[RISCV] Add support for matching vwmul(u) and vwmacc(u) from fixed vectors.

[craig.topper]

Summary

This adds a DAG combine to detect sext/zext inputs and emit a
new ISD opcode. The extends will either be removed or replaced
with narrower extends.

Isel patterns are used to match add and widening mul to vwmacc
similar to the recently added vmacc patterns.

There's still some work to be to match vmulsu.
We should also rewrite splats that were extended as scalars and
then splatted.

[craig.topper]

clang-format

[craig.topper]

Reword a comment slightly

[arcbbb]

LGTM

llvm/lib/Target/RISCV/RISCVISelLowering.h

enum NodeType : unsigned {
   MULHU_VL,
   FP_TO_SINT_VL,
   FP_TO_UINT_VL,
   SINT_TO_FP_VL,
   UINT_TO_FP_VL,
   FP_ROUND_VL,
   FP_EXTEND_VL,
 
+  // Widening instructions
+  VWMUL_VL,
+  VWMULU_VL,
+
   // Vector compare producing a mask. Fourth operand is input mask. Fifth
   // operand is VL.
   SETCC_VL,
 
   // Vector select with an additional VL operand. This operation is unmasked.
   VSELECT_VL,
 
   // Mask binary operators.
enum NodeType : unsigned {
   // for VL.
   VRGATHER_VX_VL,
   VRGATHER_VV_VL,
   VRGATHEREI16_VV_VL,
 
   // Vector sign/zero extend with additional mask & VL operands.
   VSEXT_VL,
   VZEXT_VL,
+
   //  vpopc.m with additional mask and VL operands.
   VPOPC_VL,
 
   // Reads value of CSR.
   // The first operand is a chain pointer. The second specifies address of the
   // required CSR. Two results are produced, the read value and the new chain
   // pointer.
   READ_CSR,

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

if (ShAmt.getOpcode() == RISCVISD::SPLAT_VECTOR_SPLIT_I64_VL) {
       SDLoc DL(N);
       EVT VT = N->getValueType(0);
       ShAmt =
           DAG.getNode(RISCVISD::SPLAT_VECTOR_I64, DL, VT, ShAmt.getOperand(0));
       return DAG.getNode(N->getOpcode(), DL, VT, N->getOperand(0), ShAmt);
     }
     break;
   }
+  case RISCVISD::MUL_VL: {
+    // Try to form VWMUL or VWMULU.
+    // FIXME: Look for splat of extended scalar as well.
+    // FIXME: Support VWMULSU.
+    SDValue Op0 = N->getOperand(0);
+    SDValue Op1 = N->getOperand(1);
+    bool IsSignExt = Op0.getOpcode() == RISCVISD::VSEXT_VL;
+    bool IsZeroExt = Op0.getOpcode() == RISCVISD::VZEXT_VL;
+    if ((!IsSignExt && !IsZeroExt) || Op0.getOpcode() != Op1.getOpcode())
+      return SDValue();
+
+    // Make sure the extends have a single use.
+    if (!Op0.hasOneUse() || !Op1.hasOneUse())
+      return SDValue();
+
+    SDValue Mask = N->getOperand(2);
+    SDValue VL = N->getOperand(3);
+    if (Op0.getOperand(1) != Mask || Op1.getOperand(1) != Mask ||
+        Op0.getOperand(2) != VL || Op1.getOperand(2) != VL)
+      return SDValue();
+
+    Op0 = Op0.getOperand(0);
+    Op1 = Op1.getOperand(0);
+
+    MVT VT = N->getSimpleValueType(0);
+    MVT NarrowVT =
+        MVT::getVectorVT(MVT::getIntegerVT(VT.getScalarSizeInBits() / 2),
+                         VT.getVectorElementCount());
+
+    SDLoc DL(N);
+
+    // Re-introduce narrower extends if needed.
+    unsigned ExtOpc = IsSignExt ? RISCVISD::VSEXT_VL : RISCVISD::VZEXT_VL;
+    if (Op0.getValueType() != NarrowVT)
+      Op0 = DAG.getNode(ExtOpc, DL, NarrowVT, Op0, Mask, VL);
+    if (Op1.getValueType() != NarrowVT)
+      Op1 = DAG.getNode(ExtOpc, DL, NarrowVT, Op1, Mask, VL);
+
+    unsigned WMulOpc = IsSignExt ? RISCVISD::VWMUL_VL : RISCVISD::VWMULU_VL;
+    return DAG.getNode(WMulOpc, DL, VT, Op0, Op1, Mask, VL);
+  }
   }
 
   return SDValue();
 }
 
 bool RISCVTargetLowering::isDesirableToCommuteWithShift(
     const SDNode *N, CombineLevel Level) const {
   // The following folds are only desirable if `(OP _, c1 << c2)` can be
#define NODE_NAME_CASE(NODE)                                                   \
   NODE_NAME_CASE(MULHS_VL)
   NODE_NAME_CASE(MULHU_VL)
   NODE_NAME_CASE(FP_TO_SINT_VL)
   NODE_NAME_CASE(FP_TO_UINT_VL)
   NODE_NAME_CASE(SINT_TO_FP_VL)
   NODE_NAME_CASE(UINT_TO_FP_VL)
   NODE_NAME_CASE(FP_EXTEND_VL)
   NODE_NAME_CASE(FP_ROUND_VL)
+  NODE_NAME_CASE(VWMUL_VL)
+  NODE_NAME_CASE(VWMULU_VL)
   NODE_NAME_CASE(SETCC_VL)
   NODE_NAME_CASE(VSELECT_VL)
   NODE_NAME_CASE(VMAND_VL)
   NODE_NAME_CASE(VMOR_VL)
   NODE_NAME_CASE(VMXOR_VL)
   NODE_NAME_CASE(VMCLR_VL)
   NODE_NAME_CASE(VMSET_VL)
   NODE_NAME_CASE(VRGATHER_VX_VL)

llvm/lib/Target/RISCV/RISCVInstrInfoVVLPatterns.td

 
 def riscv_trunc_vector_vl : SDNode<"RISCVISD::TRUNCATE_VECTOR_VL",
                                    SDTypeProfile<1, 3, [SDTCisVec<0>,
                                                         SDTCisVec<1>,
                                                         SDTCisSameNumEltsAs<0, 2>,
                                                         SDTCVecEltisVT<2, i1>,
                                                         SDTCisVT<3, XLenVT>]>>;
 
+def SDT_RISCVVWMUL_VL : SDTypeProfile<1, 4, [SDTCisVec<0>,
+                                             SDTCisSameNumEltsAs<0, 1>,
+                                             SDTCisSameAs<1, 2>,
+                                             SDTCisSameNumEltsAs<1, 3>,
+                                             SDTCVecEltisVT<3, i1>,
+                                             SDTCisVT<4, XLenVT>]>;
+def riscv_vwmul_vl  : SDNode<"RISCVISD::VWMUL_VL",  SDT_RISCVVWMUL_VL, [SDNPCommutative]>;
+def riscv_vwmulu_vl : SDNode<"RISCVISD::VWMULU_VL", SDT_RISCVVWMUL_VL, [SDNPCommutative]>;
+
 def SDTRVVVecReduce : SDTypeProfile<1, 4, [
   SDTCisVec<0>, SDTCisVec<1>, SDTCisSameAs<0, 2>, SDTCVecEltisVT<3, i1>,
   SDTCisSameNumEltsAs<1, 3>, SDTCisVT<4, XLenVT>
 ]>;
 
 def riscv_mul_vl_oneuse : PatFrag<(ops node:$A, node:$B, node:$C, node:$D),
                                   (riscv_mul_vl node:$A, node:$B, node:$C,
                                                 node:$D), [{
   return N->hasOneUse();
 }]>;
 
+def riscv_vwmul_vl_oneuse : PatFrag<(ops node:$A, node:$B, node:$C, node:$D),
+                                    (riscv_vwmul_vl node:$A, node:$B, node:$C,
+                                                    node:$D), [{
+  return N->hasOneUse();
+}]>;
+
+def riscv_vwmulu_vl_oneuse : PatFrag<(ops node:$A, node:$B, node:$C, node:$D),
+                                     (riscv_vwmulu_vl node:$A, node:$B, node:$C,
+                                                      node:$D), [{
+  return N->hasOneUse();
+}]>;
+
 foreach kind = ["ADD", "UMAX", "SMAX", "UMIN", "SMIN", "AND", "OR", "XOR",
                 "FADD", "SEQ_FADD", "FMIN", "FMAX"] in
   def rvv_vecreduce_#kind#_vl : SDNode<"RISCVISD::VECREDUCE_"#kind#"_VL", SDTRVVVecReduce>;
 
 // Ignore the vl operand.
 def SplatFPOp : PatFrag<(ops node:$op),
                         (riscv_vfmv_v_f_vl node:$op, srcvalue)>;
 
foreach vti = AllIntegerVectors in {
     defm : VPatBinaryVL_XI<vop, instruction_name, "VI",
                            vti.Vector, vti.Vector, vti.Mask, vti.Log2SEW,
                            vti.LMul, vti.RegClass, vti.RegClass,
                            !cast<ComplexPattern>(SplatPat#_#ImmType),
                            ImmType>;
   }
 }
 
+multiclass VPatBinaryWVL_VV_VX<SDNode vop, string instruction_name> {
+  foreach VtiToWti = AllWidenableIntVectors in {
+    defvar vti = VtiToWti.Vti;
+    defvar wti = VtiToWti.Wti;
+    defm : VPatBinaryVL_VV<vop, instruction_name,
+                           wti.Vector, vti.Vector, vti.Mask, vti.Log2SEW,
+                           vti.LMul, wti.RegClass, vti.RegClass>;
+    defm : VPatBinaryVL_XI<vop, instruction_name, "VX",
+                           wti.Vector, vti.Vector, vti.Mask, vti.Log2SEW,
+                           vti.LMul, wti.RegClass, vti.RegClass,
+                           SplatPat, GPR>;
+  }
+}
+
 class VPatBinaryVL_VF<SDNode vop,
                       string instruction_name,
                       ValueType result_type,
                       ValueType vop_type,
                       ValueType mask_type,
                       int sew,
                       LMULInfo vlmul,
                       VReg RetClass,

 defm : VPatBinaryVL_VV_VX<riscv_mulhu_vl, "PseudoVMULHU">;
 
 // 12.11. Vector Integer Divide Instructions
 defm : VPatBinaryVL_VV_VX<riscv_udiv_vl, "PseudoVDIVU">;
 defm : VPatBinaryVL_VV_VX<riscv_sdiv_vl, "PseudoVDIV">;
 defm : VPatBinaryVL_VV_VX<riscv_urem_vl, "PseudoVREMU">;
 defm : VPatBinaryVL_VV_VX<riscv_srem_vl, "PseudoVREM">;
 
