; RV32-NEXT:    vmv.x.s a0, v25
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: extractelt_v16i8:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi a1, zero, 16
+; RV64-NEXT:    vsetvli a1, a1, e8,m1,ta,mu
+; RV64-NEXT:    vle8.v v25, (a0)
+; RV64-NEXT:    addi a0, zero, 1
+; RV64-NEXT:    vsetvli a0, a0, e8,m1,ta,mu
+; RV64-NEXT:    vslidedown.vi v25, v25, 7
+; RV64-NEXT:    vsetvli zero, zero, e8,m1,ta,mu
+; RV64-NEXT:    vmv.x.s a0, v25
+; RV64-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = extractelement <16 x i8> %a, i32 7
+  ret i8 %b
+}
+
+define i16 @extractelt_v8i16(<8 x i16>* %x) nounwind {
+; RV32-LABEL: extractelt_v8i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi a1, zero, 8
+; RV32-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; RV32-NEXT:    vle16.v v25, (a0)
+; RV32-NEXT:    addi a0, zero, 1
+; RV32-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; RV32-NEXT:    vslidedown.vi v25, v25, 7
+; RV32-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
+; RV32-NEXT:    vmv.x.s a0, v25
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: extractelt_v8i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi a1, zero, 8
+; RV64-NEXT:    vsetvli a1, a1, e16,m1,ta,mu
+; RV64-NEXT:    vle16.v v25, (a0)
+; RV64-NEXT:    addi a0, zero, 1
+; RV64-NEXT:    vsetvli a0, a0, e16,m1,ta,mu
+; RV64-NEXT:    vslidedown.vi v25, v25, 7
+; RV64-NEXT:    vsetvli zero, zero, e16,m1,ta,mu
+; RV64-NEXT:    vmv.x.s a0, v25
+; RV64-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = extractelement <8 x i16> %a, i32 7
+  ret i16 %b
+}
+
+define i32 @extractelt_v4i32(<4 x i32>* %x) nounwind {
+; RV32-LABEL: extractelt_v4i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi a1, zero, 4
+; RV32-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; RV32-NEXT:    vle32.v v25, (a0)
+; RV32-NEXT:    addi a0, zero, 1
+; RV32-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; RV32-NEXT:    vslidedown.vi v25, v25, 2
+; RV32-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
+; RV32-NEXT:    vmv.x.s a0, v25
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: extractelt_v4i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi a1, zero, 4
+; RV64-NEXT:    vsetvli a1, a1, e32,m1,ta,mu
+; RV64-NEXT:    vle32.v v25, (a0)
+; RV64-NEXT:    addi a0, zero, 1
+; RV64-NEXT:    vsetvli a0, a0, e32,m1,ta,mu
+; RV64-NEXT:    vslidedown.vi v25, v25, 2
+; RV64-NEXT:    vsetvli zero, zero, e32,m1,ta,mu
+; RV64-NEXT:    vmv.x.s a0, v25
+; RV64-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = extractelement <4 x i32> %a, i32 2
+  ret i32 %b
+}
+
+define i64 @extractelt_v2i64(<2 x i64>* %x) nounwind {
+; RV32-LABEL: extractelt_v2i64:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi a1, zero, 2
+; RV32-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; RV32-NEXT:    vle64.v v25, (a0)
+; RV32-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
+; RV32-NEXT:    vmv.x.s a0, v25
+; RV32-NEXT:    addi a1, zero, 1
+; RV32-NEXT:    addi a2, zero, 32
