diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 774088a4449b..83a417aa148c 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -19517,13 +19517,6 @@ SDValue DAGCombiner::visitBUILD_VECTOR(SDNode *N) {
     }
   }
 
-  // A splat of a single element is a SPLAT_VECTOR if supported on the target.
-  if (TLI.getOperationAction(ISD::SPLAT_VECTOR, VT) != TargetLowering::Expand)
-    if (SDValue V = cast<BuildVectorSDNode>(N)->getSplatValue()) {
-      assert(!V.isUndef() && "Splat of undef should have been handled earlier");
-      return DAG.getNode(ISD::SPLAT_VECTOR, SDLoc(N), VT, V);
-    }
-
   // Check if we can express BUILD VECTOR via subvector extract.
   if (!LegalTypes && (N->getNumOperands() > 1)) {
     SDValue Op0 = N->getOperand(0);
@@ -19565,6 +19558,14 @@ SDValue DAGCombiner::visitBUILD_VECTOR(SDNode *N) {
   if (SDValue V = reduceBuildVecToShuffle(N))
     return V;
 
+  // A splat of a single element is a SPLAT_VECTOR if supported on the target.
+  // Do this late as some of the above may replace the splat.
+  if (TLI.getOperationAction(ISD::SPLAT_VECTOR, VT) != TargetLowering::Expand)
+    if (SDValue V = cast<BuildVectorSDNode>(N)->getSplatValue()) {
+      assert(!V.isUndef() && "Splat of undef should have been handled earlier");
+      return DAG.getNode(ISD::SPLAT_VECTOR, SDLoc(N), VT, V);
+    }
+
   return SDValue();
 }
 
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index f0d875770376..571eae6cb757 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -636,6 +636,15 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
           continue;
         }
 
+        // Use SPLAT_VECTOR to prevent type legalization from destroying the
+        // splats when type legalizing i64 scalar on RV32.
+        // FIXME: Use SPLAT_VECTOR for all types? DAGCombine probably needs
+        // improvements first.
+        if (!Subtarget.is64Bit() && VT.getVectorElementType() == MVT::i64) {
+          setOperationAction(ISD::SPLAT_VECTOR, VT, Custom);
+          setOperationAction(ISD::SPLAT_VECTOR_PARTS, VT, Custom);
+        }
+
         setOperationAction(ISD::VECTOR_SHUFFLE, VT, Custom);
         setOperationAction(ISD::INSERT_VECTOR_ELT, VT, Custom);
 
@@ -1265,6 +1274,23 @@ bool RISCVTargetLowering::isShuffleMaskLegal(ArrayRef<int> M, EVT VT) const {
   return false;
 }
 
+static SDValue lowerSPLAT_VECTOR(SDValue Op, SelectionDAG &DAG,
+                                 const RISCVSubtarget &Subtarget) {
+  MVT VT = Op.getSimpleValueType();
+  assert(VT.isFixedLengthVector() && "Unexpected vector!");
+
+  MVT ContainerVT = getContainerForFixedLengthVector(DAG, VT, Subtarget);
+
+  SDLoc DL(Op);
+  SDValue Mask, VL;
+  std::tie(Mask, VL) = getDefaultVLOps(VT, ContainerVT, DL, DAG, Subtarget);
+
+  unsigned Opc =
+      VT.isFloatingPoint() ? RISCVISD::VFMV_V_F_VL : RISCVISD::VMV_V_X_VL;
+  SDValue Splat = DAG.getNode(Opc, DL, ContainerVT, Op.getOperand(0), VL);
+  return convertFromScalableVector(VT, Splat, DAG, Subtarget);
+}
+
 static SDValue lowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG,
                                  const RISCVSubtarget &Subtarget) {
   MVT VT = Op.getSimpleValueType();
@@ -1515,8 +1541,7 @@ static SDValue lowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG,
 // vector nxvXi64 VT.
 static SDValue splatPartsI64ThroughStack(const SDLoc &DL, MVT VT, SDValue Lo,
                                          SDValue Hi, SDValue VL,
-                                         SelectionDAG &DAG,
-                                         const RISCVSubtarget &Subtarget) {
+                                         SelectionDAG &DAG) {
   assert(VT.getVectorElementType() == MVT::i64 && VT.isScalableVector() &&
          Lo.getValueType() == MVT::i32 && Hi.getValueType() == MVT::i32 &&
          "Unexpected VTs!");
@@ -1540,29 +1565,41 @@ static SDValue splatPartsI64ThroughStack(const SDLoc &DL, MVT VT, SDValue Lo,
 
   Chain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Lo, Hi);
 
-  MVT XLenVT = Subtarget.getXLenVT();
   SDVTList VTs = DAG.getVTList({VT, MVT::Other});
-  SDValue IntID = DAG.getTargetConstant(Intrinsic::riscv_vlse, DL, XLenVT);
-  SDValue Ops[] = {Chain, IntID, StackSlot, DAG.getRegister(RISCV::X0, XLenVT),
-                   VL};
+  SDValue IntID = DAG.getTargetConstant(Intrinsic::riscv_vlse, DL, MVT::i64);
+  SDValue Ops[] = {Chain, IntID, StackSlot,
+                   DAG.getRegister(RISCV::X0, MVT::i64), VL};
 
   return DAG.getMemIntrinsicNode(ISD::INTRINSIC_W_CHAIN, DL, VTs, Ops, MVT::i64,
                                  MPI, Align(8), MachineMemOperand::MOLoad);
 }
 
+static SDValue splatPartsI64WithVL(const SDLoc &DL, MVT VT, SDValue Lo,
+                                   SDValue Hi, SDValue VL, SelectionDAG &DAG) {
+  if (isa<ConstantSDNode>(Lo) && isa<ConstantSDNode>(Hi)) {
+    int32_t LoC = cast<ConstantSDNode>(Lo)->getSExtValue();
+    int32_t HiC = cast<ConstantSDNode>(Hi)->getSExtValue();
+    // If Hi constant is all the same sign bit as Lo, lower this as a custom
+    // node in order to try and match RVV vector/scalar instructions.
+    if ((LoC >> 31) == HiC)
+      return DAG.getNode(RISCVISD::VMV_V_X_VL, DL, VT, Lo, VL);
+  }
+
+  // Fall back to a stack store and stride x0 vector load.
+  return splatPartsI64ThroughStack(DL, VT, Lo, Hi, VL, DAG);
+}
+
 // Called by type legalization to handle splat of i64 on RV32.
 // FIXME: We can optimize this when the type has sign or zero bits in one
 // of the halves.
 static SDValue splatSplitI64WithVL(const SDLoc &DL, MVT VT, SDValue Scalar,
-                                   SDValue VL, SelectionDAG &DAG,
-                                   const RISCVSubtarget &Subtarget) {
+                                   SDValue VL, SelectionDAG &DAG) {
+  assert(Scalar.getValueType() == MVT::i64 && "Unexpected VT!");
   SDValue Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, MVT::i32, Scalar,
                            DAG.getConstant(0, DL, MVT::i32));
   SDValue Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, MVT::i32, Scalar,
                            DAG.getConstant(1, DL, MVT::i32));
-
-  // Fall back to a stack store and stride x0 vector load.
-  return splatPartsI64ThroughStack(DL, VT, Lo, Hi, VL, DAG, Subtarget);
+  return splatPartsI64WithVL(DL, VT, Lo, Hi, VL, DAG);
 }
 
 // This function lowers a splat of a scalar operand Splat with the vector
@@ -1591,17 +1628,8 @@ static SDValue lowerScalarSplat(SDValue Scalar, SDValue VL, MVT VT, SDLoc DL,
   assert(XLenVT == MVT::i32 && Scalar.getValueType() == MVT::i64 &&
          "Unexpected scalar for splat lowering!");
 