+// 12.12. Vector Widening Integer Multiply Instructions
+defm : VPatBinaryWVL_VV_VX<riscv_vwmul_vl, "PseudoVWMUL">;
+defm : VPatBinaryWVL_VV_VX<riscv_vwmulu_vl, "PseudoVWMULU">;
+
 // 12.13 Vector Single-Width Integer Multiply-Add Instructions
 foreach vti = AllIntegerVectors in {
   // NOTE: We choose VMADD because it has the most commuting freedom. So it
   // works best with how TwoAddressInstructionPass tries commuting.
   defvar suffix = vti.LMul.MX # "_COMMUTABLE";
   def : Pat<(vti.Vector
              (riscv_add_vl vti.RegClass:$rs2,
                            (riscv_mul_vl_oneuse vti.RegClass:$rs1,
def : Pat<(vti.Vector
                                                 (vti.Mask true_mask),
                                                 VLOpFrag),
                            (vti.Mask true_mask), VLOpFrag)),
             (!cast<Instruction>("PseudoVNMSUB_VX_" # suffix)
                  vti.RegClass:$rd, vti.ScalarRegClass:$rs1, vti.RegClass:$rs2,
                  GPR:$vl, vti.Log2SEW)>;
 }
 
+// 12.14. Vector Widening Integer Multiply-Add Instructions
+foreach vtiTowti = AllWidenableIntVectors in {
+  defvar vti = vtiTowti.Vti;
+  defvar wti = vtiTowti.Wti;
+  def : Pat<(wti.Vector
+             (riscv_add_vl wti.RegClass:$rd,
+                           (riscv_vwmul_vl_oneuse vti.RegClass:$rs1,
+                                                  (vti.Vector vti.RegClass:$rs2),
+                                                  (vti.Mask true_mask), VLOpFrag),
+                           (vti.Mask true_mask), VLOpFrag)),
+            (!cast<Instruction>("PseudoVWMACC_VV_"# vti.LMul.MX)
+                 wti.RegClass:$rd, vti.RegClass:$rs1, vti.RegClass:$rs2,
+                 GPR:$vl, vti.Log2SEW)>;
+  def : Pat<(wti.Vector
+             (riscv_add_vl wti.RegClass:$rd,
+                           (riscv_vwmulu_vl_oneuse vti.RegClass:$rs1,
+                                                   (vti.Vector vti.RegClass:$rs2),
+                                                   (vti.Mask true_mask), VLOpFrag),
+                           (vti.Mask true_mask), VLOpFrag)),
+            (!cast<Instruction>("PseudoVWMACCU_VV_"# vti.LMul.MX)
+                 wti.RegClass:$rd, vti.RegClass:$rs1, vti.RegClass:$rs2,
+                 GPR:$vl, vti.Log2SEW)>;
+
+  def : Pat<(wti.Vector
+             (riscv_add_vl wti.RegClass:$rd,
+                           (riscv_vwmul_vl_oneuse (SplatPat XLenVT:$rs1),
+                                                  (vti.Vector vti.RegClass:$rs2),
+                                                  (vti.Mask true_mask), VLOpFrag),
+                           (vti.Mask true_mask), VLOpFrag)),
+            (!cast<Instruction>("PseudoVWMACC_VX_" # vti.LMul.MX)
+                 wti.RegClass:$rd, vti.ScalarRegClass:$rs1, vti.RegClass:$rs2,
+                 GPR:$vl, vti.Log2SEW)>;
+  def : Pat<(wti.Vector
+             (riscv_add_vl wti.RegClass:$rd,
+                           (riscv_vwmulu_vl_oneuse (SplatPat XLenVT:$rs1),
+                                                   (vti.Vector vti.RegClass:$rs2),
+                                                   (vti.Mask true_mask), VLOpFrag),
+                           (vti.Mask true_mask), VLOpFrag)),
+            (!cast<Instruction>("PseudoVWMACCU_VX_" # vti.LMul.MX)
+                 wti.RegClass:$rd, vti.ScalarRegClass:$rs1, vti.RegClass:$rs2,
+                 GPR:$vl, vti.Log2SEW)>;
+}
+
 // 12.15. Vector Integer Merge Instructions
 foreach vti = AllIntegerVectors in {
   def : Pat<(vti.Vector (riscv_vselect_vl (vti.Mask VMV0:$vm),
                                           vti.RegClass:$rs1,
                                           vti.RegClass:$rs2,
                                           VLOpFrag)),
             (!cast<Instruction>("PseudoVMERGE_VVM_"#vti.LMul.MX)
                  vti.RegClass:$rs2, vti.RegClass:$rs1, VMV0:$vm,