+; RV32-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; RV32-NEXT:    vsrl.vx v25, v25, a2
+; RV32-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
+; RV32-NEXT:    vmv.x.s a1, v25
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: extractelt_v2i64:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi a1, zero, 2
+; RV64-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; RV64-NEXT:    vle64.v v25, (a0)
+; RV64-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
+; RV64-NEXT:    vmv.x.s a0, v25
+; RV64-NEXT:    ret
+  %a = load <2 x i64>, <2 x i64>* %x
+  %b = extractelement <2 x i64> %a, i32 0
+  ret i64 %b
+}
+
+define i8 @extractelt_v32i8(<32 x i8>* %x) nounwind {
+; RV32-LABEL: extractelt_v32i8:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi a1, zero, 32
+; RV32-NEXT:    vsetvli a1, a1, e8,m2,ta,mu
+; RV32-NEXT:    vle8.v v26, (a0)
+; RV32-NEXT:    addi a0, zero, 1
+; RV32-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; RV32-NEXT:    vslidedown.vi v26, v26, 7
+; RV32-NEXT:    vsetvli zero, zero, e8,m2,ta,mu
+; RV32-NEXT:    vmv.x.s a0, v26
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: extractelt_v32i8:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi a1, zero, 32
+; RV64-NEXT:    vsetvli a1, a1, e8,m2,ta,mu
+; RV64-NEXT:    vle8.v v26, (a0)
+; RV64-NEXT:    addi a0, zero, 1
+; RV64-NEXT:    vsetvli a0, a0, e8,m2,ta,mu
+; RV64-NEXT:    vslidedown.vi v26, v26, 7
+; RV64-NEXT:    vsetvli zero, zero, e8,m2,ta,mu
+; RV64-NEXT:    vmv.x.s a0, v26
+; RV64-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = extractelement <32 x i8> %a, i32 7
+  ret i8 %b
+}
+
+define i16 @extractelt_v16i16(<16 x i16>* %x) nounwind {
+; RV32-LABEL: extractelt_v16i16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi a1, zero, 16
+; RV32-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; RV32-NEXT:    vle16.v v26, (a0)
+; RV32-NEXT:    addi a0, zero, 1
+; RV32-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; RV32-NEXT:    vslidedown.vi v26, v26, 7
+; RV32-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
+; RV32-NEXT:    vmv.x.s a0, v26
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: extractelt_v16i16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi a1, zero, 16
+; RV64-NEXT:    vsetvli a1, a1, e16,m2,ta,mu
+; RV64-NEXT:    vle16.v v26, (a0)
+; RV64-NEXT:    addi a0, zero, 1
+; RV64-NEXT:    vsetvli a0, a0, e16,m2,ta,mu
+; RV64-NEXT:    vslidedown.vi v26, v26, 7
+; RV64-NEXT:    vsetvli zero, zero, e16,m2,ta,mu
+; RV64-NEXT:    vmv.x.s a0, v26
+; RV64-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = extractelement <16 x i16> %a, i32 7
+  ret i16 %b
+}
+
+define i32 @extractelt_v8i32(<8 x i32>* %x) nounwind {
+; RV32-LABEL: extractelt_v8i32:
+; RV32:       # %bb.0:
+; RV32-NEXT:    addi a1, zero, 8
+; RV32-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; RV32-NEXT:    vle32.v v26, (a0)
+; RV32-NEXT:    addi a0, zero, 1
+; RV32-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; RV32-NEXT:    vslidedown.vi v26, v26, 6