-  // If this is a sign-extended 32-bit constant, we can truncate it and rely
-  // on the instruction to sign-extend since SEW>XLEN.
-  if (auto *CVal = dyn_cast<ConstantSDNode>(Scalar)) {
-    if (isInt<32>(CVal->getSExtValue()))
-      return DAG.getNode(RISCVISD::VMV_V_X_VL, DL, VT,
-                         DAG.getConstant(CVal->getSExtValue(), DL, MVT::i32),
-                         VL);
-  }
-
   // Otherwise use the more complicated splatting algorithm.
-  return splatSplitI64WithVL(DL, VT, Scalar, VL, DAG, Subtarget);
+  return splatSplitI64WithVL(DL, VT, Scalar, VL, DAG);
 }
 
 static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
@@ -2209,6 +2237,8 @@ SDValue RISCVTargetLowering::LowerOperation(SDValue Op,
     return lowerVECTOR_REVERSE(Op, DAG);
   case ISD::BUILD_VECTOR:
     return lowerBUILD_VECTOR(Op, DAG, Subtarget);
+  case ISD::SPLAT_VECTOR:
+    return lowerSPLAT_VECTOR(Op, DAG, Subtarget);
   case ISD::VECTOR_SHUFFLE:
     return lowerVECTOR_SHUFFLE(Op, DAG, Subtarget);
   case ISD::CONCAT_VECTORS: {
@@ -2781,6 +2811,17 @@ SDValue RISCVTargetLowering::lowerSPLAT_VECTOR_PARTS(SDValue Op,
   SDValue Lo = Op.getOperand(0);
   SDValue Hi = Op.getOperand(1);
 
+  if (VecVT.isFixedLengthVector()) {
+    MVT ContainerVT = getContainerForFixedLengthVector(VecVT);
+    SDLoc DL(Op);
+    SDValue Mask, VL;
+    std::tie(Mask, VL) =
+        getDefaultVLOps(VecVT, ContainerVT, DL, DAG, Subtarget);
+
+    SDValue Res = splatPartsI64WithVL(DL, ContainerVT, Lo, Hi, VL, DAG);
+    return convertFromScalableVector(VecVT, Res, DAG, Subtarget);
+  }
+
   if (isa<ConstantSDNode>(Lo) && isa<ConstantSDNode>(Hi)) {
     int32_t LoC = cast<ConstantSDNode>(Lo)->getSExtValue();
     int32_t HiC = cast<ConstantSDNode>(Hi)->getSExtValue();
@@ -2797,8 +2838,8 @@ SDValue RISCVTargetLowering::lowerSPLAT_VECTOR_PARTS(SDValue Op,
     return DAG.getNode(RISCVISD::SPLAT_VECTOR_I64, DL, VecVT, Lo);
 
   // Fall back to use a stack store and stride x0 vector load. Use X0 as VL.
-  return splatPartsI64ThroughStack(
-      DL, VecVT, Lo, Hi, DAG.getRegister(RISCV::X0, MVT::i64), DAG, Subtarget);
+  return splatPartsI64ThroughStack(DL, VecVT, Lo, Hi,
+                                   DAG.getRegister(RISCV::X0, MVT::i64), DAG);
 }
 
 // Custom-lower extensions from mask vectors by using a vselect either with 1
@@ -3136,7 +3177,7 @@ static SDValue lowerVectorIntrinsicSplats(SDValue Op, SelectionDAG &DAG,
   // VL should be the last operand.
   SDValue VL = Op.getOperand(Op.getNumOperands() - 1);
   assert(VL.getValueType() == XLenVT);
-  ScalarOp = splatSplitI64WithVL(DL, VT, ScalarOp, VL, DAG, Subtarget);
+  ScalarOp = splatSplitI64WithVL(DL, VT, ScalarOp, VL, DAG);
   return DAG.getNode(Op->getOpcode(), DL, Op->getVTList(), Operands);
 }
 
@@ -3204,12 +3245,9 @@ SDValue RISCVTargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
     // FIXME: This is probably not the best way to do this, but it is
     // consistent with INSERT_VECTOR_ELT lowering so it is a good starting
     // point.
-    //   vmv.v.x vX, hi
-    //   vsll.vx vX, vX, /*32*/
-    //   vmv.v.x vY, lo
-    //   vsll.vx vY, vY, /*32*/
-    //   vsrl.vx vY, vY, /*32*/
-    //   vor.vv vX, vX, vY
+    //   sw lo, (a0)
+    //   sw hi, 4(a0)
+    //   vlse vX, (a0)
     //
     //   vid.v      vVid
     //   vmseq.vx   mMask, vVid, 0
@@ -3218,8 +3256,7 @@ SDValue RISCVTargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
     SDValue Vec = Op.getOperand(1);
     SDValue VL = Op.getOperand(3);
 
-    SDValue SplattedVal =
-        splatSplitI64WithVL(DL, VT, Scalar, VL, DAG, Subtarget);
+    SDValue SplattedVal = splatSplitI64WithVL(DL, VT, Scalar, VL, DAG);
     SDValue SplattedIdx = DAG.getNode(RISCVISD::VMV_V_X_VL, DL, VT,
                                       DAG.getConstant(0, DL, MVT::i32), VL);
 