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

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK
+
+define <2 x i16> @vwmacc_v2i16(<2 x i8>* %x, <2 x i8>* %y, <2 x i16> %z) {
+; CHECK-LABEL: vwmacc_v2i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = load <2 x i8>, <2 x i8>* %y
+  %c = sext <2 x i8> %a to <2 x i16>
+  %d = sext <2 x i8> %b to <2 x i16>
+  %e = mul <2 x i16> %c, %d
+  %f = add <2 x i16> %e, %z
+  ret <2 x i16> %f
+}
+
+define <4 x i16> @vwmacc_v4i16(<4 x i8>* %x, <4 x i8>* %y, <4 x i16> %z) {
+; CHECK-LABEL: vwmacc_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = load <4 x i8>, <4 x i8>* %y
+  %c = sext <4 x i8> %a to <4 x i16>
+  %d = sext <4 x i8> %b to <4 x i16>
+  %e = mul <4 x i16> %c, %d
+  %f = add <4 x i16> %e, %z
+  ret <4 x i16> %f
+}
+
+define <2 x i32> @vwmacc_v2i32(<2 x i16>* %x, <2 x i16>* %y, <2 x i32> %z) {
+; CHECK-LABEL: vwmacc_v2i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i16>, <2 x i16>* %x
+  %b = load <2 x i16>, <2 x i16>* %y
+  %c = sext <2 x i16> %a to <2 x i32>
+  %d = sext <2 x i16> %b to <2 x i32>
+  %e = mul <2 x i32> %c, %d
+  %f = add <2 x i32> %e, %z
+  ret <2 x i32> %f
+}
+
+define <8 x i16> @vwmacc_v8i16(<8 x i8>* %x, <8 x i8>* %y, <8 x i16> %z) {
+; CHECK-LABEL: vwmacc_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i8>, <8 x i8>* %x
+  %b = load <8 x i8>, <8 x i8>* %y
+  %c = sext <8 x i8> %a to <8 x i16>
+  %d = sext <8 x i8> %b to <8 x i16>
+  %e = mul <8 x i16> %c, %d
+  %f = add <8 x i16> %e, %z
+  ret <8 x i16> %f
+}
+
+define <4 x i32> @vwmacc_v4i32(<4 x i16>* %x, <4 x i16>* %y, <4 x i32> %z) {
+; CHECK-LABEL: vwmacc_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, <4 x i16>* %x
+  %b = load <4 x i16>, <4 x i16>* %y
+  %c = sext <4 x i16> %a to <4 x i32>
+  %d = sext <4 x i16> %b to <4 x i32>
+  %e = mul <4 x i32> %c, %d
+  %f = add <4 x i32> %e, %z
+  ret <4 x i32> %f
+}
+
+define <2 x i64> @vwmacc_v2i64(<2 x i32>* %x, <2 x i32>* %y, <2 x i64> %z) {
+; CHECK-LABEL: vwmacc_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vle32.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i32>, <2 x i32>* %x
+  %b = load <2 x i32>, <2 x i32>* %y
+  %c = sext <2 x i32> %a to <2 x i64>
+  %d = sext <2 x i32> %b to <2 x i64>
+  %e = mul <2 x i64> %c, %d
+  %f = add <2 x i64> %e, %z
+  ret <2 x i64> %f
+}
+
+define <16 x i16> @vwmacc_v16i16(<16 x i8>* %x, <16 x i8>* %y, <16 x i16> %z) {
+; CHECK-LABEL: vwmacc_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = load <16 x i8>, <16 x i8>* %y
+  %c = sext <16 x i8> %a to <16 x i16>
+  %d = sext <16 x i8> %b to <16 x i16>
+  %e = mul <16 x i16> %c, %d
+  %f = add <16 x i16> %e, %z
+  ret <16 x i16> %f
+}
+
+define <8 x i32> @vwmacc_v8i32(<8 x i16>* %x, <8 x i16>* %y, <8 x i32> %z) {
+; CHECK-LABEL: vwmacc_v8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = load <8 x i16>, <8 x i16>* %y
+  %c = sext <8 x i16> %a to <8 x i32>
+  %d = sext <8 x i16> %b to <8 x i32>
+  %e = mul <8 x i32> %c, %d
+  %f = add <8 x i32> %e, %z
+  ret <8 x i32> %f
+}
+
+define <4 x i64> @vwmacc_v4i64(<4 x i32>* %x, <4 x i32>* %y, <4 x i64> %z) {
+; CHECK-LABEL: vwmacc_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vle32.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = load <4 x i32>, <4 x i32>* %y
+  %c = sext <4 x i32> %a to <4 x i64>
+  %d = sext <4 x i32> %b to <4 x i64>
+  %e = mul <4 x i64> %c, %d
+  %f = add <4 x i64> %e, %z
+  ret <4 x i64> %f
+}
+
+define <32 x i16> @vwmacc_v32i16(<32 x i8>* %x, <32 x i8>* %y, <32 x i16> %z) {
+; CHECK-LABEL: vwmacc_v32i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e8, m2, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vle8.v v28, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m2, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = load <32 x i8>, <32 x i8>* %y
+  %c = sext <32 x i8> %a to <32 x i16>
+  %d = sext <32 x i8> %b to <32 x i16>
+  %e = mul <32 x i16> %c, %d
+  %f = add <32 x i16> %e, %z
+  ret <32 x i16> %f
+}
+
+define <16 x i32> @vwmacc_v16i32(<16 x i16>* %x, <16 x i16>* %y, <16 x i32> %z) {
+; CHECK-LABEL: vwmacc_v16i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vle16.v v28, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = load <16 x i16>, <16 x i16>* %y
+  %c = sext <16 x i16> %a to <16 x i32>
+  %d = sext <16 x i16> %b to <16 x i32>
+  %e = mul <16 x i32> %c, %d
+  %f = add <16 x i32> %e, %z
+  ret <16 x i32> %f
+}
+
+define <8 x i64> @vwmacc_v8i64(<8 x i32>* %x, <8 x i32>* %y, <8 x i64> %z) {
+; CHECK-LABEL: vwmacc_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vle32.v v28, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <8 x i32>, <8 x i32>* %x
+  %b = load <8 x i32>, <8 x i32>* %y
+  %c = sext <8 x i32> %a to <8 x i64>
+  %d = sext <8 x i32> %b to <8 x i64>
+  %e = mul <8 x i64> %c, %d
+  %f = add <8 x i64> %e, %z
+  ret <8 x i64> %f
+}
+
+define <64 x i16> @vwmacc_v64i16(<64 x i8>* %x, <64 x i8>* %y, <64 x i16> %z) {
+; CHECK-LABEL: vwmacc_v64i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vle8.v v16, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m4, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <64 x i8>, <64 x i8>* %x
+  %b = load <64 x i8>, <64 x i8>* %y
+  %c = sext <64 x i8> %a to <64 x i16>
+  %d = sext <64 x i8> %b to <64 x i16>
+  %e = mul <64 x i16> %c, %d
+  %f = add <64 x i16> %e, %z
+  ret <64 x i16> %f
+}
+
+define <32 x i32> @vwmacc_v32i32(<32 x i16>* %x, <32 x i16>* %y, <32 x i32> %z) {
+; CHECK-LABEL: vwmacc_v32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vle16.v v16, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m4, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <32 x i16>, <32 x i16>* %x
+  %b = load <32 x i16>, <32 x i16>* %y
+  %c = sext <32 x i16> %a to <32 x i32>
+  %d = sext <32 x i16> %b to <32 x i32>
+  %e = mul <32 x i32> %c, %d
+  %f = add <32 x i32> %e, %z
+  ret <32 x i32> %f
+}
+
+define <16 x i64> @vwmacc_v16i64(<16 x i32>* %x, <16 x i32>* %y, <16 x i64> %z) {
+; CHECK-LABEL: vwmacc_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vle32.v v16, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, tu, mu
+; CHECK-NEXT:    vwmacc.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = load <16 x i32>, <16 x i32>* %y
+  %c = sext <16 x i32> %a to <16 x i64>
+  %d = sext <16 x i32> %b to <16 x i64>
+  %e = mul <16 x i64> %c, %d
+  %f = add <16 x i64> %e, %z
+  ret <16 x i64> %f
+}
+
+define <2 x i16> @vwmacc_vx_v2i16(<2 x i8>* %x, i8 %y, <2 x i16> %z) {
+; CHECK-LABEL: vwmacc_vx_v2i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = insertelement <2 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <2 x i8> %b, <2 x i8> undef, <2 x i32> zeroinitializer
+  %d = sext <2 x i8> %a to <2 x i16>
+  %e = sext <2 x i8> %c to <2 x i16>
+  %f = mul <2 x i16> %d, %e
+  %g = add <2 x i16> %f, %z
+  ret <2 x i16> %g
+}
+
+define <4 x i16> @vwmacc_vx_v4i16(<4 x i8>* %x, i8 %y, <4 x i16> %z) {
+; CHECK-LABEL: vwmacc_vx_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = insertelement <4 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <4 x i8> %b, <4 x i8> undef, <4 x i32> zeroinitializer
+  %d = sext <4 x i8> %a to <4 x i16>
+  %e = sext <4 x i8> %c to <4 x i16>
+  %f = mul <4 x i16> %d, %e
+  %g = add <4 x i16> %f, %z
+  ret <4 x i16> %g
+}
+
+define <2 x i32> @vwmacc_vx_v2i32(<2 x i16>* %x, i16 %y, <2 x i32> %z) {
+; CHECK-LABEL: vwmacc_vx_v2i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <2 x i16>, <2 x i16>* %x
+  %b = insertelement <2 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <2 x i16> %b, <2 x i16> undef, <2 x i32> zeroinitializer
+  %d = sext <2 x i16> %a to <2 x i32>
+  %e = sext <2 x i16> %c to <2 x i32>
+  %f = mul <2 x i32> %d, %e
+  %g = add <2 x i32> %f, %z
+  ret <2 x i32> %g
+}
+
+define <8 x i16> @vwmacc_vx_v8i16(<8 x i8>* %x, i8 %y, <8 x i16> %z) {
+; CHECK-LABEL: vwmacc_vx_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <8 x i8>, <8 x i8>* %x
+  %b = insertelement <8 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <8 x i8> %b, <8 x i8> undef, <8 x i32> zeroinitializer
+  %d = sext <8 x i8> %a to <8 x i16>
+  %e = sext <8 x i8> %c to <8 x i16>
+  %f = mul <8 x i16> %d, %e
+  %g = add <8 x i16> %f, %z
+  ret <8 x i16> %g
+}
+
+define <4 x i32> @vwmacc_vx_v4i32(<4 x i16>* %x, i16 %y, <4 x i32> %z) {
+; CHECK-LABEL: vwmacc_vx_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, <4 x i16>* %x
+  %b = insertelement <4 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <4 x i16> %b, <4 x i16> undef, <4 x i32> zeroinitializer
+  %d = sext <4 x i16> %a to <4 x i32>
+  %e = sext <4 x i16> %c to <4 x i32>
+  %f = mul <4 x i32> %d, %e
+  %g = add <4 x i32> %f, %z
+  ret <4 x i32> %g
+}
+
+define <2 x i64> @vwmacc_vx_v2i64(<2 x i32>* %x, i32 %y, <2 x i64> %z) {
+; CHECK-LABEL: vwmacc_vx_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <2 x i32>, <2 x i32>* %x
+  %b = insertelement <2 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <2 x i32> %b, <2 x i32> undef, <2 x i32> zeroinitializer
+  %d = sext <2 x i32> %a to <2 x i64>
+  %e = sext <2 x i32> %c to <2 x i64>
+  %f = mul <2 x i64> %d, %e
+  %g = add <2 x i64> %f, %z
+  ret <2 x i64> %g
+}
+
+define <16 x i16> @vwmacc_vx_v16i16(<16 x i8>* %x, i8 %y, <16 x i16> %z) {
+; CHECK-LABEL: vwmacc_vx_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = insertelement <16 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <16 x i8> %b, <16 x i8> undef, <16 x i32> zeroinitializer
+  %d = sext <16 x i8> %a to <16 x i16>
+  %e = sext <16 x i8> %c to <16 x i16>
+  %f = mul <16 x i16> %d, %e
+  %g = add <16 x i16> %f, %z
+  ret <16 x i16> %g
+}
+
+define <8 x i32> @vwmacc_vx_v8i32(<8 x i16>* %x, i16 %y, <8 x i32> %z) {
+; CHECK-LABEL: vwmacc_vx_v8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = insertelement <8 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <8 x i16> %b, <8 x i16> undef, <8 x i32> zeroinitializer
+  %d = sext <8 x i16> %a to <8 x i32>
+  %e = sext <8 x i16> %c to <8 x i32>
+  %f = mul <8 x i32> %d, %e
+  %g = add <8 x i32> %f, %z
+  ret <8 x i32> %g
+}
+
+define <4 x i64> @vwmacc_vx_v4i64(<4 x i32>* %x, i32 %y, <4 x i64> %z) {
+; CHECK-LABEL: vwmacc_vx_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = insertelement <4 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <4 x i32> %b, <4 x i32> undef, <4 x i32> zeroinitializer
+  %d = sext <4 x i32> %a to <4 x i64>
+  %e = sext <4 x i32> %c to <4 x i64>
+  %f = mul <4 x i64> %d, %e
+  %g = add <4 x i64> %f, %z
+  ret <4 x i64> %g
+}
+
+define <32 x i16> @vwmacc_vx_v32i16(<32 x i8>* %x, i8 %y, <32 x i16> %z) {
+; CHECK-LABEL: vwmacc_vx_v32i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e8, m2, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m2, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v26
+; CHECK-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = insertelement <32 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <32 x i8> %b, <32 x i8> undef, <32 x i32> zeroinitializer
+  %d = sext <32 x i8> %a to <32 x i16>
+  %e = sext <32 x i8> %c to <32 x i16>
+  %f = mul <32 x i16> %d, %e
+  %g = add <32 x i16> %f, %z
+  ret <32 x i16> %g
+}
+
+define <16 x i32> @vwmacc_vx_v16i32(<16 x i16>* %x, i16 %y, <16 x i32> %z) {
+; CHECK-LABEL: vwmacc_vx_v16i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v26
+; CHECK-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = insertelement <16 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <16 x i16> %b, <16 x i16> undef, <16 x i32> zeroinitializer
+  %d = sext <16 x i16> %a to <16 x i32>
+  %e = sext <16 x i16> %c to <16 x i32>
+  %f = mul <16 x i32> %d, %e
+  %g = add <16 x i32> %f, %z
+  ret <16 x i32> %g
+}
+
+define <8 x i64> @vwmacc_vx_v8i64(<8 x i32>* %x, i32 %y, <8 x i64> %z) {
+; CHECK-LABEL: vwmacc_vx_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i32>, <8 x i32>* %x
+  %b = insertelement <8 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <8 x i32> %b, <8 x i32> undef, <8 x i32> zeroinitializer
+  %d = sext <8 x i32> %a to <8 x i64>
+  %e = sext <8 x i32> %c to <8 x i64>
+  %f = mul <8 x i64> %d, %e
+  %g = add <8 x i64> %f, %z
+  ret <8 x i64> %g
+}
+
+define <64 x i16> @vwmacc_vx_v64i16(<64 x i8>* %x, i8 %y, <64 x i16> %z) {
+; CHECK-LABEL: vwmacc_vx_v64i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m4, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v28
+; CHECK-NEXT:    ret
+  %a = load <64 x i8>, <64 x i8>* %x
+  %b = insertelement <64 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <64 x i8> %b, <64 x i8> undef, <64 x i32> zeroinitializer
+  %d = sext <64 x i8> %a to <64 x i16>
+  %e = sext <64 x i8> %c to <64 x i16>
+  %f = mul <64 x i16> %d, %e
+  %g = add <64 x i16> %f, %z
+  ret <64 x i16> %g
+}
+
+define <32 x i32> @vwmacc_vx_v32i32(<32 x i16>* %x, i16 %y, <32 x i32> %z) {
+; CHECK-LABEL: vwmacc_vx_v32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m4, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v28
+; CHECK-NEXT:    ret
+  %a = load <32 x i16>, <32 x i16>* %x
+  %b = insertelement <32 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <32 x i16> %b, <32 x i16> undef, <32 x i32> zeroinitializer
+  %d = sext <32 x i16> %a to <32 x i32>
+  %e = sext <32 x i16> %c to <32 x i32>
+  %f = mul <32 x i32> %d, %e
+  %g = add <32 x i32> %f, %z
+  ret <32 x i32> %g
+}
+
+define <16 x i64> @vwmacc_vx_v16i64(<16 x i32>* %x, i32 %y, <16 x i64> %z) {
+; CHECK-LABEL: vwmacc_vx_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, tu, mu
+; CHECK-NEXT:    vwmacc.vx v8, a1, v28
+; CHECK-NEXT:    ret
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = insertelement <16 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
+  %d = sext <16 x i32> %a to <16 x i64>
+  %e = sext <16 x i32> %c to <16 x i64>
+  %f = mul <16 x i64> %d, %e
+  %g = add <16 x i64> %f, %z
+  ret <16 x i64> %g
+}