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
+; RV32-NEXT:    vmv.x.s a0, v26
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: extractelt_v8i32:
+; RV64:       # %bb.0:
+; RV64-NEXT:    addi a1, zero, 8
+; RV64-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; RV64-NEXT:    vle32.v v26, (a0)
+; RV64-NEXT:    addi a0, zero, 1
+; RV64-NEXT:    vsetvli a0, a0, e32,m2,ta,mu
+; RV64-NEXT:    vslidedown.vi v26, v26, 6
+; RV64-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
+; RV64-NEXT:    vmv.x.s a0, v26
+; RV64-NEXT:    ret
+  %a = load <8 x i32>, <8 x i32>* %x
+  %b = extractelement <8 x i32> %a, i32 6
+  ret i32 %b
+}
 
 define i64 @extractelt_v4i64(<4 x i64>* %x) nounwind {
 ; RV32-LABEL: extractelt_v4i64:
 ; RV32:       # %bb.0:
-; RV32-NEXT:    addi sp, sp, -64
+; RV32-NEXT:    addi a1, zero, 4
-; RV32-NEXT:    sw ra, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
-; RV32-NEXT:    sw s0, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT:    vle64.v v26, (a0)
-; RV32-NEXT:    addi s0, sp, 64
+; RV32-NEXT:    addi a1, zero, 1
-; RV32-NEXT:    andi sp, sp, -32
+; RV32-NEXT:    vsetvli a0, a1, e64,m2,ta,mu
-; RV32-NEXT:    addi a1, zero, 8
+; RV32-NEXT:    vslidedown.vi v26, v26, 3
-; RV32-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; RV32-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
-; RV32-NEXT:    vle32.v v26, (a0)
+; RV32-NEXT:    vmv.x.s a0, v26
-; RV32-NEXT:    vse32.v v26, (sp)
+; RV32-NEXT:    addi a2, zero, 32
-; RV32-NEXT:    lw a0, 24(sp)
+; RV32-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
-; RV32-NEXT:    lw a1, 28(sp)
+; RV32-NEXT:    vsrl.vx v26, v26, a2
-; RV32-NEXT:    addi sp, s0, -64
+; RV32-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
-; RV32-NEXT:    lw s0, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT:    vmv.x.s a1, v26
-; RV32-NEXT:    lw ra, 60(sp) # 4-byte Folded Reload
-; RV32-NEXT:    addi sp, sp, 64
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: extractelt_v4i64:
 ; RV64:       # %bb.0:
-; RV64-NEXT:    addi sp, sp, -64
-; RV64-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
-; RV64-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
-; RV64-NEXT:    addi s0, sp, 64
-; RV64-NEXT:    andi sp, sp, -32
 ; RV64-NEXT:    addi a1, zero, 4
 ; RV64-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
 ; RV64-NEXT:    vle64.v v26, (a0)
-; RV64-NEXT:    vse64.v v26, (sp)
+; RV64-NEXT:    addi a0, zero, 1
-; RV64-NEXT:    ld a0, 24(sp)
+; RV64-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
-; RV64-NEXT:    addi sp, s0, -64
+; RV64-NEXT:    vslidedown.vi v26, v26, 3
-; RV64-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
-; RV64-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT:    vmv.x.s a0, v26
-; RV64-NEXT:    addi sp, sp, 64
 ; RV64-NEXT:    ret
   %a = load <4 x i64>, <4 x i64>* %x
   %b = extractelement <4 x i64> %a, i32 3
@@ -49,42 +241,35 @@ define i64 @extractelt_v4i64(<4 x i64>* %x) nounwind {
 
 ; This uses a non-power of 2 type so that it isn't an MVT to catch an
