From 2ca38c891410bd712957b284a77760a3464f5d26 Mon Sep 17 00:00:00 2001
From: Hsiangkai Wang <kai.wang@sifive.com>
Date: Wed, 16 Dec 2020 16:46:21 +0800
Subject: [PATCH] [RISCV] Define vector widening mul intrinsics.

Define vector widening mul intrinsics and lower them to V instructions.

We work with @rogfer01 from BSC to come out this patch.

Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>

Differential Revision: https://reviews.llvm.org/D93381
---
 include/llvm/IR/IntrinsicsRISCV.td         |    4 +
 lib/Target/RISCV/RISCVInstrInfoVPseudos.td |   14 +
 test/CodeGen/RISCV/rvv/vwmul-rv32.ll       |  881 ++++++++++++++
 test/CodeGen/RISCV/rvv/vwmul-rv64.ll       | 1201 ++++++++++++++++++++
 test/CodeGen/RISCV/rvv/vwmulsu-rv32.ll     |  881 ++++++++++++++
 test/CodeGen/RISCV/rvv/vwmulsu-rv64.ll     | 1201 ++++++++++++++++++++
 test/CodeGen/RISCV/rvv/vwmulu-rv32.ll      |  881 ++++++++++++++
 test/CodeGen/RISCV/rvv/vwmulu-rv64.ll      | 1201 ++++++++++++++++++++
 8 files changed, 6264 insertions(+)
 create mode 100644 test/CodeGen/RISCV/rvv/vwmul-rv32.ll
 create mode 100644 test/CodeGen/RISCV/rvv/vwmul-rv64.ll
 create mode 100644 test/CodeGen/RISCV/rvv/vwmulsu-rv32.ll
 create mode 100644 test/CodeGen/RISCV/rvv/vwmulsu-rv64.ll
 create mode 100644 test/CodeGen/RISCV/rvv/vwmulu-rv32.ll
 create mode 100644 test/CodeGen/RISCV/rvv/vwmulu-rv64.ll

diff --git a/include/llvm/IR/IntrinsicsRISCV.td b/include/llvm/IR/IntrinsicsRISCV.td
index c749d78023b..bb695befd13 100644
--- a/include/llvm/IR/IntrinsicsRISCV.td
+++ b/include/llvm/IR/IntrinsicsRISCV.td
@@ -247,6 +247,10 @@ let TargetPrefix = "riscv" in {
   defm vremu : RISCVBinaryAAX;
   defm vrem : RISCVBinaryAAX;
 
+  defm vwmul : RISCVBinaryABX;
+  defm vwmulu : RISCVBinaryABX;
+  defm vwmulsu : RISCVBinaryABX;
+
   defm vfadd : RISCVBinaryAAX;
   defm vfsub : RISCVBinaryAAX;
   defm vfrsub : RISCVBinaryAAX;
diff --git a/lib/Target/RISCV/RISCVInstrInfoVPseudos.td b/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
index a05075cebd7..4d31f1217a3 100644
--- a/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
+++ b/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
@@ -1156,6 +1156,13 @@ defm PseudoVDIV        : VPseudoBinaryV_VV_VX;
 defm PseudoVREMU       : VPseudoBinaryV_VV_VX;
 defm PseudoVREM        : VPseudoBinaryV_VV_VX;
 
+//===----------------------------------------------------------------------===//
+// 12.12. Vector Widening Integer Multiply Instructions
+//===----------------------------------------------------------------------===//
+defm PseudoVWMUL       : VPseudoBinaryW_VV_VX;
+defm PseudoVWMULU      : VPseudoBinaryW_VV_VX;
+defm PseudoVWMULSU     : VPseudoBinaryW_VV_VX;
+
 } // Predicates = [HasStdExtV]
 
 let Predicates = [HasStdExtV, HasStdExtF] in {
@@ -1274,6 +1281,13 @@ defm "" : VPatBinaryV_VV_VX<"int_riscv_vdiv", "PseudoVDIV", AllIntegerVectors>;
 defm "" : VPatBinaryV_VV_VX<"int_riscv_vremu", "PseudoVREMU", AllIntegerVectors>;
 defm "" : VPatBinaryV_VV_VX<"int_riscv_vrem", "PseudoVREM", AllIntegerVectors>;
 