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

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK
+
+define <2 x i16> @vwmaccu_v2i16(<2 x i8>* %x, <2 x i8>* %y, <2 x i16> %z) {
+; CHECK-LABEL: vwmaccu_v2i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = load <2 x i8>, <2 x i8>* %y
+  %c = zext <2 x i8> %a to <2 x i16>
+  %d = zext <2 x i8> %b to <2 x i16>
+  %e = mul <2 x i16> %c, %d
+  %f = add <2 x i16> %e, %z
+  ret <2 x i16> %f
+}
+
+define <4 x i16> @vwmaccu_v4i16(<4 x i8>* %x, <4 x i8>* %y, <4 x i16> %z) {
+; CHECK-LABEL: vwmaccu_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = load <4 x i8>, <4 x i8>* %y
+  %c = zext <4 x i8> %a to <4 x i16>
+  %d = zext <4 x i8> %b to <4 x i16>
+  %e = mul <4 x i16> %c, %d
+  %f = add <4 x i16> %e, %z
+  ret <4 x i16> %f
+}
+
+define <2 x i32> @vwmaccu_v2i32(<2 x i16>* %x, <2 x i16>* %y, <2 x i32> %z) {
+; CHECK-LABEL: vwmaccu_v2i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i16>, <2 x i16>* %x
+  %b = load <2 x i16>, <2 x i16>* %y
+  %c = zext <2 x i16> %a to <2 x i32>
+  %d = zext <2 x i16> %b to <2 x i32>
+  %e = mul <2 x i32> %c, %d
+  %f = add <2 x i32> %e, %z
+  ret <2 x i32> %f
+}
+
+define <8 x i16> @vwmaccu_v8i16(<8 x i8>* %x, <8 x i8>* %y, <8 x i16> %z) {
+; CHECK-LABEL: vwmaccu_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i8>, <8 x i8>* %x
+  %b = load <8 x i8>, <8 x i8>* %y
+  %c = zext <8 x i8> %a to <8 x i16>
+  %d = zext <8 x i8> %b to <8 x i16>
+  %e = mul <8 x i16> %c, %d
+  %f = add <8 x i16> %e, %z
+  ret <8 x i16> %f
+}
+
+define <4 x i32> @vwmaccu_v4i32(<4 x i16>* %x, <4 x i16>* %y, <4 x i32> %z) {
+; CHECK-LABEL: vwmaccu_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, <4 x i16>* %x
+  %b = load <4 x i16>, <4 x i16>* %y
+  %c = zext <4 x i16> %a to <4 x i32>
+  %d = zext <4 x i16> %b to <4 x i32>
+  %e = mul <4 x i32> %c, %d
+  %f = add <4 x i32> %e, %z
+  ret <4 x i32> %f
+}
+
+define <2 x i64> @vwmaccu_v2i64(<2 x i32>* %x, <2 x i32>* %y, <2 x i64> %z) {
+; CHECK-LABEL: vwmaccu_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vle32.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i32>, <2 x i32>* %x
+  %b = load <2 x i32>, <2 x i32>* %y
+  %c = zext <2 x i32> %a to <2 x i64>
+  %d = zext <2 x i32> %b to <2 x i64>
+  %e = mul <2 x i64> %c, %d
+  %f = add <2 x i64> %e, %z
+  ret <2 x i64> %f
+}
+
+define <16 x i16> @vwmaccu_v16i16(<16 x i8>* %x, <16 x i8>* %y, <16 x i16> %z) {
+; CHECK-LABEL: vwmaccu_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = load <16 x i8>, <16 x i8>* %y
+  %c = zext <16 x i8> %a to <16 x i16>
+  %d = zext <16 x i8> %b to <16 x i16>
+  %e = mul <16 x i16> %c, %d
+  %f = add <16 x i16> %e, %z
+  ret <16 x i16> %f
+}
+
+define <8 x i32> @vwmaccu_v8i32(<8 x i16>* %x, <8 x i16>* %y, <8 x i32> %z) {
+; CHECK-LABEL: vwmaccu_v8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = load <8 x i16>, <8 x i16>* %y
+  %c = zext <8 x i16> %a to <8 x i32>
+  %d = zext <8 x i16> %b to <8 x i32>
+  %e = mul <8 x i32> %c, %d
+  %f = add <8 x i32> %e, %z
+  ret <8 x i32> %f
+}
+
+define <4 x i64> @vwmaccu_v4i64(<4 x i32>* %x, <4 x i32>* %y, <4 x i64> %z) {
+; CHECK-LABEL: vwmaccu_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vle32.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = load <4 x i32>, <4 x i32>* %y
+  %c = zext <4 x i32> %a to <4 x i64>
+  %d = zext <4 x i32> %b to <4 x i64>
+  %e = mul <4 x i64> %c, %d
+  %f = add <4 x i64> %e, %z
+  ret <4 x i64> %f
+}
+
+define <32 x i16> @vwmaccu_v32i16(<32 x i8>* %x, <32 x i8>* %y, <32 x i16> %z) {
+; CHECK-LABEL: vwmaccu_v32i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e8, m2, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vle8.v v28, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m2, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = load <32 x i8>, <32 x i8>* %y
+  %c = zext <32 x i8> %a to <32 x i16>
+  %d = zext <32 x i8> %b to <32 x i16>
+  %e = mul <32 x i16> %c, %d
+  %f = add <32 x i16> %e, %z
+  ret <32 x i16> %f
+}
+
+define <16 x i32> @vwmaccu_v16i32(<16 x i16>* %x, <16 x i16>* %y, <16 x i32> %z) {
+; CHECK-LABEL: vwmaccu_v16i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vle16.v v28, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = load <16 x i16>, <16 x i16>* %y
+  %c = zext <16 x i16> %a to <16 x i32>
+  %d = zext <16 x i16> %b to <16 x i32>
+  %e = mul <16 x i32> %c, %d
+  %f = add <16 x i32> %e, %z
+  ret <16 x i32> %f
+}
+
+define <8 x i64> @vwmaccu_v8i64(<8 x i32>* %x, <8 x i32>* %y, <8 x i64> %z) {
+; CHECK-LABEL: vwmaccu_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vle32.v v28, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <8 x i32>, <8 x i32>* %x
+  %b = load <8 x i32>, <8 x i32>* %y
+  %c = zext <8 x i32> %a to <8 x i64>
+  %d = zext <8 x i32> %b to <8 x i64>
+  %e = mul <8 x i64> %c, %d
+  %f = add <8 x i64> %e, %z
+  ret <8 x i64> %f
+}
+
+define <64 x i16> @vwmaccu_v64i16(<64 x i8>* %x, <64 x i8>* %y, <64 x i16> %z) {
+; CHECK-LABEL: vwmaccu_v64i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vle8.v v16, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m4, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <64 x i8>, <64 x i8>* %x
+  %b = load <64 x i8>, <64 x i8>* %y
+  %c = zext <64 x i8> %a to <64 x i16>
+  %d = zext <64 x i8> %b to <64 x i16>
+  %e = mul <64 x i16> %c, %d
+  %f = add <64 x i16> %e, %z
+  ret <64 x i16> %f
+}
+
+define <32 x i32> @vwmaccu_v32i32(<32 x i16>* %x, <32 x i16>* %y, <32 x i32> %z) {
+; CHECK-LABEL: vwmaccu_v32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vle16.v v16, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m4, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <32 x i16>, <32 x i16>* %x
+  %b = load <32 x i16>, <32 x i16>* %y
+  %c = zext <32 x i16> %a to <32 x i32>
+  %d = zext <32 x i16> %b to <32 x i32>
+  %e = mul <32 x i32> %c, %d
+  %f = add <32 x i32> %e, %z
+  ret <32 x i32> %f
+}
+
+define <16 x i64> @vwmaccu_v16i64(<16 x i32>* %x, <16 x i32>* %y, <16 x i64> %z) {
+; CHECK-LABEL: vwmaccu_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vle32.v v16, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, tu, mu
+; CHECK-NEXT:    vwmaccu.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = load <16 x i32>, <16 x i32>* %y
+  %c = zext <16 x i32> %a to <16 x i64>
+  %d = zext <16 x i32> %b to <16 x i64>
+  %e = mul <16 x i64> %c, %d
+  %f = add <16 x i64> %e, %z
+  ret <16 x i64> %f
+}
+
+define <2 x i16> @vwmaccu_vx_v2i16(<2 x i8>* %x, i8 %y, <2 x i16> %z) {
+; CHECK-LABEL: vwmaccu_vx_v2i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = insertelement <2 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <2 x i8> %b, <2 x i8> undef, <2 x i32> zeroinitializer
+  %d = zext <2 x i8> %a to <2 x i16>
+  %e = zext <2 x i8> %c to <2 x i16>
+  %f = mul <2 x i16> %d, %e
+  %g = add <2 x i16> %f, %z
+  ret <2 x i16> %g
+}
+
+define <4 x i16> @vwmaccu_vx_v4i16(<4 x i8>* %x, i8 %y, <4 x i16> %z) {
+; CHECK-LABEL: vwmaccu_vx_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = insertelement <4 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <4 x i8> %b, <4 x i8> undef, <4 x i32> zeroinitializer
+  %d = zext <4 x i8> %a to <4 x i16>
+  %e = zext <4 x i8> %c to <4 x i16>
+  %f = mul <4 x i16> %d, %e
+  %g = add <4 x i16> %f, %z
+  ret <4 x i16> %g
+}
+
+define <2 x i32> @vwmaccu_vx_v2i32(<2 x i16>* %x, i16 %y, <2 x i32> %z) {
+; CHECK-LABEL: vwmaccu_vx_v2i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <2 x i16>, <2 x i16>* %x
+  %b = insertelement <2 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <2 x i16> %b, <2 x i16> undef, <2 x i32> zeroinitializer
+  %d = zext <2 x i16> %a to <2 x i32>
+  %e = zext <2 x i16> %c to <2 x i32>
+  %f = mul <2 x i32> %d, %e
+  %g = add <2 x i32> %f, %z
+  ret <2 x i32> %g
+}
+
+define <8 x i16> @vwmaccu_vx_v8i16(<8 x i8>* %x, i8 %y, <8 x i16> %z) {
+; CHECK-LABEL: vwmaccu_vx_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <8 x i8>, <8 x i8>* %x
+  %b = insertelement <8 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <8 x i8> %b, <8 x i8> undef, <8 x i32> zeroinitializer
+  %d = zext <8 x i8> %a to <8 x i16>
+  %e = zext <8 x i8> %c to <8 x i16>
+  %f = mul <8 x i16> %d, %e
+  %g = add <8 x i16> %f, %z
+  ret <8 x i16> %g
+}
+
+define <4 x i32> @vwmaccu_vx_v4i32(<4 x i16>* %x, i16 %y, <4 x i32> %z) {
+; CHECK-LABEL: vwmaccu_vx_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, <4 x i16>* %x
+  %b = insertelement <4 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <4 x i16> %b, <4 x i16> undef, <4 x i32> zeroinitializer
+  %d = zext <4 x i16> %a to <4 x i32>
+  %e = zext <4 x i16> %c to <4 x i32>
+  %f = mul <4 x i32> %d, %e
+  %g = add <4 x i32> %f, %z
+  ret <4 x i32> %g
+}
+
+define <2 x i64> @vwmaccu_vx_v2i64(<2 x i32>* %x, i32 %y, <2 x i64> %z) {
+; CHECK-LABEL: vwmaccu_vx_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e32, mf2, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <2 x i32>, <2 x i32>* %x
+  %b = insertelement <2 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <2 x i32> %b, <2 x i32> undef, <2 x i32> zeroinitializer
+  %d = zext <2 x i32> %a to <2 x i64>
+  %e = zext <2 x i32> %c to <2 x i64>
+  %f = mul <2 x i64> %d, %e
+  %g = add <2 x i64> %f, %z
+  ret <2 x i64> %g
+}
+
+define <16 x i16> @vwmaccu_vx_v16i16(<16 x i8>* %x, i8 %y, <16 x i16> %z) {
+; CHECK-LABEL: vwmaccu_vx_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = insertelement <16 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <16 x i8> %b, <16 x i8> undef, <16 x i32> zeroinitializer
+  %d = zext <16 x i8> %a to <16 x i16>
+  %e = zext <16 x i8> %c to <16 x i16>
+  %f = mul <16 x i16> %d, %e
+  %g = add <16 x i16> %f, %z
+  ret <16 x i16> %g
+}
+
+define <8 x i32> @vwmaccu_vx_v8i32(<8 x i16>* %x, i16 %y, <8 x i32> %z) {
+; CHECK-LABEL: vwmaccu_vx_v8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m1, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = insertelement <8 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <8 x i16> %b, <8 x i16> undef, <8 x i32> zeroinitializer
+  %d = zext <8 x i16> %a to <8 x i32>
+  %e = zext <8 x i16> %c to <8 x i32>
+  %f = mul <8 x i32> %d, %e
+  %g = add <8 x i32> %f, %z
+  ret <8 x i32> %g
+}
+
+define <4 x i64> @vwmaccu_vx_v4i64(<4 x i32>* %x, i32 %y, <4 x i64> %z) {
+; CHECK-LABEL: vwmaccu_vx_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v25
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = insertelement <4 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <4 x i32> %b, <4 x i32> undef, <4 x i32> zeroinitializer
+  %d = zext <4 x i32> %a to <4 x i64>
+  %e = zext <4 x i32> %c to <4 x i64>
+  %f = mul <4 x i64> %d, %e
+  %g = add <4 x i64> %f, %z
+  ret <4 x i64> %g
+}
+
+define <32 x i16> @vwmaccu_vx_v32i16(<32 x i8>* %x, i8 %y, <32 x i16> %z) {
+; CHECK-LABEL: vwmaccu_vx_v32i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e8, m2, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m2, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v26
+; CHECK-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = insertelement <32 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <32 x i8> %b, <32 x i8> undef, <32 x i32> zeroinitializer
+  %d = zext <32 x i8> %a to <32 x i16>
+  %e = zext <32 x i8> %c to <32 x i16>
+  %f = mul <32 x i16> %d, %e
+  %g = add <32 x i16> %f, %z
+  ret <32 x i16> %g
+}
+
+define <16 x i32> @vwmaccu_vx_v16i32(<16 x i16>* %x, i16 %y, <16 x i32> %z) {
+; CHECK-LABEL: vwmaccu_vx_v16i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m2, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v26
+; CHECK-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = insertelement <16 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <16 x i16> %b, <16 x i16> undef, <16 x i32> zeroinitializer
+  %d = zext <16 x i16> %a to <16 x i32>
+  %e = zext <16 x i16> %c to <16 x i32>
+  %f = mul <16 x i32> %d, %e
+  %g = add <16 x i32> %f, %z
+  ret <16 x i32> %g
+}
+
+define <8 x i64> @vwmaccu_vx_v8i64(<8 x i32>* %x, i32 %y, <8 x i64> %z) {
+; CHECK-LABEL: vwmaccu_vx_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m2, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i32>, <8 x i32>* %x
+  %b = insertelement <8 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <8 x i32> %b, <8 x i32> undef, <8 x i32> zeroinitializer
+  %d = zext <8 x i32> %a to <8 x i64>
+  %e = zext <8 x i32> %c to <8 x i64>
+  %f = mul <8 x i64> %d, %e
+  %g = add <8 x i64> %f, %z
+  ret <8 x i64> %g
+}
+
+define <64 x i16> @vwmaccu_vx_v64i16(<64 x i8>* %x, i8 %y, <64 x i16> %z) {
+; CHECK-LABEL: vwmaccu_vx_v64i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, m4, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v28
+; CHECK-NEXT:    ret
+  %a = load <64 x i8>, <64 x i8>* %x
+  %b = insertelement <64 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <64 x i8> %b, <64 x i8> undef, <64 x i32> zeroinitializer
+  %d = zext <64 x i8> %a to <64 x i16>
+  %e = zext <64 x i8> %c to <64 x i16>
+  %f = mul <64 x i16> %d, %e
+  %g = add <64 x i16> %f, %z
+  ret <64 x i16> %g
+}
+
+define <32 x i32> @vwmaccu_vx_v32i32(<32 x i16>* %x, i16 %y, <32 x i32> %z) {
+; CHECK-LABEL: vwmaccu_vx_v32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, m4, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v28
+; CHECK-NEXT:    ret
+  %a = load <32 x i16>, <32 x i16>* %x
+  %b = insertelement <32 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <32 x i16> %b, <32 x i16> undef, <32 x i32> zeroinitializer
+  %d = zext <32 x i16> %a to <32 x i32>
+  %e = zext <32 x i16> %c to <32 x i32>
+  %f = mul <32 x i32> %d, %e
+  %g = add <32 x i32> %f, %z
+  ret <32 x i32> %g
+}
+
+define <16 x i64> @vwmaccu_vx_v16i64(<16 x i32>* %x, i32 %y, <16 x i64> %z) {
+; CHECK-LABEL: vwmaccu_vx_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m4, tu, mu
+; CHECK-NEXT:    vwmaccu.vx v8, a1, v28
+; CHECK-NEXT:    ret
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = insertelement <16 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
+  %d = zext <16 x i32> %a to <16 x i64>
+  %e = zext <16 x i32> %c to <16 x i64>
+  %f = mul <16 x i64> %d, %e
+  %g = add <16 x i64> %f, %z
+  ret <16 x i64> %g
+}