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
index 77b51cd2c675..d83626831c17 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
@@ -271,9 +271,8 @@ define <8 x i64> @vrgather_shuffle_xv_v8i64(<8 x i64> %x) {
 ; RV32-NEXT:    addi a0, a0, %lo(.LCPI12_0)
 ; RV32-NEXT:    vsetivli a1, 8, e16,m1,ta,mu
 ; RV32-NEXT:    vle16.v v25, (a0)
-; RV32-NEXT:    vsetivli a0, 16, e32,m4,ta,mu
-; RV32-NEXT:    vmv.v.i v12, -1
 ; RV32-NEXT:    vsetivli a0, 8, e64,m4,ta,mu
+; RV32-NEXT:    vmv.v.i v12, -1
 ; RV32-NEXT:    vrgatherei16.vv v28, v12, v25
 ; RV32-NEXT:    addi a0, zero, 113
 ; RV32-NEXT:    vsetivli a1, 1, e8,m1,ta,mu
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-splat.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-splat.ll
index 6072abc59f3e..94761f487c63 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-splat.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-splat.ll
@@ -48,35 +48,41 @@ define void @splat_v4i32(<4 x i32>* %x, i32 %y) {
 define void @splat_v2i64(<2 x i64>* %x, i64 %y) {
 ; LMULMAX8-RV32-LABEL: splat_v2i64:
 ; LMULMAX8-RV32:       # %bb.0:
-; LMULMAX8-RV32-NEXT:    addi a3, zero, 5
-; LMULMAX8-RV32-NEXT:    vsetivli a4, 1, e8,m1,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.s.x v0, a3
-; LMULMAX8-RV32-NEXT:    vsetivli a3, 4, e32,m1,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.v.x v25, a2
-; LMULMAX8-RV32-NEXT:    vmerge.vxm v25, v25, a1, v0
-; LMULMAX8-RV32-NEXT:    vse32.v v25, (a0)
+; LMULMAX8-RV32-NEXT:    addi sp, sp, -16
+; LMULMAX8-RV32-NEXT:    .cfi_def_cfa_offset 16
+; LMULMAX8-RV32-NEXT:    sw a2, 12(sp)
+; LMULMAX8-RV32-NEXT:    sw a1, 8(sp)
+; LMULMAX8-RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; LMULMAX8-RV32-NEXT:    addi a1, sp, 8
+; LMULMAX8-RV32-NEXT:    vlse64.v v25, (a1), zero
+; LMULMAX8-RV32-NEXT:    vse64.v v25, (a0)
+; LMULMAX8-RV32-NEXT:    addi sp, sp, 16
 ; LMULMAX8-RV32-NEXT:    ret
 ;
 ; LMULMAX2-RV32-LABEL: splat_v2i64:
 ; LMULMAX2-RV32:       # %bb.0:
-; LMULMAX2-RV32-NEXT:    addi a3, zero, 5
-; LMULMAX2-RV32-NEXT:    vsetivli a4, 1, e8,m1,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.s.x v0, a3
-; LMULMAX2-RV32-NEXT:    vsetivli a3, 4, e32,m1,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.v.x v25, a2
-; LMULMAX2-RV32-NEXT:    vmerge.vxm v25, v25, a1, v0
-; LMULMAX2-RV32-NEXT:    vse32.v v25, (a0)
+; LMULMAX2-RV32-NEXT:    addi sp, sp, -16
+; LMULMAX2-RV32-NEXT:    .cfi_def_cfa_offset 16
+; LMULMAX2-RV32-NEXT:    sw a2, 12(sp)
+; LMULMAX2-RV32-NEXT:    sw a1, 8(sp)
+; LMULMAX2-RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; LMULMAX2-RV32-NEXT:    addi a1, sp, 8
+; LMULMAX2-RV32-NEXT:    vlse64.v v25, (a1), zero
+; LMULMAX2-RV32-NEXT:    vse64.v v25, (a0)
+; LMULMAX2-RV32-NEXT:    addi sp, sp, 16
 ; LMULMAX2-RV32-NEXT:    ret
 ;
 ; LMULMAX1-RV32-LABEL: splat_v2i64:
 ; LMULMAX1-RV32:       # %bb.0:
-; LMULMAX1-RV32-NEXT:    addi a3, zero, 5
-; LMULMAX1-RV32-NEXT:    vsetivli a4, 1, e8,m1,ta,mu
-; LMULMAX1-RV32-NEXT:    vmv.s.x v0, a3
-; LMULMAX1-RV32-NEXT:    vsetivli a3, 4, e32,m1,ta,mu
-; LMULMAX1-RV32-NEXT:    vmv.v.x v25, a2
-; LMULMAX1-RV32-NEXT:    vmerge.vxm v25, v25, a1, v0
-; LMULMAX1-RV32-NEXT:    vse32.v v25, (a0)
+; LMULMAX1-RV32-NEXT:    addi sp, sp, -16
+; LMULMAX1-RV32-NEXT:    .cfi_def_cfa_offset 16
+; LMULMAX1-RV32-NEXT:    sw a2, 12(sp)
+; LMULMAX1-RV32-NEXT:    sw a1, 8(sp)
+; LMULMAX1-RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; LMULMAX1-RV32-NEXT:    addi a1, sp, 8
+; LMULMAX1-RV32-NEXT:    vlse64.v v25, (a1), zero
+; LMULMAX1-RV32-NEXT:    vse64.v v25, (a0)
+; LMULMAX1-RV32-NEXT:    addi sp, sp, 16
 ; LMULMAX1-RV32-NEXT:    ret
 ;
 ; LMULMAX8-RV64-LABEL: splat_v2i64:
@@ -197,24 +203,28 @@ define void @splat_v8i32(<8 x i32>* %x, i32 %y) {
 define void @splat_v4i64(<4 x i64>* %x, i64 %y) {
 ; LMULMAX8-RV32-LABEL: splat_v4i64:
 ; LMULMAX8-RV32:       # %bb.0:
-; LMULMAX8-RV32-NEXT:    addi a3, zero, 85
-; LMULMAX8-RV32-NEXT:    vsetivli a4, 1, e8,m1,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.s.x v0, a3
-; LMULMAX8-RV32-NEXT:    vsetivli a3, 8, e32,m2,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.v.x v26, a2
-; LMULMAX8-RV32-NEXT:    vmerge.vxm v26, v26, a1, v0
-; LMULMAX8-RV32-NEXT:    vse32.v v26, (a0)
+; LMULMAX8-RV32-NEXT:    addi sp, sp, -16
+; LMULMAX8-RV32-NEXT:    .cfi_def_cfa_offset 16
+; LMULMAX8-RV32-NEXT:    sw a2, 12(sp)
+; LMULMAX8-RV32-NEXT:    sw a1, 8(sp)
+; LMULMAX8-RV32-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
+; LMULMAX8-RV32-NEXT:    addi a1, sp, 8
+; LMULMAX8-RV32-NEXT:    vlse64.v v26, (a1), zero
+; LMULMAX8-RV32-NEXT:    vse64.v v26, (a0)
+; LMULMAX8-RV32-NEXT:    addi sp, sp, 16
 ; LMULMAX8-RV32-NEXT:    ret
 ;
 ; LMULMAX2-RV32-LABEL: splat_v4i64:
 ; LMULMAX2-RV32:       # %bb.0:
-; LMULMAX2-RV32-NEXT:    addi a3, zero, 85
-; LMULMAX2-RV32-NEXT:    vsetivli a4, 1, e8,m1,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.s.x v0, a3
-; LMULMAX2-RV32-NEXT:    vsetivli a3, 8, e32,m2,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.v.x v26, a2
-; LMULMAX2-RV32-NEXT:    vmerge.vxm v26, v26, a1, v0
-; LMULMAX2-RV32-NEXT:    vse32.v v26, (a0)
+; LMULMAX2-RV32-NEXT:    addi sp, sp, -16
+; LMULMAX2-RV32-NEXT:    .cfi_def_cfa_offset 16
+; LMULMAX2-RV32-NEXT:    sw a2, 12(sp)
+; LMULMAX2-RV32-NEXT:    sw a1, 8(sp)
+; LMULMAX2-RV32-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
+; LMULMAX2-RV32-NEXT:    addi a1, sp, 8
+; LMULMAX2-RV32-NEXT:    vlse64.v v26, (a1), zero
+; LMULMAX2-RV32-NEXT:    vse64.v v26, (a0)
+; LMULMAX2-RV32-NEXT:    addi sp, sp, 16
 ; LMULMAX2-RV32-NEXT:    ret
 ;
 ; LMULMAX1-RV32-LABEL: splat_v4i64:
@@ -298,47 +308,12 @@ define void @splat_zero_v4i32(<4 x i32>* %x) {
 }
 
 define void @splat_zero_v2i64(<2 x i64>* %x) {
-; LMULMAX8-RV32-LABEL: splat_zero_v2i64:
-; LMULMAX8-RV32:       # %bb.0:
-; LMULMAX8-RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.v.i v25, 0
-; LMULMAX8-RV32-NEXT:    vse32.v v25, (a0)
-; LMULMAX8-RV32-NEXT:    ret
-;
-; LMULMAX2-RV32-LABEL: splat_zero_v2i64:
-; LMULMAX2-RV32:       # %bb.0:
-; LMULMAX2-RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.v.i v25, 0
-; LMULMAX2-RV32-NEXT:    vse32.v v25, (a0)
-; LMULMAX2-RV32-NEXT:    ret
-;
-; LMULMAX1-RV32-LABEL: splat_zero_v2i64:
-; LMULMAX1-RV32:       # %bb.0:
-; LMULMAX1-RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; LMULMAX1-RV32-NEXT:    vmv.v.i v25, 0
-; LMULMAX1-RV32-NEXT:    vse32.v v25, (a0)
-; LMULMAX1-RV32-NEXT:    ret
-;
-; LMULMAX8-RV64-LABEL: splat_zero_v2i64:
-; LMULMAX8-RV64:       # %bb.0:
-; LMULMAX8-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; LMULMAX8-RV64-NEXT:    vmv.v.i v25, 0
-; LMULMAX8-RV64-NEXT:    vse64.v v25, (a0)
-; LMULMAX8-RV64-NEXT:    ret
-;
-; LMULMAX2-RV64-LABEL: splat_zero_v2i64:
-; LMULMAX2-RV64:       # %bb.0:
-; LMULMAX2-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; LMULMAX2-RV64-NEXT:    vmv.v.i v25, 0
-; LMULMAX2-RV64-NEXT:    vse64.v v25, (a0)
-; LMULMAX2-RV64-NEXT:    ret
-;
-; LMULMAX1-RV64-LABEL: splat_zero_v2i64:
-; LMULMAX1-RV64:       # %bb.0:
-; LMULMAX1-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; LMULMAX1-RV64-NEXT:    vmv.v.i v25, 0
-; LMULMAX1-RV64-NEXT:    vse64.v v25, (a0)
-; LMULMAX1-RV64-NEXT:    ret
+; CHECK-LABEL: splat_zero_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; CHECK-NEXT:    vmv.v.i v25, 0
+; CHECK-NEXT:    vse64.v v25, (a0)
+; CHECK-NEXT:    ret
   %a = insertelement <2 x i64> undef, i64 0, i32 0
   %b = shufflevector <2 x i64> %a, <2 x i64> undef, <2 x i32> zeroinitializer
   store <2 x i64> %b, <2 x i64>* %x
@@ -435,19 +410,19 @@ define void @splat_zero_v8i32(<8 x i32>* %x) {
 }
 