 ; incorrect use of getSimpleValueType().
+; NOTE: Type legalization is bitcasting to vXi32 and doing 2 independent
+; slidedowns and extracts.
 define i64 @extractelt_v3i64(<3 x i64>* %x) nounwind {
 ; RV32-LABEL: extractelt_v3i64:
 ; RV32:       # %bb.0:
-; RV32-NEXT:    addi sp, sp, -64
-; RV32-NEXT:    sw ra, 60(sp) # 4-byte Folded Spill
-; RV32-NEXT:    sw s0, 56(sp) # 4-byte Folded Spill
-; RV32-NEXT:    addi s0, sp, 64
-; RV32-NEXT:    andi sp, sp, -32
 ; RV32-NEXT:    addi a1, zero, 8
 ; RV32-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
 ; RV32-NEXT:    vle32.v v26, (a0)
-; RV32-NEXT:    vse32.v v26, (sp)
+; RV32-NEXT:    addi a1, zero, 1
-; RV32-NEXT:    lw a0, 16(sp)
+; RV32-NEXT:    vsetvli a0, a1, e32,m2,ta,mu
-; RV32-NEXT:    lw a1, 20(sp)
+; RV32-NEXT:    vslidedown.vi v28, v26, 4
-; RV32-NEXT:    addi sp, s0, -64
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
-; RV32-NEXT:    lw s0, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT:    vmv.x.s a0, v28
-; RV32-NEXT:    lw ra, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
-; RV32-NEXT:    addi sp, sp, 64
+; RV32-NEXT:    vslidedown.vi v26, v26, 5
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
+; RV32-NEXT:    vmv.x.s a1, v26
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: extractelt_v3i64:
 ; RV64:       # %bb.0:
-; RV64-NEXT:    addi sp, sp, -64
-; RV64-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
-; RV64-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
-; RV64-NEXT:    addi s0, sp, 64
-; RV64-NEXT:    andi sp, sp, -32
 ; RV64-NEXT:    addi a1, zero, 4
 ; RV64-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
 ; RV64-NEXT:    vle64.v v26, (a0)
-; RV64-NEXT:    vse64.v v26, (sp)
+; RV64-NEXT:    addi a0, zero, 1
-; RV64-NEXT:    ld a0, 16(sp)
+; RV64-NEXT:    vsetvli a0, a0, e64,m2,ta,mu
-; RV64-NEXT:    addi sp, s0, -64
+; RV64-NEXT:    vslidedown.vi v26, v26, 2
-; RV64-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
-; RV64-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT:    vmv.x.s a0, v26
-; RV64-NEXT:    addi sp, sp, 64
 ; RV64-NEXT:    ret
   %a = load <3 x i64>, <3 x i64>* %x
   %b = extractelement <3 x i64> %a, i32 2

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert.ll

@@ -8,95 +8,112 @@
 define void @insertelt_v4i64(<4 x i64>* %x, i64 %y) {
 ; RV32-LABEL: insertelt_v4i64:
 ; RV32:       # %bb.0:
-; RV32-NEXT:    addi sp, sp, -224
+; RV32-NEXT:    addi sp, sp, -128
-; RV32-NEXT:    .cfi_def_cfa_offset 224
+; RV32-NEXT:    .cfi_def_cfa_offset 128
-; RV32-NEXT:    sw ra, 220(sp) # 4-byte Folded Spill
+; RV32-NEXT:    sw ra, 124(sp) # 4-byte Folded Spill
-; RV32-NEXT:    sw s0, 216(sp) # 4-byte Folded Spill
+; RV32-NEXT:    sw s0, 120(sp) # 4-byte Folded Spill
 ; RV32-NEXT:    .cfi_offset ra, -4
 ; RV32-NEXT:    .cfi_offset s0, -8
-; RV32-NEXT:    addi s0, sp, 224
+; RV32-NEXT:    addi s0, sp, 128
 ; RV32-NEXT:    .cfi_def_cfa s0, 0
 ; RV32-NEXT:    andi sp, sp, -32
-; RV32-NEXT:    addi a3, zero, 8
+; RV32-NEXT:    sw a2, 32(sp)