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

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK
+
+define <2 x i16> @vwmul_v2i16(<2 x i8>* %x, <2 x i8>* %y) {
+; CHECK-LABEL: vwmul_v2i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = load <2 x i8>, <2 x i8>* %y
+  %c = sext <2 x i8> %a to <2 x i16>
+  %d = sext <2 x i8> %b to <2 x i16>
+  %e = mul <2 x i16> %c, %d
+  ret <2 x i16> %e
+}
+
+define <4 x i16> @vwmul_v4i16(<4 x i8>* %x, <4 x i8>* %y) {
+; CHECK-LABEL: vwmul_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = load <4 x i8>, <4 x i8>* %y
+  %c = sext <4 x i8> %a to <4 x i16>
+  %d = sext <4 x i8> %b to <4 x i16>
+  %e = mul <4 x i16> %c, %d
+  ret <4 x i16> %e
+}
+
+define <2 x i32> @vwmul_v2i32(<2 x i16>* %x, <2 x i16>* %y) {
+; CHECK-LABEL: vwmul_v2i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i16>, <2 x i16>* %x
+  %b = load <2 x i16>, <2 x i16>* %y
+  %c = sext <2 x i16> %a to <2 x i32>
+  %d = sext <2 x i16> %b to <2 x i32>
+  %e = mul <2 x i32> %c, %d
+  ret <2 x i32> %e
+}
+
+define <8 x i16> @vwmul_v8i16(<8 x i8>* %x, <8 x i8>* %y) {
+; CHECK-LABEL: vwmul_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i8>, <8 x i8>* %x
+  %b = load <8 x i8>, <8 x i8>* %y
+  %c = sext <8 x i8> %a to <8 x i16>
+  %d = sext <8 x i8> %b to <8 x i16>
+  %e = mul <8 x i16> %c, %d
+  ret <8 x i16> %e
+}
+
+define <4 x i32> @vwmul_v4i32(<4 x i16>* %x, <4 x i16>* %y) {
+; CHECK-LABEL: vwmul_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, <4 x i16>* %x
+  %b = load <4 x i16>, <4 x i16>* %y
+  %c = sext <4 x i16> %a to <4 x i32>
+  %d = sext <4 x i16> %b to <4 x i32>
+  %e = mul <4 x i32> %c, %d
+  ret <4 x i32> %e
+}
+
+define <2 x i64> @vwmul_v2i64(<2 x i32>* %x, <2 x i32>* %y) {
+; CHECK-LABEL: vwmul_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vle32.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i32>, <2 x i32>* %x
+  %b = load <2 x i32>, <2 x i32>* %y
+  %c = sext <2 x i32> %a to <2 x i64>
+  %d = sext <2 x i32> %b to <2 x i64>
+  %e = mul <2 x i64> %c, %d
+  ret <2 x i64> %e
+}
+
+define <16 x i16> @vwmul_v16i16(<16 x i8>* %x, <16 x i8>* %y) {
+; CHECK-LABEL: vwmul_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = load <16 x i8>, <16 x i8>* %y
+  %c = sext <16 x i8> %a to <16 x i16>
+  %d = sext <16 x i8> %b to <16 x i16>
+  %e = mul <16 x i16> %c, %d
+  ret <16 x i16> %e
+}
+
+define <8 x i32> @vwmul_v8i32(<8 x i16>* %x, <8 x i16>* %y) {
+; CHECK-LABEL: vwmul_v8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = load <8 x i16>, <8 x i16>* %y
+  %c = sext <8 x i16> %a to <8 x i32>
+  %d = sext <8 x i16> %b to <8 x i32>
+  %e = mul <8 x i32> %c, %d
+  ret <8 x i32> %e
+}
+
+define <4 x i64> @vwmul_v4i64(<4 x i32>* %x, <4 x i32>* %y) {
+; CHECK-LABEL: vwmul_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vle32.v v26, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = load <4 x i32>, <4 x i32>* %y
+  %c = sext <4 x i32> %a to <4 x i64>
+  %d = sext <4 x i32> %b to <4 x i64>
+  %e = mul <4 x i64> %c, %d
+  ret <4 x i64> %e
+}
+
+define <32 x i16> @vwmul_v32i16(<32 x i8>* %x, <32 x i8>* %y) {
+; CHECK-LABEL: vwmul_v32i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e8, m2, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vle8.v v28, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = load <32 x i8>, <32 x i8>* %y
+  %c = sext <32 x i8> %a to <32 x i16>
+  %d = sext <32 x i8> %b to <32 x i16>
+  %e = mul <32 x i16> %c, %d
+  ret <32 x i16> %e
+}
+
+define <16 x i32> @vwmul_v16i32(<16 x i16>* %x, <16 x i16>* %y) {
+; CHECK-LABEL: vwmul_v16i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vle16.v v28, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = load <16 x i16>, <16 x i16>* %y
+  %c = sext <16 x i16> %a to <16 x i32>
+  %d = sext <16 x i16> %b to <16 x i32>
+  %e = mul <16 x i32> %c, %d
+  ret <16 x i32> %e
+}
+
+define <8 x  i64> @vwmul_v8i64(<8 x  i32>* %x, <8 x  i32>* %y) {
+; CHECK-LABEL: vwmul_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vle32.v v28, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <8 x  i32>, <8 x  i32>* %x
+  %b = load <8 x  i32>, <8 x  i32>* %y
+  %c = sext <8 x  i32> %a to <8 x  i64>
+  %d = sext <8 x  i32> %b to <8 x  i64>
+  %e = mul <8 x  i64> %c, %d
+  ret <8 x  i64> %e
+}
+
+define <64 x i16> @vwmul_v64i16(<64 x i8>* %x, <64 x i8>* %y) {
+; CHECK-LABEL: vwmul_v64i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vle8.v v16, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <64 x i8>, <64 x i8>* %x
+  %b = load <64 x i8>, <64 x i8>* %y
+  %c = sext <64 x i8> %a to <64 x i16>
+  %d = sext <64 x i8> %b to <64 x i16>
+  %e = mul <64 x i16> %c, %d
+  ret <64 x i16> %e
+}
+
+define <32 x i32> @vwmul_v32i32(<32 x i16>* %x, <32 x i16>* %y) {
+; CHECK-LABEL: vwmul_v32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vle16.v v16, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <32 x i16>, <32 x i16>* %x
+  %b = load <32 x i16>, <32 x i16>* %y
+  %c = sext <32 x i16> %a to <32 x i32>
+  %d = sext <32 x i16> %b to <32 x i32>
+  %e = mul <32 x i32> %c, %d
+  ret <32 x i32> %e
+}
+
+define <16 x i64> @vwmul_v16i64(<16 x i32>* %x, <16 x i32>* %y) {
+; CHECK-LABEL: vwmul_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vle32.v v16, (a1)
+; CHECK-NEXT:    vwmul.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = load <16 x i32>, <16 x i32>* %y
+  %c = sext <16 x i32> %a to <16 x i64>
+  %d = sext <16 x i32> %b to <16 x i64>
+  %e = mul <16 x i64> %c, %d
+  ret <16 x i64> %e
+}
+
+define <128 x i16> @vwmul_v128i16(<128 x i8>* %x, <128 x i8>* %y) {
+; CHECK-LABEL: vwmul_v128i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    addi a2, zero, 128
+; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, mu
+; CHECK-NEXT:    vle8.v v16, (a0)
+; CHECK-NEXT:    vle8.v v24, (a1)
+; CHECK-NEXT:    addi a0, zero, 64
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vslidedown.vx v8, v16, a0
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vslidedown.vx v0, v24, a0
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vwmul.vv v8, v16, v24
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vwmul.vv v16, v24, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %a = load <128 x i8>, <128 x i8>* %x
+  %b = load <128 x i8>, <128 x i8>* %y
+  %c = sext <128 x i8> %a to <128 x i16>
+  %d = sext <128 x i8> %b to <128 x i16>
+  %e = mul <128 x i16> %c, %d
+  ret <128 x i16> %e
+}
+
+define <64 x i32> @vwmul_v64i32(<64 x i16>* %x, <64 x i16>* %y) {
+; CHECK-LABEL: vwmul_v64i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e16, m8, ta, mu
+; CHECK-NEXT:    vle16.v v16, (a0)
+; CHECK-NEXT:    vle16.v v24, (a1)
+; CHECK-NEXT:    addi a0, zero, 32
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vslidedown.vx v8, v16, a0
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vslidedown.vx v0, v24, a0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vwmul.vv v8, v16, v24
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vwmul.vv v16, v24, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %a = load <64 x i16>, <64 x i16>* %x
+  %b = load <64 x i16>, <64 x i16>* %y
+  %c = sext <64 x i16> %a to <64 x i32>
+  %d = sext <64 x i16> %b to <64 x i32>
+  %e = mul <64 x i32> %c, %d
+  ret <64 x i32> %e
+}
+
+define <32 x i64> @vwmul_v32i64(<32 x i32>* %x, <32 x i32>* %y) {
+; CHECK-LABEL: vwmul_v32i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
+; CHECK-NEXT:    vle32.v v16, (a0)
+; CHECK-NEXT:    vle32.v v24, (a1)
+; CHECK-NEXT:    vsetivli zero, 16, e32, m8, ta, mu
+; CHECK-NEXT:    vslidedown.vi v8, v16, 16
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    vslidedown.vi v0, v24, 16
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vwmul.vv v8, v16, v24
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vwmul.vv v16, v24, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %a = load <32 x i32>, <32 x i32>* %x
+  %b = load <32 x i32>, <32 x i32>* %y
+  %c = sext <32 x i32> %a to <32 x i64>
+  %d = sext <32 x i32> %b to <32 x i64>
+  %e = mul <32 x i64> %c, %d
+  ret <32 x i64> %e
+}
+
+define <2 x i32> @vwmul_v2i32_v2i8(<2 x i8>* %x, <2 x i8>* %y) {