+//===----------------------------------------------------------------------===//
+// 12.12. Vector Widening Integer Multiply Instructions
+//===----------------------------------------------------------------------===//
+defm "" : VPatBinaryW_VV_VX<"int_riscv_vwmul", "PseudoVWMUL">;
+defm "" : VPatBinaryW_VV_VX<"int_riscv_vwmulu", "PseudoVWMULU">;
+defm "" : VPatBinaryW_VV_VX<"int_riscv_vwmulsu", "PseudoVWMULSU">;
+
 } // Predicates = [HasStdExtV]
 
 let Predicates = [HasStdExtV, HasStdExtF] in {
diff --git a/test/CodeGen/RISCV/rvv/vwmul-rv32.ll b/test/CodeGen/RISCV/rvv/vwmul-rv32.ll
new file mode 100644
index 00000000000..57f516d9ef1
--- /dev/null
+++ b/test/CodeGen/RISCV/rvv/vwmul-rv32.ll
@@ -0,0 +1,881 @@
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i16> @llvm.riscv.vwmul.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmul_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmul.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmul.mask.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmul_mask_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmul.mask.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmul.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmul_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmul.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmul.mask.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmul_mask_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmul.mask.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmul.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmul_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmul.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmul.mask.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmul_mask_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmul.mask.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmul.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmul_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmul.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmul.mask.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmul_mask_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmul.mask.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmul.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmul_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmul.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmul.mask.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmul_mask_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmul.mask.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmul.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmul_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmul.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmul.mask.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmul_mask_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmul.mask.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmul.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmul_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmul.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmul.mask.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmul_mask_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmul.mask.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmul.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmul_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmul.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmul.mask.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmul_mask_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmul.mask.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmul.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmul_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmul.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmul.mask.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmul_mask_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmul.mask.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmul.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmul_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmul.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmul.mask.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmul_mask_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmul.mask.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmul.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmul_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmul.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmul.mask.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmul_mask_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmul.mask.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmul.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmul_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmul.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmul.mask.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmul_mask_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmul.mask.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmul.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmul_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmul.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmul.mask.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmul_mask_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmul.mask.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmul.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmul_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmul.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmul.mask.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmul_mask_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmul.mask.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmul.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmul_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmul.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmul.mask.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmul_mask_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmul.mask.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmul.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmul_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmul.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmul.mask.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmul_mask_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmul.mask.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmul.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmul_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmul.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmul.mask.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmul_mask_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmul.mask.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmul.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmul_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmul.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmul.mask.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmul_mask_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmul.mask.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmul.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmul_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmul.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmul.mask.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmul_mask_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmul.mask.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmul.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmul_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmul.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmul.mask.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmul_mask_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmul.mask.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmul.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmul_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmul.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmul.mask.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmul_mask_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmul.mask.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmul.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmul_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmul.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmul.mask.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmul_mask_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmul.mask.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
diff --git a/test/CodeGen/RISCV/rvv/vwmul-rv64.ll b/test/CodeGen/RISCV/rvv/vwmul-rv64.ll
new file mode 100644
index 00000000000..d361814644c
--- /dev/null
+++ b/test/CodeGen/RISCV/rvv/vwmul-rv64.ll
@@ -0,0 +1,1201 @@
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i16> @llvm.riscv.vwmul.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmul_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmul.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmul.mask.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmul_mask_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmul.mask.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmul.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmul_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmul.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmul.mask.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmul_mask_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmul.mask.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmul.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmul_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmul.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmul.mask.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmul_mask_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmul.mask.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmul.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmul_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmul.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmul.mask.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmul_mask_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmul.mask.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmul.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmul_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmul.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmul.mask.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmul_mask_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmul.mask.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmul.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmul_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmul.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmul.mask.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmul_mask_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmul.mask.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmul.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmul_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmul.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmul.mask.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmul_mask_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmul.mask.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmul.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmul_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmul.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmul.mask.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmul_mask_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmul.mask.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmul.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmul_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmul.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmul.mask.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmul_mask_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmul.mask.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmul.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmul_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmul.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmul.mask.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmul_mask_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmul.mask.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmul.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmul_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmul.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmul.mask.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmul_mask_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmul.mask.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmul.nxv1i64.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmul_vv_nxv1i64_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv1i64_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmul.nxv1i64.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmul.mask.nxv1i64.nxv1i32.nxv1i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmul_mask_vv_nxv1i64_nxv1i32_nxv1i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv1i64_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmul.mask.nxv1i64.nxv1i32.nxv1i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmul.nxv2i64.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmul_vv_nxv2i64_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv2i64_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmul.nxv2i64.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmul.mask.nxv2i64.nxv2i32.nxv2i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmul_mask_vv_nxv2i64_nxv2i32_nxv2i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv2i64_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmul.mask.nxv2i64.nxv2i32.nxv2i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmul.nxv4i64.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmul_vv_nxv4i64_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv4i64_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmul.nxv4i64.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmul.mask.nxv4i64.nxv4i32.nxv4i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmul_mask_vv_nxv4i64_nxv4i32_nxv4i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv4i64_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmul.mask.nxv4i64.nxv4i32.nxv4i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmul.nxv8i64.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmul_vv_nxv8i64_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vv_nxv8i64_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmul.nxv8i64.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmul.mask.nxv8i64.nxv8i32.nxv8i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmul_mask_vv_nxv8i64_nxv8i32_nxv8i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vv_nxv8i64_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmul.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmul.mask.nxv8i64.nxv8i32.nxv8i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmul.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmul_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmul.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmul.mask.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmul_mask_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmul.mask.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmul.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmul_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmul.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmul.mask.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmul_mask_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmul.mask.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmul.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmul_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmul.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmul.mask.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmul_mask_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmul.mask.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmul.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmul_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmul.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmul.mask.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmul_mask_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmul.mask.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmul.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmul_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmul.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmul.mask.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmul_mask_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmul.mask.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmul.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmul_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmul.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmul.mask.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmul_mask_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmul.mask.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmul.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmul_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmul.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmul.mask.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmul_mask_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmul.mask.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmul.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmul_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmul.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmul.mask.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmul_mask_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmul.mask.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmul.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmul_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmul.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmul.mask.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmul_mask_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmul.mask.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmul.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmul_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmul.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmul.mask.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmul_mask_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmul.mask.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmul.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmul_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmul.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmul.mask.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmul_mask_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmul.mask.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmul.nxv1i64.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  i32,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmul_vx_nxv1i64_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv1i64_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmul.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmul.mask.nxv1i64.nxv1i32.i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmul_mask_vx_nxv1i64_nxv1i32_i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv1i64_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmul.mask.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmul.nxv2i64.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  i32,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmul_vx_nxv2i64_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv2i64_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmul.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmul.mask.nxv2i64.nxv2i32.i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmul_mask_vx_nxv2i64_nxv2i32_i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv2i64_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmul.mask.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmul.nxv4i64.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  i32,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmul_vx_nxv4i64_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv4i64_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmul.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmul.mask.nxv4i64.nxv4i32.i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmul_mask_vx_nxv4i64_nxv4i32_i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv4i64_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmul.mask.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmul.nxv8i64.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  i32,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmul_vx_nxv8i64_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_vx_nxv8i64_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmul.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmul.mask.nxv8i64.nxv8i32.i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmul_mask_vx_nxv8i64_nxv8i32_i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmul_mask_vx_nxv8i64_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmul.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmul.mask.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
diff --git a/test/CodeGen/RISCV/rvv/vwmulsu-rv32.ll b/test/CodeGen/RISCV/rvv/vwmulsu-rv32.ll
new file mode 100644
index 00000000000..34c9be77315
--- /dev/null
+++ b/test/CodeGen/RISCV/rvv/vwmulsu-rv32.ll
@@ -0,0 +1,881 @@