-; RV32-NEXT:    vsetvli a4, a3, e32,m2,ta,mu
+; RV32-NEXT:    sw a1, 64(sp)
+; RV32-NEXT:    addi a1, zero, 8
+; RV32-NEXT:    vsetvli a2, a1, e32,m2,ta,mu
 ; RV32-NEXT:    vle32.v v26, (a0)
-; RV32-NEXT:    vse32.v v26, (sp)
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
-; RV32-NEXT:    addi a6, zero, 2
+; RV32-NEXT:    vmv.x.s a2, v26
-; RV32-NEXT:    addi a5, sp, 16
+; RV32-NEXT:    sw a2, 0(sp)
-; RV32-NEXT:    vsetvli a4, a6, e32,m1,ta,mu
+; RV32-NEXT:    vsetvli a2, a1, e32,m2,ta,mu
-; RV32-NEXT:    vle32.v v25, (a5)
+; RV32-NEXT:    addi a2, sp, 32
-; RV32-NEXT:    addi a4, sp, 112
+; RV32-NEXT:    vle32.v v28, (a2)
-; RV32-NEXT:    vse32.v v25, (a4)
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
-; RV32-NEXT:    addi a4, sp, 8
+; RV32-NEXT:    vmv.x.s a2, v28
-; RV32-NEXT:    vle32.v v25, (a4)
+; RV32-NEXT:    sw a2, 28(sp)
-; RV32-NEXT:    addi a4, sp, 104
+; RV32-NEXT:    vsetvli a2, a1, e32,m2,ta,mu
-; RV32-NEXT:    vse32.v v25, (a4)
-; RV32-NEXT:    sw a2, 128(sp)
-; RV32-NEXT:    vsetvli a2, a3, e32,m2,ta,mu
-; RV32-NEXT:    addi a2, sp, 128
-; RV32-NEXT:    vle32.v v26, (a2)
 ; RV32-NEXT:    addi a2, sp, 64
-; RV32-NEXT:    vse32.v v26, (a2)
+; RV32-NEXT:    vle32.v v28, (a2)
-; RV32-NEXT:    sw a1, 160(sp)
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
-; RV32-NEXT:    addi a1, sp, 160
+; RV32-NEXT:    vmv.x.s a2, v28
-; RV32-NEXT:    vle32.v v26, (a1)
+; RV32-NEXT:    sw a2, 24(sp)
-; RV32-NEXT:    addi a1, sp, 32
+; RV32-NEXT:    addi a2, zero, 1
-; RV32-NEXT:    vse32.v v26, (a1)
+; RV32-NEXT:    vsetvli a3, a2, e32,m2,ta,mu
-; RV32-NEXT:    vsetvli a1, a6, e32,m1,ta,mu
+; RV32-NEXT:    vslidedown.vi v28, v26, 5
-; RV32-NEXT:    vle32.v v25, (sp)
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
-; RV32-NEXT:    addi a1, sp, 96
+; RV32-NEXT:    vmv.x.s a3, v28
-; RV32-NEXT:    vse32.v v25, (a1)
+; RV32-NEXT:    sw a3, 20(sp)
-; RV32-NEXT:    lw a1, 64(sp)
+; RV32-NEXT:    vsetvli a3, a2, e32,m2,ta,mu
-; RV32-NEXT:    sw a1, 124(sp)
+; RV32-NEXT:    vslidedown.vi v28, v26, 4
-; RV32-NEXT:    lw a1, 32(sp)
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
-; RV32-NEXT:    sw a1, 120(sp)
+; RV32-NEXT:    vmv.x.s a3, v28
-; RV32-NEXT:    vsetvli a1, a3, e32,m2,ta,mu
+; RV32-NEXT:    sw a3, 16(sp)
-; RV32-NEXT:    addi a1, sp, 96
+; RV32-NEXT:    vsetvli a3, a2, e32,m2,ta,mu
-; RV32-NEXT:    vle32.v v26, (a1)
+; RV32-NEXT:    vslidedown.vi v28, v26, 3
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
+; RV32-NEXT:    vmv.x.s a3, v28
+; RV32-NEXT:    sw a3, 12(sp)
+; RV32-NEXT:    vsetvli a3, a2, e32,m2,ta,mu
+; RV32-NEXT:    vslidedown.vi v28, v26, 2
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
+; RV32-NEXT:    vmv.x.s a3, v28
+; RV32-NEXT:    sw a3, 8(sp)
+; RV32-NEXT:    vsetvli a2, a2, e32,m2,ta,mu
+; RV32-NEXT:    vslidedown.vi v26, v26, 1
+; RV32-NEXT:    vsetvli zero, zero, e32,m2,ta,mu
+; RV32-NEXT:    vmv.x.s a2, v26
+; RV32-NEXT:    sw a2, 4(sp)
+; RV32-NEXT:    vsetvli a1, a1, e32,m2,ta,mu
+; RV32-NEXT:    vle32.v v26, (sp)