+; CHECK-LABEL: vwmul_v2i32_v2i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a1)
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
+; CHECK-NEXT:    vsext.vf2 v27, v25
+; CHECK-NEXT:    vsext.vf2 v25, v26
+; CHECK-NEXT:    vwmul.vv v8, v25, v27
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = load <2 x i8>, <2 x i8>* %y
+  %c = sext <2 x i8> %a to <2 x i32>
+  %d = sext <2 x i8> %b to <2 x i32>
+  %e = mul <2 x i32> %c, %d
+  ret <2 x i32> %e
+}
+
+define <4 x i32> @vwmul_v4i32_v4i8_v4i16(<4 x i8>* %x, <4 x i16>* %y) {
+; CHECK-LABEL: vwmul_v4i32_v4i8_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vsext.vf2 v27, v25
+; CHECK-NEXT:    vwmul.vv v8, v27, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = load <4 x i16>, <4 x i16>* %y
+  %c = sext <4 x i8> %a to <4 x i32>
+  %d = sext <4 x i16> %b to <4 x i32>
+  %e = mul <4 x i32> %c, %d
+  ret <4 x i32> %e
+}
+
+define <4 x i64> @vwmul_v4i64_v4i32_v4i8(<4 x i32>* %x, <4 x i8>* %y) {
+; CHECK-LABEL: vwmul_v4i64_v4i32_v4i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
+; CHECK-NEXT:    vsext.vf4 v27, v26
+; CHECK-NEXT:    vwmul.vv v8, v25, v27
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = load <4 x i8>, <4 x i8>* %y
+  %c = sext <4 x i32> %a to <4 x i64>
+  %d = sext <4 x i8> %b to <4 x i64>
+  %e = mul <4 x i64> %c, %d
+  ret <4 x i64> %e
+}
+
+define <2 x i16> @vwmul_vx_v2i16(<2 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmul_vx_v2i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = insertelement <2 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <2 x i8> %b, <2 x i8> undef, <2 x i32> zeroinitializer
+  %d = sext <2 x i8> %a to <2 x i16>
+  %e = sext <2 x i8> %c to <2 x i16>
+  %f = mul <2 x i16> %d, %e
+  ret <2 x i16> %f
+}
+
+define <4 x i16> @vwmul_vx_v4i16(<4 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmul_vx_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = insertelement <4 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <4 x i8> %b, <4 x i8> undef, <4 x i32> zeroinitializer
+  %d = sext <4 x i8> %a to <4 x i16>
+  %e = sext <4 x i8> %c to <4 x i16>
+  %f = mul <4 x i16> %d, %e
+  ret <4 x i16> %f
+}
+
+define <2 x i32> @vwmul_vx_v2i32(<2 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmul_vx_v2i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <2 x i16>, <2 x i16>* %x
+  %b = insertelement <2 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <2 x i16> %b, <2 x i16> undef, <2 x i32> zeroinitializer
+  %d = sext <2 x i16> %a to <2 x i32>
+  %e = sext <2 x i16> %c to <2 x i32>
+  %f = mul <2 x i32> %d, %e
+  ret <2 x i32> %f
+}
+
+define <8 x i16> @vwmul_vx_v8i16(<8 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmul_vx_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <8 x i8>, <8 x i8>* %x
+  %b = insertelement <8 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <8 x i8> %b, <8 x i8> undef, <8 x i32> zeroinitializer
+  %d = sext <8 x i8> %a to <8 x i16>
+  %e = sext <8 x i8> %c to <8 x i16>
+  %f = mul <8 x i16> %d, %e
+  ret <8 x i16> %f
+}
+
+define <4 x i32> @vwmul_vx_v4i32(<4 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmul_vx_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, <4 x i16>* %x
+  %b = insertelement <4 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <4 x i16> %b, <4 x i16> undef, <4 x i32> zeroinitializer
+  %d = sext <4 x i16> %a to <4 x i32>
+  %e = sext <4 x i16> %c to <4 x i32>
+  %f = mul <4 x i32> %d, %e
+  ret <4 x i32> %f
+}
+
+define <2 x i64> @vwmul_vx_v2i64(<2 x i32>* %x, i32 %y) {
+; CHECK-LABEL: vwmul_vx_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <2 x i32>, <2 x i32>* %x
+  %b = insertelement <2 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <2 x i32> %b, <2 x i32> undef, <2 x i32> zeroinitializer
+  %d = sext <2 x i32> %a to <2 x i64>
+  %e = sext <2 x i32> %c to <2 x i64>
+  %f = mul <2 x i64> %d, %e
+  ret <2 x i64> %f
+}
+
+define <16 x i16> @vwmul_vx_v16i16(<16 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmul_vx_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = insertelement <16 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <16 x i8> %b, <16 x i8> undef, <16 x i32> zeroinitializer
+  %d = sext <16 x i8> %a to <16 x i16>
+  %e = sext <16 x i8> %c to <16 x i16>
+  %f = mul <16 x i16> %d, %e
+  ret <16 x i16> %f
+}
+
+define <8 x i32> @vwmul_vx_v8i32(<8 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmul_vx_v8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = insertelement <8 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <8 x i16> %b, <8 x i16> undef, <8 x i32> zeroinitializer
+  %d = sext <8 x i16> %a to <8 x i32>
+  %e = sext <8 x i16> %c to <8 x i32>
+  %f = mul <8 x i32> %d, %e
+  ret <8 x i32> %f
+}
+
+define <4 x i64> @vwmul_vx_v4i64(<4 x i32>* %x, i32 %y) {
+; CHECK-LABEL: vwmul_vx_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = insertelement <4 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <4 x i32> %b, <4 x i32> undef, <4 x i32> zeroinitializer
+  %d = sext <4 x i32> %a to <4 x i64>
+  %e = sext <4 x i32> %c to <4 x i64>
+  %f = mul <4 x i64> %d, %e
+  ret <4 x i64> %f
+}
+
+define <32 x i16> @vwmul_vx_v32i16(<32 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmul_vx_v32i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e8, m2, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v26, a1
+; CHECK-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = insertelement <32 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <32 x i8> %b, <32 x i8> undef, <32 x i32> zeroinitializer
+  %d = sext <32 x i8> %a to <32 x i16>
+  %e = sext <32 x i8> %c to <32 x i16>
+  %f = mul <32 x i16> %d, %e
+  ret <32 x i16> %f
+}
+
+define <16 x i32> @vwmul_vx_v16i32(<16 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmul_vx_v16i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v26, a1
+; CHECK-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = insertelement <16 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <16 x i16> %b, <16 x i16> undef, <16 x i32> zeroinitializer
+  %d = sext <16 x i16> %a to <16 x i32>
+  %e = sext <16 x i16> %c to <16 x i32>
+  %f = mul <16 x i32> %d, %e
+  ret <16 x i32> %f
+}
+
+define <8 x i64> @vwmul_vx_v8i64(<8 x i32>* %x, i32 %y) {
+; CHECK-LABEL: vwmul_vx_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v26, a1
+; CHECK-NEXT:    ret
+  %a = load <8 x i32>, <8 x i32>* %x
+  %b = insertelement <8 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <8 x i32> %b, <8 x i32> undef, <8 x i32> zeroinitializer
+  %d = sext <8 x i32> %a to <8 x i64>
+  %e = sext <8 x i32> %c to <8 x i64>
+  %f = mul <8 x i64> %d, %e
+  ret <8 x i64> %f
+}
+
+define <64 x i16> @vwmul_vx_v64i16(<64 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmul_vx_v64i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v28, a1
+; CHECK-NEXT:    ret
+  %a = load <64 x i8>, <64 x i8>* %x
+  %b = insertelement <64 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <64 x i8> %b, <64 x i8> undef, <64 x i32> zeroinitializer
+  %d = sext <64 x i8> %a to <64 x i16>
+  %e = sext <64 x i8> %c to <64 x i16>
+  %f = mul <64 x i16> %d, %e
+  ret <64 x i16> %f
+}
+
+define <32 x i32> @vwmul_vx_v32i32(<32 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmul_vx_v32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v28, a1
+; CHECK-NEXT:    ret
+  %a = load <32 x i16>, <32 x i16>* %x
+  %b = insertelement <32 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <32 x i16> %b, <32 x i16> undef, <32 x i32> zeroinitializer
+  %d = sext <32 x i16> %a to <32 x i32>
+  %e = sext <32 x i16> %c to <32 x i32>
+  %f = mul <32 x i32> %d, %e
+  ret <32 x i32> %f
+}
+
+define <16 x i64> @vwmul_vx_v16i64(<16 x i32>* %x, i32 %y) {
+; CHECK-LABEL: vwmul_vx_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vwmul.vx v8, v28, a1
+; CHECK-NEXT:    ret
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = insertelement <16 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
+  %d = sext <16 x i32> %a to <16 x i64>
+  %e = sext <16 x i32> %c to <16 x i64>
+  %f = mul <16 x i64> %d, %e
+  ret <16 x i64> %f
+}
+