 define void @splat_zero_v4i64(<4 x i64>* %x) {
-; LMULMAX8-RV32-LABEL: splat_zero_v4i64:
-; LMULMAX8-RV32:       # %bb.0:
-; LMULMAX8-RV32-NEXT:    vsetivli a1, 8, e32,m2,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.v.i v26, 0
-; LMULMAX8-RV32-NEXT:    vse32.v v26, (a0)
-; LMULMAX8-RV32-NEXT:    ret
+; LMULMAX8-LABEL: splat_zero_v4i64:
+; LMULMAX8:       # %bb.0:
+; LMULMAX8-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
+; LMULMAX8-NEXT:    vmv.v.i v26, 0
+; LMULMAX8-NEXT:    vse64.v v26, (a0)
+; LMULMAX8-NEXT:    ret
 ;
-; LMULMAX2-RV32-LABEL: splat_zero_v4i64:
-; LMULMAX2-RV32:       # %bb.0:
-; LMULMAX2-RV32-NEXT:    vsetivli a1, 8, e32,m2,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.v.i v26, 0
-; LMULMAX2-RV32-NEXT:    vse32.v v26, (a0)
-; LMULMAX2-RV32-NEXT:    ret
+; LMULMAX2-LABEL: splat_zero_v4i64:
+; LMULMAX2:       # %bb.0:
+; LMULMAX2-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
+; LMULMAX2-NEXT:    vmv.v.i v26, 0
+; LMULMAX2-NEXT:    vse64.v v26, (a0)
+; LMULMAX2-NEXT:    ret
 ;
 ; LMULMAX1-RV32-LABEL: splat_zero_v4i64:
 ; LMULMAX1-RV32:       # %bb.0:
@@ -458,20 +433,6 @@ define void @splat_zero_v4i64(<4 x i64>* %x) {
 ; LMULMAX1-RV32-NEXT:    vse32.v v25, (a0)
 ; LMULMAX1-RV32-NEXT:    ret
 ;
-; LMULMAX8-RV64-LABEL: splat_zero_v4i64:
-; LMULMAX8-RV64:       # %bb.0:
-; LMULMAX8-RV64-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX8-RV64-NEXT:    vmv.v.i v26, 0
-; LMULMAX8-RV64-NEXT:    vse64.v v26, (a0)
-; LMULMAX8-RV64-NEXT:    ret
-;
-; LMULMAX2-RV64-LABEL: splat_zero_v4i64:
-; LMULMAX2-RV64:       # %bb.0:
-; LMULMAX2-RV64-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX2-RV64-NEXT:    vmv.v.i v26, 0
-; LMULMAX2-RV64-NEXT:    vse64.v v26, (a0)
-; LMULMAX2-RV64-NEXT:    ret
-;
 ; LMULMAX1-RV64-LABEL: splat_zero_v4i64:
 ; LMULMAX1-RV64:       # %bb.0:
 ; LMULMAX1-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
@@ -526,47 +487,12 @@ define void @splat_allones_v4i32(<4 x i32>* %x) {
 }
 
 define void @splat_allones_v2i64(<2 x i64>* %x) {
-; LMULMAX8-RV32-LABEL: splat_allones_v2i64:
-; LMULMAX8-RV32:       # %bb.0:
-; LMULMAX8-RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.v.i v25, -1
-; LMULMAX8-RV32-NEXT:    vse32.v v25, (a0)
-; LMULMAX8-RV32-NEXT:    ret
-;
-; LMULMAX2-RV32-LABEL: splat_allones_v2i64:
-; LMULMAX2-RV32:       # %bb.0:
-; LMULMAX2-RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.v.i v25, -1
-; LMULMAX2-RV32-NEXT:    vse32.v v25, (a0)
-; LMULMAX2-RV32-NEXT:    ret
-;
-; LMULMAX1-RV32-LABEL: splat_allones_v2i64:
-; LMULMAX1-RV32:       # %bb.0:
-; LMULMAX1-RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; LMULMAX1-RV32-NEXT:    vmv.v.i v25, -1
-; LMULMAX1-RV32-NEXT:    vse32.v v25, (a0)
-; LMULMAX1-RV32-NEXT:    ret
-;
-; LMULMAX8-RV64-LABEL: splat_allones_v2i64:
-; LMULMAX8-RV64:       # %bb.0:
-; LMULMAX8-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; LMULMAX8-RV64-NEXT:    vmv.v.i v25, -1
-; LMULMAX8-RV64-NEXT:    vse64.v v25, (a0)
-; LMULMAX8-RV64-NEXT:    ret
-;
-; LMULMAX2-RV64-LABEL: splat_allones_v2i64:
-; LMULMAX2-RV64:       # %bb.0:
-; LMULMAX2-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; LMULMAX2-RV64-NEXT:    vmv.v.i v25, -1
-; LMULMAX2-RV64-NEXT:    vse64.v v25, (a0)
-; LMULMAX2-RV64-NEXT:    ret
-;
-; LMULMAX1-RV64-LABEL: splat_allones_v2i64:
-; LMULMAX1-RV64:       # %bb.0:
-; LMULMAX1-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; LMULMAX1-RV64-NEXT:    vmv.v.i v25, -1
-; LMULMAX1-RV64-NEXT:    vse64.v v25, (a0)
-; LMULMAX1-RV64-NEXT:    ret
+; CHECK-LABEL: splat_allones_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; CHECK-NEXT:    vmv.v.i v25, -1
+; CHECK-NEXT:    vse64.v v25, (a0)
+; CHECK-NEXT:    ret
   %a = insertelement <2 x i64> undef, i64 -1, i32 0
   %b = shufflevector <2 x i64> %a, <2 x i64> undef, <2 x i32> zeroinitializer
   store <2 x i64> %b, <2 x i64>* %x
@@ -663,19 +589,19 @@ define void @splat_allones_v8i32(<8 x i32>* %x) {
 }
 