 ; RV32-NEXT:    vse32.v v26, (a0)
-; RV32-NEXT:    addi sp, s0, -224
+; RV32-NEXT:    addi sp, s0, -128
-; RV32-NEXT:    lw s0, 216(sp) # 4-byte Folded Reload
+; RV32-NEXT:    lw s0, 120(sp) # 4-byte Folded Reload
-; RV32-NEXT:    lw ra, 220(sp) # 4-byte Folded Reload
+; RV32-NEXT:    lw ra, 124(sp) # 4-byte Folded Reload
-; RV32-NEXT:    addi sp, sp, 224
+; RV32-NEXT:    addi sp, sp, 128
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: insertelt_v4i64:
 ; RV64:       # %bb.0:
-; RV64-NEXT:    addi sp, sp, -160
+; RV64-NEXT:    addi sp, sp, -96
-; RV64-NEXT:    .cfi_def_cfa_offset 160
+; RV64-NEXT:    .cfi_def_cfa_offset 96
-; RV64-NEXT:    sd ra, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT:    sd ra, 88(sp) # 8-byte Folded Spill
-; RV64-NEXT:    sd s0, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT:    sd s0, 80(sp) # 8-byte Folded Spill
 ; RV64-NEXT:    .cfi_offset ra, -8
 ; RV64-NEXT:    .cfi_offset s0, -16
-; RV64-NEXT:    addi s0, sp, 160
+; RV64-NEXT:    addi s0, sp, 96
 ; RV64-NEXT:    .cfi_def_cfa s0, 0
 ; RV64-NEXT:    andi sp, sp, -32
 ; RV64-NEXT:    addi a2, zero, 4
 ; RV64-NEXT:    vsetvli a3, a2, e64,m2,ta,mu
 ; RV64-NEXT:    vle64.v v26, (a0)
-; RV64-NEXT:    vse64.v v26, (sp)
+; RV64-NEXT:    sd a1, 32(sp)
-; RV64-NEXT:    sd a1, 96(sp)
+; RV64-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
-; RV64-NEXT:    addi a1, sp, 96
+; RV64-NEXT:    vmv.x.s a1, v26
-; RV64-NEXT:    vle64.v v26, (a1)
+; RV64-NEXT:    sd a1, 0(sp)
-; RV64-NEXT:    addi a1, sp, 32
-; RV64-NEXT:    vse64.v v26, (a1)
-; RV64-NEXT:    addi a1, zero, 2
-; RV64-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
-; RV64-NEXT:    vle64.v v25, (sp)
-; RV64-NEXT:    addi a1, sp, 64
-; RV64-NEXT:    vse64.v v25, (a1)
-; RV64-NEXT:    ld a1, 16(sp)
-; RV64-NEXT:    sd a1, 80(sp)
-; RV64-NEXT:    ld a1, 32(sp)
-; RV64-NEXT:    sd a1, 88(sp)
 ; RV64-NEXT:    vsetvli a1, a2, e64,m2,ta,mu
-; RV64-NEXT:    addi a1, sp, 64
+; RV64-NEXT:    addi a1, sp, 32
-; RV64-NEXT:    vle64.v v26, (a1)
+; RV64-NEXT:    vle64.v v28, (a1)
+; RV64-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
+; RV64-NEXT:    vmv.x.s a1, v28
+; RV64-NEXT:    sd a1, 24(sp)
+; RV64-NEXT:    addi a1, zero, 1
+; RV64-NEXT:    vsetvli a3, a1, e64,m2,ta,mu
+; RV64-NEXT:    vslidedown.vi v28, v26, 2
+; RV64-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
+; RV64-NEXT:    vmv.x.s a3, v28
+; RV64-NEXT:    sd a3, 16(sp)
+; RV64-NEXT:    vsetvli a1, a1, e64,m2,ta,mu
+; RV64-NEXT:    vslidedown.vi v26, v26, 1
+; RV64-NEXT:    vsetvli zero, zero, e64,m2,ta,mu
+; RV64-NEXT:    vmv.x.s a1, v26
+; RV64-NEXT:    sd a1, 8(sp)
+; RV64-NEXT:    vsetvli a1, a2, e64,m2,ta,mu
+; RV64-NEXT:    vle64.v v26, (sp)
 ; RV64-NEXT:    vse64.v v26, (a0)
-; RV64-NEXT:    addi sp, s0, -160
+; RV64-NEXT:    addi sp, s0, -96
-; RV64-NEXT:    ld s0, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT:    ld s0, 80(sp) # 8-byte Folded Reload
-; RV64-NEXT:    ld ra, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT:    ld ra, 88(sp) # 8-byte Folded Reload