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

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK
+
+define <2 x i16> @vwmulu_v2i16(<2 x i8>* %x, <2 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v2i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = load <2 x i8>, <2 x i8>* %y
+  %c = zext <2 x i8> %a to <2 x i16>
+  %d = zext <2 x i8> %b to <2 x i16>
+  %e = mul <2 x i16> %c, %d
+  ret <2 x i16> %e
+}
+
+define <4 x i16> @vwmulu_v4i16(<4 x i8>* %x, <4 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = load <4 x i8>, <4 x i8>* %y
+  %c = zext <4 x i8> %a to <4 x i16>
+  %d = zext <4 x i8> %b to <4 x i16>
+  %e = mul <4 x i16> %c, %d
+  ret <4 x i16> %e
+}
+
+define <2 x i32> @vwmulu_v2i32(<2 x i16>* %x, <2 x i16>* %y) {
+; CHECK-LABEL: vwmulu_v2i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i16>, <2 x i16>* %x
+  %b = load <2 x i16>, <2 x i16>* %y
+  %c = zext <2 x i16> %a to <2 x i32>
+  %d = zext <2 x i16> %b to <2 x i32>
+  %e = mul <2 x i32> %c, %d
+  ret <2 x i32> %e
+}
+
+define <8 x i16> @vwmulu_v8i16(<8 x i8>* %x, <8 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i8>, <8 x i8>* %x
+  %b = load <8 x i8>, <8 x i8>* %y
+  %c = zext <8 x i8> %a to <8 x i16>
+  %d = zext <8 x i8> %b to <8 x i16>
+  %e = mul <8 x i16> %c, %d
+  ret <8 x i16> %e
+}
+
+define <4 x i32> @vwmulu_v4i32(<4 x i16>* %x, <4 x i16>* %y) {
+; CHECK-LABEL: vwmulu_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, <4 x i16>* %x
+  %b = load <4 x i16>, <4 x i16>* %y
+  %c = zext <4 x i16> %a to <4 x i32>
+  %d = zext <4 x i16> %b to <4 x i32>
+  %e = mul <4 x i32> %c, %d
+  ret <4 x i32> %e
+}
+
+define <2 x i64> @vwmulu_v2i64(<2 x i32>* %x, <2 x i32>* %y) {
+; CHECK-LABEL: vwmulu_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vle32.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <2 x i32>, <2 x i32>* %x
+  %b = load <2 x i32>, <2 x i32>* %y
+  %c = zext <2 x i32> %a to <2 x i64>
+  %d = zext <2 x i32> %b to <2 x i64>
+  %e = mul <2 x i64> %c, %d
+  ret <2 x i64> %e
+}
+
+define <16 x i16> @vwmulu_v16i16(<16 x i8>* %x, <16 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = load <16 x i8>, <16 x i8>* %y
+  %c = zext <16 x i8> %a to <16 x i16>
+  %d = zext <16 x i8> %b to <16 x i16>
+  %e = mul <16 x i16> %c, %d
+  ret <16 x i16> %e
+}
+
+define <8 x i32> @vwmulu_v8i32(<8 x i16>* %x, <8 x i16>* %y) {
+; CHECK-LABEL: vwmulu_v8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = load <8 x i16>, <8 x i16>* %y
+  %c = zext <8 x i16> %a to <8 x i32>
+  %d = zext <8 x i16> %b to <8 x i32>
+  %e = mul <8 x i32> %c, %d
+  ret <8 x i32> %e
+}
+
+define <4 x i64> @vwmulu_v4i64(<4 x i32>* %x, <4 x i32>* %y) {
+; CHECK-LABEL: vwmulu_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vle32.v v26, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v25, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = load <4 x i32>, <4 x i32>* %y
+  %c = zext <4 x i32> %a to <4 x i64>
+  %d = zext <4 x i32> %b to <4 x i64>
+  %e = mul <4 x i64> %c, %d
+  ret <4 x i64> %e
+}
+
+define <32 x i16> @vwmulu_v32i16(<32 x i8>* %x, <32 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v32i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e8, m2, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vle8.v v28, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = load <32 x i8>, <32 x i8>* %y
+  %c = zext <32 x i8> %a to <32 x i16>
+  %d = zext <32 x i8> %b to <32 x i16>
+  %e = mul <32 x i16> %c, %d
+  ret <32 x i16> %e
+}
+
+define <16 x i32> @vwmulu_v16i32(<16 x i16>* %x, <16 x i16>* %y) {
+; CHECK-LABEL: vwmulu_v16i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vle16.v v28, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = load <16 x i16>, <16 x i16>* %y
+  %c = zext <16 x i16> %a to <16 x i32>
+  %d = zext <16 x i16> %b to <16 x i32>
+  %e = mul <16 x i32> %c, %d
+  ret <16 x i32> %e
+}
+
+define <8 x  i64> @vwmulu_v8i64(<8 x  i32>* %x, <8 x  i32>* %y) {
+; CHECK-LABEL: vwmulu_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vle32.v v28, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v26, v28
+; CHECK-NEXT:    ret
+  %a = load <8 x  i32>, <8 x  i32>* %x
+  %b = load <8 x  i32>, <8 x  i32>* %y
+  %c = zext <8 x  i32> %a to <8 x  i64>
+  %d = zext <8 x  i32> %b to <8 x  i64>
+  %e = mul <8 x  i64> %c, %d
+  ret <8 x  i64> %e
+}
+
+define <64 x i16> @vwmulu_v64i16(<64 x i8>* %x, <64 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v64i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vle8.v v16, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <64 x i8>, <64 x i8>* %x
+  %b = load <64 x i8>, <64 x i8>* %y
+  %c = zext <64 x i8> %a to <64 x i16>
+  %d = zext <64 x i8> %b to <64 x i16>
+  %e = mul <64 x i16> %c, %d
+  ret <64 x i16> %e
+}
+
+define <32 x i32> @vwmulu_v32i32(<32 x i16>* %x, <32 x i16>* %y) {
+; CHECK-LABEL: vwmulu_v32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vle16.v v16, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <32 x i16>, <32 x i16>* %x
+  %b = load <32 x i16>, <32 x i16>* %y
+  %c = zext <32 x i16> %a to <32 x i32>
+  %d = zext <32 x i16> %b to <32 x i32>
+  %e = mul <32 x i32> %c, %d
+  ret <32 x i32> %e
+}
+
+define <16 x i64> @vwmulu_v16i64(<16 x i32>* %x, <16 x i32>* %y) {
+; CHECK-LABEL: vwmulu_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vle32.v v16, (a1)
+; CHECK-NEXT:    vwmulu.vv v8, v28, v16
+; CHECK-NEXT:    ret
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = load <16 x i32>, <16 x i32>* %y
+  %c = zext <16 x i32> %a to <16 x i64>
+  %d = zext <16 x i32> %b to <16 x i64>
+  %e = mul <16 x i64> %c, %d
+  ret <16 x i64> %e
+}
+
+define <128 x i16> @vwmulu_v128i16(<128 x i8>* %x, <128 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v128i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    addi a2, zero, 128
+; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, mu
+; CHECK-NEXT:    vle8.v v16, (a0)
+; CHECK-NEXT:    vle8.v v24, (a1)
+; CHECK-NEXT:    addi a0, zero, 64
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vslidedown.vx v8, v16, a0
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vslidedown.vx v0, v24, a0
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vwmulu.vv v8, v16, v24
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vwmulu.vv v16, v24, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %a = load <128 x i8>, <128 x i8>* %x
+  %b = load <128 x i8>, <128 x i8>* %y
+  %c = zext <128 x i8> %a to <128 x i16>
+  %d = zext <128 x i8> %b to <128 x i16>
+  %e = mul <128 x i16> %c, %d
+  ret <128 x i16> %e
+}
+
+define <64 x i32> @vwmulu_v64i32(<64 x i16>* %x, <64 x i16>* %y) {
+; CHECK-LABEL: vwmulu_v64i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e16, m8, ta, mu
+; CHECK-NEXT:    vle16.v v16, (a0)
+; CHECK-NEXT:    vle16.v v24, (a1)
+; CHECK-NEXT:    addi a0, zero, 32
+; CHECK-NEXT:    vsetvli zero, a0, e16, m8, ta, mu
+; CHECK-NEXT:    vslidedown.vx v8, v16, a0
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    vslidedown.vx v0, v24, a0
+; CHECK-NEXT:    vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT:    vwmulu.vv v8, v16, v24
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vwmulu.vv v16, v24, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %a = load <64 x i16>, <64 x i16>* %x
+  %b = load <64 x i16>, <64 x i16>* %y
+  %c = zext <64 x i16> %a to <64 x i32>
+  %d = zext <64 x i16> %b to <64 x i32>
+  %e = mul <64 x i32> %c, %d
+  ret <64 x i32> %e
+}
+
+define <32 x i64> @vwmulu_v32i64(<32 x i32>* %x, <32 x i32>* %y) {
+; CHECK-LABEL: vwmulu_v32i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 3
+; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
+; CHECK-NEXT:    vle32.v v16, (a0)
+; CHECK-NEXT:    vle32.v v24, (a1)
+; CHECK-NEXT:    vsetivli zero, 16, e32, m8, ta, mu
+; CHECK-NEXT:    vslidedown.vi v8, v16, 16
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    vslidedown.vi v0, v24, 16
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vwmulu.vv v8, v16, v24
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vwmulu.vv v16, v24, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %a = load <32 x i32>, <32 x i32>* %x
+  %b = load <32 x i32>, <32 x i32>* %y
+  %c = zext <32 x i32> %a to <32 x i64>
+  %d = zext <32 x i32> %b to <32 x i64>
+  %e = mul <32 x i64> %c, %d
+  ret <32 x i64> %e
+}
+
+define <2 x i32> @vwmulu_v2i32_v2i8(<2 x i8>* %x, <2 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v2i32_v2i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a1)
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf4, ta, mu
+; CHECK-NEXT:    vzext.vf2 v27, v25
+; CHECK-NEXT:    vzext.vf2 v25, v26
+; CHECK-NEXT:    vwmulu.vv v8, v25, v27
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = load <2 x i8>, <2 x i8>* %y
+  %c = zext <2 x i8> %a to <2 x i32>
+  %d = zext <2 x i8> %b to <2 x i32>
+  %e = mul <2 x i32> %c, %d