 define void @splat_allones_v4i64(<4 x i64>* %x) {
-; LMULMAX8-RV32-LABEL: splat_allones_v4i64:
-; LMULMAX8-RV32:       # %bb.0:
-; LMULMAX8-RV32-NEXT:    vsetivli a1, 8, e32,m2,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.v.i v26, -1
-; LMULMAX8-RV32-NEXT:    vse32.v v26, (a0)
-; LMULMAX8-RV32-NEXT:    ret
+; LMULMAX8-LABEL: splat_allones_v4i64:
+; LMULMAX8:       # %bb.0:
+; LMULMAX8-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
+; LMULMAX8-NEXT:    vmv.v.i v26, -1
+; LMULMAX8-NEXT:    vse64.v v26, (a0)
+; LMULMAX8-NEXT:    ret
 ;
-; LMULMAX2-RV32-LABEL: splat_allones_v4i64:
-; LMULMAX2-RV32:       # %bb.0:
-; LMULMAX2-RV32-NEXT:    vsetivli a1, 8, e32,m2,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.v.i v26, -1
-; LMULMAX2-RV32-NEXT:    vse32.v v26, (a0)
-; LMULMAX2-RV32-NEXT:    ret
+; LMULMAX2-LABEL: splat_allones_v4i64:
+; LMULMAX2:       # %bb.0:
+; LMULMAX2-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
+; LMULMAX2-NEXT:    vmv.v.i v26, -1
+; LMULMAX2-NEXT:    vse64.v v26, (a0)
+; LMULMAX2-NEXT:    ret
 ;
 ; LMULMAX1-RV32-LABEL: splat_allones_v4i64:
 ; LMULMAX1-RV32:       # %bb.0:
@@ -686,20 +612,6 @@ define void @splat_allones_v4i64(<4 x i64>* %x) {
 ; LMULMAX1-RV32-NEXT:    vse32.v v25, (a0)
 ; LMULMAX1-RV32-NEXT:    ret
 ;
-; LMULMAX8-RV64-LABEL: splat_allones_v4i64:
-; LMULMAX8-RV64:       # %bb.0:
-; LMULMAX8-RV64-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX8-RV64-NEXT:    vmv.v.i v26, -1
-; LMULMAX8-RV64-NEXT:    vse64.v v26, (a0)
-; LMULMAX8-RV64-NEXT:    ret
-;
-; LMULMAX2-RV64-LABEL: splat_allones_v4i64:
-; LMULMAX2-RV64:       # %bb.0:
-; LMULMAX2-RV64-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX2-RV64-NEXT:    vmv.v.i v26, -1
-; LMULMAX2-RV64-NEXT:    vse64.v v26, (a0)
-; LMULMAX2-RV64-NEXT:    ret
-;
 ; LMULMAX1-RV64-LABEL: splat_allones_v4i64:
 ; LMULMAX1-RV64:       # %bb.0:
 ; LMULMAX1-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
@@ -719,27 +631,21 @@ define void @splat_allones_v4i64(<4 x i64>* %x) {
 ; FIXME: We should prevent this and use the implicit sign extension of vmv.v.x
 ; with SEW=64 on RV32.
 define void @splat_allones_with_use_v4i64(<4 x i64>* %x) {
-; LMULMAX8-RV32-LABEL: splat_allones_with_use_v4i64:
-; LMULMAX8-RV32:       # %bb.0:
-; LMULMAX8-RV32-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX8-RV32-NEXT:    vle64.v v26, (a0)
-; LMULMAX8-RV32-NEXT:    vsetivli a1, 8, e32,m2,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.v.i v28, -1
-; LMULMAX8-RV32-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX8-RV32-NEXT:    vadd.vv v26, v26, v28
-; LMULMAX8-RV32-NEXT:    vse64.v v26, (a0)
-; LMULMAX8-RV32-NEXT:    ret
+; LMULMAX8-LABEL: splat_allones_with_use_v4i64:
+; LMULMAX8:       # %bb.0:
+; LMULMAX8-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
+; LMULMAX8-NEXT:    vle64.v v26, (a0)
+; LMULMAX8-NEXT:    vadd.vi v26, v26, -1
+; LMULMAX8-NEXT:    vse64.v v26, (a0)
+; LMULMAX8-NEXT:    ret
 ;
-; LMULMAX2-RV32-LABEL: splat_allones_with_use_v4i64:
-; LMULMAX2-RV32:       # %bb.0:
-; LMULMAX2-RV32-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX2-RV32-NEXT:    vle64.v v26, (a0)
-; LMULMAX2-RV32-NEXT:    vsetivli a1, 8, e32,m2,ta,mu
-; LMULMAX2-RV32-NEXT:    vmv.v.i v28, -1
-; LMULMAX2-RV32-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX2-RV32-NEXT:    vadd.vv v26, v26, v28
-; LMULMAX2-RV32-NEXT:    vse64.v v26, (a0)
-; LMULMAX2-RV32-NEXT:    ret
+; LMULMAX2-LABEL: splat_allones_with_use_v4i64:
+; LMULMAX2:       # %bb.0:
+; LMULMAX2-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
+; LMULMAX2-NEXT:    vle64.v v26, (a0)
+; LMULMAX2-NEXT:    vadd.vi v26, v26, -1
+; LMULMAX2-NEXT:    vse64.v v26, (a0)
+; LMULMAX2-NEXT:    ret
 ;
 ; LMULMAX1-RV32-LABEL: splat_allones_with_use_v4i64:
 ; LMULMAX1-RV32:       # %bb.0:
@@ -756,22 +662,6 @@ define void @splat_allones_with_use_v4i64(<4 x i64>* %x) {
 ; LMULMAX1-RV32-NEXT:    vse64.v v26, (a1)
 ; LMULMAX1-RV32-NEXT:    ret
 ;
-; LMULMAX8-RV64-LABEL: splat_allones_with_use_v4i64:
-; LMULMAX8-RV64:       # %bb.0:
-; LMULMAX8-RV64-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX8-RV64-NEXT:    vle64.v v26, (a0)
-; LMULMAX8-RV64-NEXT:    vadd.vi v26, v26, -1
-; LMULMAX8-RV64-NEXT:    vse64.v v26, (a0)
-; LMULMAX8-RV64-NEXT:    ret
-;
-; LMULMAX2-RV64-LABEL: splat_allones_with_use_v4i64:
-; LMULMAX2-RV64:       # %bb.0:
-; LMULMAX2-RV64-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; LMULMAX2-RV64-NEXT:    vle64.v v26, (a0)
-; LMULMAX2-RV64-NEXT:    vadd.vi v26, v26, -1
-; LMULMAX2-RV64-NEXT:    vse64.v v26, (a0)
-; LMULMAX2-RV64-NEXT:    ret
-;
 ; LMULMAX1-RV64-LABEL: splat_allones_with_use_v4i64:
 ; LMULMAX1-RV64:       # %bb.0:
 ; LMULMAX1-RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
@@ -796,20 +686,17 @@ define void @splat_allones_with_use_v4i64(<4 x i64>* %x) {
 define void @vadd_vx_v16i64(<16 x i64>* %a, i64 %b, <16 x i64>* %c) {
 ; LMULMAX8-RV32-LABEL: vadd_vx_v16i64:
 ; LMULMAX8-RV32:       # %bb.0:
+; LMULMAX8-RV32-NEXT:    addi sp, sp, -16
+; LMULMAX8-RV32-NEXT:    .cfi_def_cfa_offset 16
 ; LMULMAX8-RV32-NEXT:    vsetivli a4, 16, e64,m8,ta,mu
 ; LMULMAX8-RV32-NEXT:    vle64.v v8, (a0)
-; LMULMAX8-RV32-NEXT:    addi a0, zero, 32
-; LMULMAX8-RV32-NEXT:    vsetvli a4, a0, e32,m8,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.v.x v16, a2
-; LMULMAX8-RV32-NEXT:    lui a2, 349525
-; LMULMAX8-RV32-NEXT:    addi a2, a2, 1365
-; LMULMAX8-RV32-NEXT:    vsetivli a4, 1, e32,m1,ta,mu
-; LMULMAX8-RV32-NEXT:    vmv.s.x v0, a2
-; LMULMAX8-RV32-NEXT:    vsetvli a0, a0, e32,m8,ta,mu
-; LMULMAX8-RV32-NEXT:    vmerge.vxm v16, v16, a1, v0
-; LMULMAX8-RV32-NEXT:    vsetivli a0, 16, e64,m8,ta,mu
+; LMULMAX8-RV32-NEXT:    sw a2, 12(sp)
+; LMULMAX8-RV32-NEXT:    sw a1, 8(sp)
+; LMULMAX8-RV32-NEXT:    addi a0, sp, 8
+; LMULMAX8-RV32-NEXT:    vlse64.v v16, (a0), zero
 ; LMULMAX8-RV32-NEXT:    vadd.vv v8, v8, v16
 ; LMULMAX8-RV32-NEXT:    vse64.v v8, (a3)
+; LMULMAX8-RV32-NEXT:    addi sp, sp, 16
 ; LMULMAX8-RV32-NEXT:    ret
 ;
 ; LMULMAX2-RV32-LABEL: vadd_vx_v16i64:
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll
index ca83e8e58716..5eac9bcc37e8 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int.ll
@@ -5622,24 +5622,13 @@ define void @add_vi_v4i32(<4 x i32>* %x) {
 }
 
 define void @add_vi_v2i64(<2 x i64>* %x) {
-; RV32-LABEL: add_vi_v2i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v25, (a0)
-; RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.i v26, -1
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV32-NEXT:    vadd.vv v25, v25, v26
-; RV32-NEXT:    vse64.v v25, (a0)
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: add_vi_v2i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV64-NEXT:    vle64.v v25, (a0)
-; RV64-NEXT:    vadd.vi v25, v25, -1
-; RV64-NEXT:    vse64.v v25, (a0)
-; RV64-NEXT:    ret
+; CHECK-LABEL: add_vi_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; CHECK-NEXT:    vle64.v v25, (a0)
+; CHECK-NEXT:    vadd.vi v25, v25, -1
+; CHECK-NEXT:    vse64.v v25, (a0)
+; CHECK-NEXT:    ret
   %a = load <2 x i64>, <2 x i64>* %x
   %b = insertelement <2 x i64> undef, i64 -1, i32 0
   %c = shufflevector <2 x i64> %b, <2 x i64> undef, <2 x i32> zeroinitializer
@@ -5860,25 +5849,14 @@ define void @sub_vi_v4i32(<4 x i32>* %x) {
 }
 