-; RV64-NEXT:    addi sp, sp, 160
+; RV64-NEXT:    addi sp, sp, 96
 ; RV64-NEXT:    ret
   %a = load <4 x i64>, <4 x i64>* %x
   %b = insertelement <4 x i64> %a, i64 %y, i32 3

llvm/test/CodeGen/RISCV/rvv/vreductions-int-rv32.ll

@@ -1154,8 +1154,11 @@ define i64 @vreduce_add_nxv1i64(<vscale x 1 x i64> %v) {
 ; CHECK-NEXT:    vmv.v.i v25, 0
 ; CHECK-NEXT:    vredsum.vs v25, v8, v25
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.add.nxv1i64(<vscale x 1 x i64> %v)
@@ -1171,8 +1174,11 @@ define i64 @vreduce_umax_nxv1i64(<vscale x 1 x i64> %v) {
 ; CHECK-NEXT:    vmv.v.i v25, 0
 ; CHECK-NEXT:    vredmaxu.vs v25, v8, v25
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> %v)
@@ -1195,7 +1201,10 @@ define i64 @vreduce_smax_nxv1i64(<vscale x 1 x i64> %v) {
 ; CHECK-NEXT:    vor.vv v25, v26, v25
 ; CHECK-NEXT:    vredmax.vs v25, v8, v25
 ; CHECK-NEXT:    vmv.x.s a0, v25
+; CHECK-NEXT:    addi a2, zero, 1
+; CHECK-NEXT:    vsetvli a2, a2, e64,m1,ta,mu
 ; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> %v)
@@ -1211,8 +1220,11 @@ define i64 @vreduce_umin_nxv1i64(<vscale x 1 x i64> %v) {
 ; CHECK-NEXT:    vmv.v.i v25, -1
 ; CHECK-NEXT:    vredminu.vs v25, v8, v25
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> %v)
@@ -1236,7 +1248,10 @@ define i64 @vreduce_smin_nxv1i64(<vscale x 1 x i64> %v) {
 ; CHECK-NEXT:    vor.vv v25, v25, v26
 ; CHECK-NEXT:    vredmin.vs v25, v8, v25
 ; CHECK-NEXT:    vmv.x.s a0, v25
+; CHECK-NEXT:    addi a2, zero, 1
+; CHECK-NEXT:    vsetvli a2, a2, e64,m1,ta,mu
 ; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> %v)
@@ -1252,8 +1267,11 @@ define i64 @vreduce_and_nxv1i64(<vscale x 1 x i64> %v) {
 ; CHECK-NEXT:    vmv.v.i v25, -1
 ; CHECK-NEXT:    vredand.vs v25, v8, v25
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.and.nxv1i64(<vscale x 1 x i64> %v)
@@ -1269,8 +1287,11 @@ define i64 @vreduce_or_nxv1i64(<vscale x 1 x i64> %v) {
 ; CHECK-NEXT:    vmv.v.i v25, 0
 ; CHECK-NEXT:    vredor.vs v25, v8, v25
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.or.nxv1i64(<vscale x 1 x i64> %v)
@@ -1286,8 +1307,11 @@ define i64 @vreduce_xor_nxv1i64(<vscale x 1 x i64> %v) {
 ; CHECK-NEXT:    vmv.v.i v25, 0
 ; CHECK-NEXT:    vredxor.vs v25, v8, v25
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.xor.nxv1i64(<vscale x 1 x i64> %v)
@@ -1305,9 +1329,11 @@ define i64 @vreduce_add_nxv2i64(<vscale x 2 x i64> %v) {
 ; CHECK-NEXT:    vredsum.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64> %v)
@@ -1325,9 +1351,11 @@ define i64 @vreduce_umax_nxv2i64(<vscale x 2 x i64> %v) {
 ; CHECK-NEXT:    vredmaxu.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.umax.nxv2i64(<vscale x 2 x i64> %v)
@@ -1352,8 +1380,10 @@ define i64 @vreduce_smax_nxv2i64(<vscale x 2 x i64> %v) {
 ; CHECK-NEXT:    vredmax.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 1
+; CHECK-NEXT:    vsetvli a2, a2, e64,m1,ta,mu
 ; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.smax.nxv2i64(<vscale x 2 x i64> %v)