+  ret <2 x i32> %e
+}
+
+define <4 x i32> @vwmulu_v4i32_v4i8_v4i16(<4 x i8>* %x, <4 x i16>* %y) {
+; CHECK-LABEL: vwmulu_v4i32_v4i8_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a1)
+; CHECK-NEXT:    vzext.vf2 v27, v25
+; CHECK-NEXT:    vwmulu.vv v8, v27, v26
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = load <4 x i16>, <4 x i16>* %y
+  %c = zext <4 x i8> %a to <4 x i32>
+  %d = zext <4 x i16> %b to <4 x i32>
+  %e = mul <4 x i32> %c, %d
+  ret <4 x i32> %e
+}
+
+define <4 x i64> @vwmulu_v4i64_v4i32_v4i8(<4 x i32>* %x, <4 x i8>* %y) {
+; CHECK-LABEL: vwmulu_v4i64_v4i32_v4i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a1)
+; CHECK-NEXT:    vsetvli zero, zero, e32, m1, ta, mu
+; CHECK-NEXT:    vzext.vf4 v27, v26
+; CHECK-NEXT:    vwmulu.vv v8, v25, v27
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = load <4 x i8>, <4 x i8>* %y
+  %c = zext <4 x i32> %a to <4 x i64>
+  %d = zext <4 x i8> %b to <4 x i64>
+  %e = mul <4 x i64> %c, %d
+  ret <4 x i64> %e
+}
+
+define <2 x i16> @vwmulu_vx_v2i16(<2 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmulu_vx_v2i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e8, mf8, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <2 x i8>, <2 x i8>* %x
+  %b = insertelement <2 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <2 x i8> %b, <2 x i8> undef, <2 x i32> zeroinitializer
+  %d = zext <2 x i8> %a to <2 x i16>
+  %e = zext <2 x i8> %c to <2 x i16>
+  %f = mul <2 x i16> %d, %e
+  ret <2 x i16> %f
+}
+
+define <4 x i16> @vwmulu_vx_v4i16(<4 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmulu_vx_v4i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <4 x i8>, <4 x i8>* %x
+  %b = insertelement <4 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <4 x i8> %b, <4 x i8> undef, <4 x i32> zeroinitializer
+  %d = zext <4 x i8> %a to <4 x i16>
+  %e = zext <4 x i8> %c to <4 x i16>
+  %f = mul <4 x i16> %d, %e
+  ret <4 x i16> %f
+}
+
+define <2 x i32> @vwmulu_vx_v2i32(<2 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmulu_vx_v2i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <2 x i16>, <2 x i16>* %x
+  %b = insertelement <2 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <2 x i16> %b, <2 x i16> undef, <2 x i32> zeroinitializer
+  %d = zext <2 x i16> %a to <2 x i32>
+  %e = zext <2 x i16> %c to <2 x i32>
+  %f = mul <2 x i32> %d, %e
+  ret <2 x i32> %f
+}
+
+define <8 x i16> @vwmulu_vx_v8i16(<8 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmulu_vx_v8i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <8 x i8>, <8 x i8>* %x
+  %b = insertelement <8 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <8 x i8> %b, <8 x i8> undef, <8 x i32> zeroinitializer
+  %d = zext <8 x i8> %a to <8 x i16>
+  %e = zext <8 x i8> %c to <8 x i16>
+  %f = mul <8 x i16> %d, %e
+  ret <8 x i16> %f
+}
+
+define <4 x i32> @vwmulu_vx_v4i32(<4 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmulu_vx_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <4 x i16>, <4 x i16>* %x
+  %b = insertelement <4 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <4 x i16> %b, <4 x i16> undef, <4 x i32> zeroinitializer
+  %d = zext <4 x i16> %a to <4 x i32>
+  %e = zext <4 x i16> %c to <4 x i32>
+  %f = mul <4 x i32> %d, %e
+  ret <4 x i32> %f
+}
+
+define <2 x i64> @vwmulu_vx_v2i64(<2 x i32>* %x, i32 %y) {
+; CHECK-LABEL: vwmulu_vx_v2i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <2 x i32>, <2 x i32>* %x
+  %b = insertelement <2 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <2 x i32> %b, <2 x i32> undef, <2 x i32> zeroinitializer
+  %d = zext <2 x i32> %a to <2 x i64>
+  %e = zext <2 x i32> %c to <2 x i64>
+  %f = mul <2 x i64> %d, %e
+  ret <2 x i64> %f
+}
+
+define <16 x i16> @vwmulu_vx_v16i16(<16 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmulu_vx_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT:    vle8.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <16 x i8>, <16 x i8>* %x
+  %b = insertelement <16 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <16 x i8> %b, <16 x i8> undef, <16 x i32> zeroinitializer
+  %d = zext <16 x i8> %a to <16 x i16>
+  %e = zext <16 x i8> %c to <16 x i16>
+  %f = mul <16 x i16> %d, %e
+  ret <16 x i16> %f
+}
+
+define <8 x i32> @vwmulu_vx_v8i32(<8 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmulu_vx_v8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
+; CHECK-NEXT:    vle16.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <8 x i16>, <8 x i16>* %x
+  %b = insertelement <8 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <8 x i16> %b, <8 x i16> undef, <8 x i32> zeroinitializer
+  %d = zext <8 x i16> %a to <8 x i32>
+  %e = zext <8 x i16> %c to <8 x i32>
+  %f = mul <8 x i32> %d, %e
+  ret <8 x i32> %f
+}
+
+define <4 x i64> @vwmulu_vx_v4i64(<4 x i32>* %x, i32 %y) {
+; CHECK-LABEL: vwmulu_vx_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT:    vle32.v v25, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v25, a1
+; CHECK-NEXT:    ret
+  %a = load <4 x i32>, <4 x i32>* %x
+  %b = insertelement <4 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <4 x i32> %b, <4 x i32> undef, <4 x i32> zeroinitializer
+  %d = zext <4 x i32> %a to <4 x i64>
+  %e = zext <4 x i32> %c to <4 x i64>
+  %f = mul <4 x i64> %d, %e
+  ret <4 x i64> %f
+}
+
+define <32 x i16> @vwmulu_vx_v32i16(<32 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmulu_vx_v32i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e8, m2, ta, mu
+; CHECK-NEXT:    vle8.v v26, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v26, a1
+; CHECK-NEXT:    ret
+  %a = load <32 x i8>, <32 x i8>* %x
+  %b = insertelement <32 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <32 x i8> %b, <32 x i8> undef, <32 x i32> zeroinitializer
+  %d = zext <32 x i8> %a to <32 x i16>
+  %e = zext <32 x i8> %c to <32 x i16>
+  %f = mul <32 x i16> %d, %e
+  ret <32 x i16> %f
+}
+
+define <16 x i32> @vwmulu_vx_v16i32(<16 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmulu_vx_v16i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, mu
+; CHECK-NEXT:    vle16.v v26, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v26, a1
+; CHECK-NEXT:    ret
+  %a = load <16 x i16>, <16 x i16>* %x
+  %b = insertelement <16 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <16 x i16> %b, <16 x i16> undef, <16 x i32> zeroinitializer
+  %d = zext <16 x i16> %a to <16 x i32>
+  %e = zext <16 x i16> %c to <16 x i32>
+  %f = mul <16 x i32> %d, %e
+  ret <16 x i32> %f
+}
+
+define <8 x i64> @vwmulu_vx_v8i64(<8 x i32>* %x, i32 %y) {
+; CHECK-LABEL: vwmulu_vx_v8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, mu
+; CHECK-NEXT:    vle32.v v26, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v26, a1
+; CHECK-NEXT:    ret
+  %a = load <8 x i32>, <8 x i32>* %x
+  %b = insertelement <8 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <8 x i32> %b, <8 x i32> undef, <8 x i32> zeroinitializer
+  %d = zext <8 x i32> %a to <8 x i64>
+  %e = zext <8 x i32> %c to <8 x i64>
+  %f = mul <8 x i64> %d, %e
+  ret <8 x i64> %f
+}
+
+define <64 x i16> @vwmulu_vx_v64i16(<64 x i8>* %x, i8 %y) {
+; CHECK-LABEL: vwmulu_vx_v64i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 64
+; CHECK-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
+; CHECK-NEXT:    vle8.v v28, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v28, a1
+; CHECK-NEXT:    ret
+  %a = load <64 x i8>, <64 x i8>* %x
+  %b = insertelement <64 x i8> undef, i8 %y, i32 0
+  %c = shufflevector <64 x i8> %b, <64 x i8> undef, <64 x i32> zeroinitializer
+  %d = zext <64 x i8> %a to <64 x i16>
+  %e = zext <64 x i8> %c to <64 x i16>
+  %f = mul <64 x i16> %d, %e
+  ret <64 x i16> %f
+}
+
+define <32 x i32> @vwmulu_vx_v32i32(<32 x i16>* %x, i16 %y) {
+; CHECK-LABEL: vwmulu_vx_v32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi a2, zero, 32
+; CHECK-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
+; CHECK-NEXT:    vle16.v v28, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v28, a1
+; CHECK-NEXT:    ret
+  %a = load <32 x i16>, <32 x i16>* %x
+  %b = insertelement <32 x i16> undef, i16 %y, i32 0
+  %c = shufflevector <32 x i16> %b, <32 x i16> undef, <32 x i32> zeroinitializer
+  %d = zext <32 x i16> %a to <32 x i32>
+  %e = zext <32 x i16> %c to <32 x i32>
+  %f = mul <32 x i32> %d, %e
+  ret <32 x i32> %f
+}
+
+define <16 x i64> @vwmulu_vx_v16i64(<16 x i32>* %x, i32 %y) {
+; CHECK-LABEL: vwmulu_vx_v16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
+; CHECK-NEXT:    vle32.v v28, (a0)
+; CHECK-NEXT:    vwmulu.vx v8, v28, a1
+; CHECK-NEXT:    ret
+  %a = load <16 x i32>, <16 x i32>* %x
+  %b = insertelement <16 x i32> undef, i32 %y, i64 0
+  %c = shufflevector <16 x i32> %b, <16 x i32> undef, <16 x i32> zeroinitializer
+  %d = zext <16 x i32> %a to <16 x i64>
+  %e = zext <16 x i32> %c to <16 x i64>
+  %f = mul <16 x i64> %d, %e
+  ret <16 x i64> %f
+}
+