 define void @sub_vi_v2i64(<2 x i64>* %x) {
-; RV32-LABEL: sub_vi_v2i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v25, (a0)
-; RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.i v26, -1
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV32-NEXT:    vsub.vv v25, v25, v26
-; RV32-NEXT:    vse64.v v25, (a0)
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: sub_vi_v2i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV64-NEXT:    vle64.v v25, (a0)
-; RV64-NEXT:    addi a1, zero, -1
-; RV64-NEXT:    vsub.vx v25, v25, a1
-; RV64-NEXT:    vse64.v v25, (a0)
-; RV64-NEXT:    ret
+; CHECK-LABEL: sub_vi_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; CHECK-NEXT:    vle64.v v25, (a0)
+; CHECK-NEXT:    addi a1, zero, -1
+; CHECK-NEXT:    vsub.vx v25, v25, a1
+; CHECK-NEXT:    vse64.v v25, (a0)
+; CHECK-NEXT:    ret
   %a = load <2 x i64>, <2 x i64>* %x
   %b = insertelement <2 x i64> undef, i64 -1, i32 0
   %c = shufflevector <2 x i64> %b, <2 x i64> undef, <2 x i32> zeroinitializer
@@ -6640,24 +6618,13 @@ define void @xor_vi_v4i32(<4 x i32>* %x) {
 }
 
 define void @xor_vi_v2i64(<2 x i64>* %x) {
-; RV32-LABEL: xor_vi_v2i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v25, (a0)
-; RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.i v26, -1
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV32-NEXT:    vxor.vv v25, v25, v26
-; RV32-NEXT:    vse64.v v25, (a0)
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: xor_vi_v2i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV64-NEXT:    vle64.v v25, (a0)
-; RV64-NEXT:    vxor.vi v25, v25, -1
-; RV64-NEXT:    vse64.v v25, (a0)
-; RV64-NEXT:    ret
+; CHECK-LABEL: xor_vi_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; CHECK-NEXT:    vle64.v v25, (a0)
+; CHECK-NEXT:    vxor.vi v25, v25, -1
+; CHECK-NEXT:    vse64.v v25, (a0)
+; CHECK-NEXT:    ret
   %a = load <2 x i64>, <2 x i64>* %x
   %b = insertelement <2 x i64> undef, i64 -1, i32 0
   %c = shufflevector <2 x i64> %b, <2 x i64> undef, <2 x i32> zeroinitializer
@@ -7435,21 +7402,21 @@ define void @mulhu_vx_v4i32(<4 x i32>* %x) {
 define void @mulhu_vx_v2i64(<2 x i64>* %x) {
 ; RV32-LABEL: mulhu_vx_v2i64:
 ; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
 ; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
 ; RV32-NEXT:    vle64.v v25, (a0)
-; RV32-NEXT:    addi a1, zero, 5
-; RV32-NEXT:    vsetivli a2, 1, e8,m1,ta,mu
-; RV32-NEXT:    vmv.s.x v0, a1
 ; RV32-NEXT:    lui a1, 699051
 ; RV32-NEXT:    addi a2, a1, -1366
-; RV32-NEXT:    vsetivli a3, 4, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.x v26, a2
+; RV32-NEXT:    sw a2, 12(sp)
 ; RV32-NEXT:    addi a1, a1, -1365
-; RV32-NEXT:    vmerge.vxm v26, v26, a1, v0
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vlse64.v v26, (a1), zero
 ; RV32-NEXT:    vmulhu.vv v25, v25, v26
 ; RV32-NEXT:    vsrl.vi v25, v25, 1
 ; RV32-NEXT:    vse64.v v25, (a0)
+; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: mulhu_vx_v2i64:
@@ -7557,23 +7524,23 @@ define void @mulhs_vx_v4i32(<4 x i32>* %x) {
 define void @mulhs_vx_v2i64(<2 x i64>* %x) {
 ; RV32-LABEL: mulhs_vx_v2i64:
 ; RV32:       # %bb.0:
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    .cfi_def_cfa_offset 16
 ; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
 ; RV32-NEXT:    vle64.v v25, (a0)
-; RV32-NEXT:    addi a1, zero, 5
-; RV32-NEXT:    vsetivli a2, 1, e8,m1,ta,mu
-; RV32-NEXT:    vmv.s.x v0, a1
 ; RV32-NEXT:    lui a1, 349525
 ; RV32-NEXT:    addi a2, a1, 1365
-; RV32-NEXT:    vsetivli a3, 4, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.x v26, a2
+; RV32-NEXT:    sw a2, 12(sp)
 ; RV32-NEXT:    addi a1, a1, 1366
-; RV32-NEXT:    vmerge.vxm v26, v26, a1, v0
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
+; RV32-NEXT:    sw a1, 8(sp)
+; RV32-NEXT:    addi a1, sp, 8
+; RV32-NEXT:    vlse64.v v26, (a1), zero
 ; RV32-NEXT:    vmulh.vv v25, v25, v26
 ; RV32-NEXT:    addi a1, zero, 63
 ; RV32-NEXT:    vsrl.vx v26, v25, a1
 ; RV32-NEXT:    vadd.vv v25, v25, v26
 ; RV32-NEXT:    vse64.v v25, (a0)
+; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: mulhs_vx_v2i64:
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-load-int.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-load-int.ll
index 5462f264667e..1f4a69d1f8ef 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-load-int.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-load-int.ll
@@ -54,26 +54,14 @@ define void @masked_load_v1i32(<1 x i32>* %a, <1 x i32>* %m_ptr, <1 x i32>* %res
 declare <1 x i32> @llvm.masked.load.v1i32(<1 x i32>*, i32, <1 x i1>, <1 x i32>)
 
 define void @masked_load_v1i64(<1 x i64>* %a, <1 x i64>* %m_ptr, <1 x i64>* %res_ptr) nounwind {
-; RV32-LABEL: masked_load_v1i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 1, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v25, (a1)
-; RV32-NEXT:    vsetivli a1, 2, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.i v26, 0
-; RV32-NEXT:    vsetivli a1, 1, e64,m1,ta,mu
-; RV32-NEXT:    vmseq.vv v0, v25, v26
-; RV32-NEXT:    vle64.v v25, (a0), v0.t
-; RV32-NEXT:    vse64.v v25, (a2)
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_load_v1i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 1, e64,m1,ta,mu
-; RV64-NEXT:    vle64.v v25, (a1)
-; RV64-NEXT:    vmseq.vi v0, v25, 0
-; RV64-NEXT:    vle64.v v25, (a0), v0.t
-; RV64-NEXT:    vse64.v v25, (a2)
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_load_v1i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 1, e64,m1,ta,mu
+; CHECK-NEXT:    vle64.v v25, (a1)
+; CHECK-NEXT:    vmseq.vi v0, v25, 0
+; CHECK-NEXT:    vle64.v v25, (a0), v0.t
+; CHECK-NEXT:    vse64.v v25, (a2)
+; CHECK-NEXT:    ret
   %m = load <1 x i64>, <1 x i64>* %m_ptr
   %mask = icmp eq <1 x i64> %m, zeroinitializer
   %load = call <1 x i64> @llvm.masked.load.v1i64(<1 x i64>* %a, i32 8, <1 x i1> %mask, <1 x i64> undef)
@@ -134,26 +122,14 @@ define void @masked_load_v2i32(<2 x i32>* %a, <2 x i32>* %m_ptr, <2 x i32>* %res
 declare <2 x i32> @llvm.masked.load.v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
 