@@ -1371,9 +1401,11 @@ define i64 @vreduce_umin_nxv2i64(<vscale x 2 x i64> %v) {
 ; CHECK-NEXT:    vredminu.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.umin.nxv2i64(<vscale x 2 x i64> %v)
@@ -1399,8 +1431,10 @@ define i64 @vreduce_smin_nxv2i64(<vscale x 2 x i64> %v) {
 ; CHECK-NEXT:    vredmin.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 1
+; CHECK-NEXT:    vsetvli a2, a2, e64,m1,ta,mu
 ; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.smin.nxv2i64(<vscale x 2 x i64> %v)
@@ -1418,9 +1452,11 @@ define i64 @vreduce_and_nxv2i64(<vscale x 2 x i64> %v) {
 ; CHECK-NEXT:    vredand.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.and.nxv2i64(<vscale x 2 x i64> %v)
@@ -1438,9 +1474,11 @@ define i64 @vreduce_or_nxv2i64(<vscale x 2 x i64> %v) {
 ; CHECK-NEXT:    vredor.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.or.nxv2i64(<vscale x 2 x i64> %v)
@@ -1458,9 +1496,11 @@ define i64 @vreduce_xor_nxv2i64(<vscale x 2 x i64> %v) {
 ; CHECK-NEXT:    vredxor.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.xor.nxv2i64(<vscale x 2 x i64> %v)
@@ -1478,9 +1518,11 @@ define i64 @vreduce_add_nxv4i64(<vscale x 4 x i64> %v) {
 ; CHECK-NEXT:    vredsum.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v)
@@ -1498,9 +1540,11 @@ define i64 @vreduce_umax_nxv4i64(<vscale x 4 x i64> %v) {
 ; CHECK-NEXT:    vredmaxu.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v)
@@ -1525,8 +1569,10 @@ define i64 @vreduce_smax_nxv4i64(<vscale x 4 x i64> %v) {
 ; CHECK-NEXT:    vredmax.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 1
+; CHECK-NEXT:    vsetvli a2, a2, e64,m1,ta,mu
 ; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v)
@@ -1544,9 +1590,11 @@ define i64 @vreduce_umin_nxv4i64(<vscale x 4 x i64> %v) {
 ; CHECK-NEXT:    vredminu.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v)
@@ -1572,8 +1620,10 @@ define i64 @vreduce_smin_nxv4i64(<vscale x 4 x i64> %v) {
 ; CHECK-NEXT:    vredmin.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 1
+; CHECK-NEXT:    vsetvli a2, a2, e64,m1,ta,mu
 ; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v)
@@ -1591,9 +1641,11 @@ define i64 @vreduce_and_nxv4i64(<vscale x 4 x i64> %v) {
 ; CHECK-NEXT:    vredand.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v)
@@ -1611,9 +1663,11 @@ define i64 @vreduce_or_nxv4i64(<vscale x 4 x i64> %v) {
 ; CHECK-NEXT:    vredor.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v)
@@ -1631,9 +1685,11 @@ define i64 @vreduce_xor_nxv4i64(<vscale x 4 x i64> %v) {
 ; CHECK-NEXT:    vredxor.vs v25, v8, v25
 ; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a0, v25
-; CHECK-NEXT:    addi a1, zero, 32
+; CHECK-NEXT:    addi a1, zero, 1
-; CHECK-NEXT:    vsetvli a2, zero, e64,m1,ta,mu
+; CHECK-NEXT:    addi a2, zero, 32
-; CHECK-NEXT:    vsrl.vx v25, v25, a1
+; CHECK-NEXT:    vsetvli a1, a1, e64,m1,ta,mu
+; CHECK-NEXT:    vsrl.vx v25, v25, a2
+; CHECK-NEXT:    vsetvli zero, zero, e64,m1,ta,mu
 ; CHECK-NEXT:    vmv.x.s a1, v25
 ; CHECK-NEXT:    ret
   %red = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v)