 define void @masked_load_v2i64(<2 x i64>* %a, <2 x i64>* %m_ptr, <2 x i64>* %res_ptr) nounwind {
-; RV32-LABEL: masked_load_v2i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 2, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v25, (a1)
-; RV32-NEXT:    vsetivli a1, 4, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.i v26, 0
-; RV32-NEXT:    vsetivli a1, 2, e64,m1,ta,mu
-; RV32-NEXT:    vmseq.vv v0, v25, v26
-; RV32-NEXT:    vle64.v v25, (a0), v0.t
-; RV32-NEXT:    vse64.v v25, (a2)
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_load_v2i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 2, e64,m1,ta,mu
-; RV64-NEXT:    vle64.v v25, (a1)
-; RV64-NEXT:    vmseq.vi v0, v25, 0
-; RV64-NEXT:    vle64.v v25, (a0), v0.t
-; RV64-NEXT:    vse64.v v25, (a2)
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_load_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 2, e64,m1,ta,mu
+; CHECK-NEXT:    vle64.v v25, (a1)
+; CHECK-NEXT:    vmseq.vi v0, v25, 0
+; CHECK-NEXT:    vle64.v v25, (a0), v0.t
+; CHECK-NEXT:    vse64.v v25, (a2)
+; CHECK-NEXT:    ret
   %m = load <2 x i64>, <2 x i64>* %m_ptr
   %mask = icmp eq <2 x i64> %m, zeroinitializer
   %load = call <2 x i64> @llvm.masked.load.v2i64(<2 x i64>* %a, i32 8, <2 x i1> %mask, <2 x i64> undef)
@@ -214,26 +190,14 @@ define void @masked_load_v4i32(<4 x i32>* %a, <4 x i32>* %m_ptr, <4 x i32>* %res
 declare <4 x i32> @llvm.masked.load.v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
 
 define void @masked_load_v4i64(<4 x i64>* %a, <4 x i64>* %m_ptr, <4 x i64>* %res_ptr) nounwind {
-; RV32-LABEL: masked_load_v4i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 4, e64,m2,ta,mu
-; RV32-NEXT:    vle64.v v26, (a1)
-; RV32-NEXT:    vsetivli a1, 8, e32,m2,ta,mu
-; RV32-NEXT:    vmv.v.i v28, 0
-; RV32-NEXT:    vsetivli a1, 4, e64,m2,ta,mu
-; RV32-NEXT:    vmseq.vv v0, v26, v28
-; RV32-NEXT:    vle64.v v26, (a0), v0.t
-; RV32-NEXT:    vse64.v v26, (a2)
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_load_v4i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 4, e64,m2,ta,mu
-; RV64-NEXT:    vle64.v v26, (a1)
-; RV64-NEXT:    vmseq.vi v0, v26, 0
-; RV64-NEXT:    vle64.v v26, (a0), v0.t
-; RV64-NEXT:    vse64.v v26, (a2)
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_load_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 4, e64,m2,ta,mu
+; CHECK-NEXT:    vle64.v v26, (a1)
+; CHECK-NEXT:    vmseq.vi v0, v26, 0
+; CHECK-NEXT:    vle64.v v26, (a0), v0.t
+; CHECK-NEXT:    vse64.v v26, (a2)
+; CHECK-NEXT:    ret
   %m = load <4 x i64>, <4 x i64>* %m_ptr
   %mask = icmp eq <4 x i64> %m, zeroinitializer
   %load = call <4 x i64> @llvm.masked.load.v4i64(<4 x i64>* %a, i32 8, <4 x i1> %mask, <4 x i64> undef)
@@ -294,26 +258,14 @@ define void @masked_load_v8i32(<8 x i32>* %a, <8 x i32>* %m_ptr, <8 x i32>* %res
 declare <8 x i32> @llvm.masked.load.v8i32(<8 x i32>*, i32, <8 x i1>, <8 x i32>)
 
 define void @masked_load_v8i64(<8 x i64>* %a, <8 x i64>* %m_ptr, <8 x i64>* %res_ptr) nounwind {
-; RV32-LABEL: masked_load_v8i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 8, e64,m4,ta,mu
-; RV32-NEXT:    vle64.v v28, (a1)
-; RV32-NEXT:    vsetivli a1, 16, e32,m4,ta,mu
-; RV32-NEXT:    vmv.v.i v8, 0
-; RV32-NEXT:    vsetivli a1, 8, e64,m4,ta,mu
-; RV32-NEXT:    vmseq.vv v0, v28, v8
-; RV32-NEXT:    vle64.v v28, (a0), v0.t
-; RV32-NEXT:    vse64.v v28, (a2)
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_load_v8i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 8, e64,m4,ta,mu
-; RV64-NEXT:    vle64.v v28, (a1)
-; RV64-NEXT:    vmseq.vi v0, v28, 0
-; RV64-NEXT:    vle64.v v28, (a0), v0.t
-; RV64-NEXT:    vse64.v v28, (a2)
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_load_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 8, e64,m4,ta,mu
+; CHECK-NEXT:    vle64.v v28, (a1)
+; CHECK-NEXT:    vmseq.vi v0, v28, 0
+; CHECK-NEXT:    vle64.v v28, (a0), v0.t
+; CHECK-NEXT:    vse64.v v28, (a2)
+; CHECK-NEXT:    ret
   %m = load <8 x i64>, <8 x i64>* %m_ptr
   %mask = icmp eq <8 x i64> %m, zeroinitializer
   %load = call <8 x i64> @llvm.masked.load.v8i64(<8 x i64>* %a, i32 8, <8 x i1> %mask, <8 x i64> undef)
@@ -374,27 +326,14 @@ define void @masked_load_v16i32(<16 x i32>* %a, <16 x i32>* %m_ptr, <16 x i32>*
 declare <16 x i32> @llvm.masked.load.v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
 
 define void @masked_load_v16i64(<16 x i64>* %a, <16 x i64>* %m_ptr, <16 x i64>* %res_ptr) nounwind {
-; RV32-LABEL: masked_load_v16i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 16, e64,m8,ta,mu
-; RV32-NEXT:    vle64.v v8, (a1)
-; RV32-NEXT:    addi a1, zero, 32
-; RV32-NEXT:    vsetvli a1, a1, e32,m8,ta,mu
-; RV32-NEXT:    vmv.v.i v16, 0
-; RV32-NEXT:    vsetivli a1, 16, e64,m8,ta,mu
-; RV32-NEXT:    vmseq.vv v0, v8, v16
-; RV32-NEXT:    vle64.v v8, (a0), v0.t
-; RV32-NEXT:    vse64.v v8, (a2)
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_load_v16i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 16, e64,m8,ta,mu
-; RV64-NEXT:    vle64.v v8, (a1)
-; RV64-NEXT:    vmseq.vi v0, v8, 0
-; RV64-NEXT:    vle64.v v8, (a0), v0.t
-; RV64-NEXT:    vse64.v v8, (a2)
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_load_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 16, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a1)
+; CHECK-NEXT:    vmseq.vi v0, v8, 0
+; CHECK-NEXT:    vle64.v v8, (a0), v0.t
+; CHECK-NEXT:    vse64.v v8, (a2)
+; CHECK-NEXT:    ret
   %m = load <16 x i64>, <16 x i64>* %m_ptr
   %mask = icmp eq <16 x i64> %m, zeroinitializer
   %load = call <16 x i64> @llvm.masked.load.v16i64(<16 x i64>* %a, i32 8, <16 x i1> %mask, <16 x i64> undef)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-store-int.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-store-int.ll
index beeaf0ff0158..22a83f3dcb4c 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-store-int.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-store-int.ll
@@ -54,26 +54,14 @@ define void @masked_store_v1i32(<1 x i32>* %val_ptr, <1 x i32>* %a, <1 x i32>* %
 declare void @llvm.masked.store.v1i32.p0v1i32(<1 x i32>, <1 x i32>*, i32, <1 x i1>)
 
 define void @masked_store_v1i64(<1 x i64>* %val_ptr, <1 x i64>* %a, <1 x i64>* %m_ptr) nounwind {
-; RV32-LABEL: masked_store_v1i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 1, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v25, (a2)
-; RV32-NEXT:    vsetivli a2, 2, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.i v26, 0
-; RV32-NEXT:    vsetivli a2, 1, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v27, (a0)
-; RV32-NEXT:    vmseq.vv v0, v25, v26
-; RV32-NEXT:    vse64.v v27, (a1), v0.t
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_store_v1i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 1, e64,m1,ta,mu
-; RV64-NEXT:    vle64.v v25, (a2)
-; RV64-NEXT:    vle64.v v26, (a0)
-; RV64-NEXT:    vmseq.vi v0, v25, 0
-; RV64-NEXT:    vse64.v v26, (a1), v0.t
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_store_v1i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 1, e64,m1,ta,mu
+; CHECK-NEXT:    vle64.v v25, (a2)
+; CHECK-NEXT:    vle64.v v26, (a0)
+; CHECK-NEXT:    vmseq.vi v0, v25, 0
+; CHECK-NEXT:    vse64.v v26, (a1), v0.t
+; CHECK-NEXT:    ret
   %m = load <1 x i64>, <1 x i64>* %m_ptr
   %mask = icmp eq <1 x i64> %m, zeroinitializer
   %val = load <1 x i64>, <1 x i64>* %val_ptr
@@ -134,26 +122,14 @@ define void @masked_store_v2i32(<2 x i32>* %val_ptr, <2 x i32>* %a, <2 x i32>* %
 declare void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
 
 define void @masked_store_v2i64(<2 x i64>* %val_ptr, <2 x i64>* %a, <2 x i64>* %m_ptr) nounwind {
-; RV32-LABEL: masked_store_v2i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 2, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v25, (a2)
-; RV32-NEXT:    vsetivli a2, 4, e32,m1,ta,mu
-; RV32-NEXT:    vmv.v.i v26, 0
-; RV32-NEXT:    vsetivli a2, 2, e64,m1,ta,mu
-; RV32-NEXT:    vle64.v v27, (a0)
-; RV32-NEXT:    vmseq.vv v0, v25, v26
-; RV32-NEXT:    vse64.v v27, (a1), v0.t
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_store_v2i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 2, e64,m1,ta,mu
-; RV64-NEXT:    vle64.v v25, (a2)
-; RV64-NEXT:    vle64.v v26, (a0)
-; RV64-NEXT:    vmseq.vi v0, v25, 0
-; RV64-NEXT:    vse64.v v26, (a1), v0.t
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_store_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 2, e64,m1,ta,mu
+; CHECK-NEXT:    vle64.v v25, (a2)
+; CHECK-NEXT:    vle64.v v26, (a0)
+; CHECK-NEXT:    vmseq.vi v0, v25, 0
+; CHECK-NEXT:    vse64.v v26, (a1), v0.t
+; CHECK-NEXT:    ret
   %m = load <2 x i64>, <2 x i64>* %m_ptr
   %mask = icmp eq <2 x i64> %m, zeroinitializer
   %val = load <2 x i64>, <2 x i64>* %val_ptr
@@ -214,26 +190,14 @@ define void @masked_store_v4i32(<4 x i32>* %val_ptr, <4 x i32>* %a, <4 x i32>* %
 declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
 
 define void @masked_store_v4i64(<4 x i64>* %val_ptr, <4 x i64>* %a, <4 x i64>* %m_ptr) nounwind {
-; RV32-LABEL: masked_store_v4i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 4, e64,m2,ta,mu
-; RV32-NEXT:    vle64.v v26, (a2)
-; RV32-NEXT:    vsetivli a2, 8, e32,m2,ta,mu
-; RV32-NEXT:    vmv.v.i v28, 0
-; RV32-NEXT:    vsetivli a2, 4, e64,m2,ta,mu
-; RV32-NEXT:    vle64.v v30, (a0)
-; RV32-NEXT:    vmseq.vv v0, v26, v28
-; RV32-NEXT:    vse64.v v30, (a1), v0.t
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_store_v4i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 4, e64,m2,ta,mu
-; RV64-NEXT:    vle64.v v26, (a2)
-; RV64-NEXT:    vle64.v v28, (a0)
-; RV64-NEXT:    vmseq.vi v0, v26, 0
-; RV64-NEXT:    vse64.v v28, (a1), v0.t
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_store_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 4, e64,m2,ta,mu
+; CHECK-NEXT:    vle64.v v26, (a2)
+; CHECK-NEXT:    vle64.v v28, (a0)
+; CHECK-NEXT:    vmseq.vi v0, v26, 0
+; CHECK-NEXT:    vse64.v v28, (a1), v0.t
+; CHECK-NEXT:    ret
   %m = load <4 x i64>, <4 x i64>* %m_ptr
   %mask = icmp eq <4 x i64> %m, zeroinitializer
   %val = load <4 x i64>, <4 x i64>* %val_ptr
@@ -294,26 +258,14 @@ define void @masked_store_v8i32(<8 x i32>* %val_ptr, <8 x i32>* %a, <8 x i32>* %
 declare void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
 
 define void @masked_store_v8i64(<8 x i64>* %val_ptr, <8 x i64>* %a, <8 x i64>* %m_ptr) nounwind {
-; RV32-LABEL: masked_store_v8i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 8, e64,m4,ta,mu
-; RV32-NEXT:    vle64.v v28, (a2)
-; RV32-NEXT:    vsetivli a2, 16, e32,m4,ta,mu
-; RV32-NEXT:    vmv.v.i v8, 0
-; RV32-NEXT:    vsetivli a2, 8, e64,m4,ta,mu
-; RV32-NEXT:    vle64.v v12, (a0)
-; RV32-NEXT:    vmseq.vv v0, v28, v8
-; RV32-NEXT:    vse64.v v12, (a1), v0.t
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_store_v8i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 8, e64,m4,ta,mu
-; RV64-NEXT:    vle64.v v28, (a2)
-; RV64-NEXT:    vle64.v v8, (a0)
-; RV64-NEXT:    vmseq.vi v0, v28, 0
-; RV64-NEXT:    vse64.v v8, (a1), v0.t
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_store_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 8, e64,m4,ta,mu
+; CHECK-NEXT:    vle64.v v28, (a2)
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vmseq.vi v0, v28, 0
+; CHECK-NEXT:    vse64.v v8, (a1), v0.t
+; CHECK-NEXT:    ret
   %m = load <8 x i64>, <8 x i64>* %m_ptr
   %mask = icmp eq <8 x i64> %m, zeroinitializer
   %val = load <8 x i64>, <8 x i64>* %val_ptr
@@ -374,27 +326,14 @@ define void @masked_store_v16i32(<16 x i32>* %val_ptr, <16 x i32>* %a, <16 x i32
 declare void @llvm.masked.store.v16i32.p0v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
 
 define void @masked_store_v16i64(<16 x i64>* %val_ptr, <16 x i64>* %a, <16 x i64>* %m_ptr) nounwind {
-; RV32-LABEL: masked_store_v16i64:
-; RV32:       # %bb.0:
-; RV32-NEXT:    vsetivli a3, 16, e64,m8,ta,mu
-; RV32-NEXT:    vle64.v v8, (a2)
-; RV32-NEXT:    addi a2, zero, 32
-; RV32-NEXT:    vsetvli a2, a2, e32,m8,ta,mu
-; RV32-NEXT:    vmv.v.i v16, 0
-; RV32-NEXT:    vsetivli a2, 16, e64,m8,ta,mu
-; RV32-NEXT:    vle64.v v24, (a0)
-; RV32-NEXT:    vmseq.vv v0, v8, v16
-; RV32-NEXT:    vse64.v v24, (a1), v0.t
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: masked_store_v16i64:
-; RV64:       # %bb.0:
-; RV64-NEXT:    vsetivli a3, 16, e64,m8,ta,mu
-; RV64-NEXT:    vle64.v v8, (a2)
-; RV64-NEXT:    vle64.v v16, (a0)
-; RV64-NEXT:    vmseq.vi v0, v8, 0
-; RV64-NEXT:    vse64.v v16, (a1), v0.t
-; RV64-NEXT:    ret
+; CHECK-LABEL: masked_store_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli a3, 16, e64,m8,ta,mu
+; CHECK-NEXT:    vle64.v v8, (a2)
+; CHECK-NEXT:    vle64.v v16, (a0)
+; CHECK-NEXT:    vmseq.vi v0, v8, 0
+; CHECK-NEXT:    vse64.v v16, (a1), v0.t
+; CHECK-NEXT:    ret
   %m = load <16 x i64>, <16 x i64>* %m_ptr
   %mask = icmp eq <16 x i64> %m, zeroinitializer
   %val = load <16 x i64>, <16 x i64>* %val_ptr