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i16> @llvm.riscv.vwmulsu.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmulsu_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulsu.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulsu.mask.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmulsu_mask_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulsu.mask.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulsu.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmulsu_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulsu.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulsu.mask.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmulsu_mask_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulsu.mask.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulsu.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmulsu_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulsu.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulsu.mask.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmulsu_mask_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulsu.mask.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulsu.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmulsu_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulsu.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulsu.mask.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmulsu_mask_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulsu.mask.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulsu.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmulsu_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulsu.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulsu.mask.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmulsu_mask_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulsu.mask.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulsu.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmulsu_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulsu.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulsu.mask.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmulsu_mask_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulsu.mask.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulsu.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmulsu_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulsu.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulsu.mask.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmulsu_mask_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulsu.mask.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulsu.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmulsu_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulsu.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulsu.mask.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmulsu_mask_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulsu.mask.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulsu.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmulsu_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulsu.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulsu.mask.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmulsu_mask_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulsu.mask.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulsu.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmulsu_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulsu.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulsu.mask.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmulsu_mask_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulsu.mask.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulsu.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmulsu_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulsu.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulsu.mask.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmulsu_mask_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulsu.mask.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulsu.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmulsu_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulsu.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulsu.mask.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmulsu_mask_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulsu.mask.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulsu.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmulsu_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulsu.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulsu.mask.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmulsu_mask_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulsu.mask.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulsu.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmulsu_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulsu.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulsu.mask.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmulsu_mask_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulsu.mask.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulsu.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmulsu_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulsu.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulsu.mask.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmulsu_mask_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulsu.mask.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulsu.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmulsu_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulsu.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulsu.mask.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmulsu_mask_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulsu.mask.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulsu.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmulsu_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulsu.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulsu.mask.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmulsu_mask_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulsu.mask.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulsu.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmulsu_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulsu.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulsu.mask.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmulsu_mask_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulsu.mask.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulsu.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmulsu_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulsu.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulsu.mask.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmulsu_mask_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulsu.mask.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulsu.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmulsu_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulsu.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulsu.mask.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmulsu_mask_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulsu.mask.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulsu.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmulsu_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulsu.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulsu.mask.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmulsu_mask_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulsu.mask.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulsu.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmulsu_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulsu.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulsu.mask.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmulsu_mask_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulsu.mask.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
diff --git a/test/CodeGen/RISCV/rvv/vwmulsu-rv64.ll b/test/CodeGen/RISCV/rvv/vwmulsu-rv64.ll
new file mode 100644
index 00000000000..089f4af5512
--- /dev/null
+++ b/test/CodeGen/RISCV/rvv/vwmulsu-rv64.ll
@@ -0,0 +1,1201 @@
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i16> @llvm.riscv.vwmulsu.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmulsu_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulsu.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulsu.mask.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmulsu_mask_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulsu.mask.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulsu.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmulsu_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulsu.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulsu.mask.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmulsu_mask_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulsu.mask.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulsu.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmulsu_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulsu.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulsu.mask.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmulsu_mask_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulsu.mask.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulsu.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmulsu_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulsu.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulsu.mask.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmulsu_mask_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulsu.mask.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulsu.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmulsu_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulsu.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulsu.mask.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmulsu_mask_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulsu.mask.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulsu.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmulsu_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulsu.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulsu.mask.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmulsu_mask_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulsu.mask.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulsu.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmulsu_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulsu.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulsu.mask.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmulsu_mask_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulsu.mask.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulsu.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmulsu_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulsu.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulsu.mask.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmulsu_mask_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulsu.mask.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulsu.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmulsu_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulsu.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulsu.mask.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmulsu_mask_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulsu.mask.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulsu.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmulsu_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulsu.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulsu.mask.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmulsu_mask_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulsu.mask.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulsu.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmulsu_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulsu.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulsu.mask.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmulsu_mask_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulsu.mask.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmulsu.nxv1i64.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmulsu_vv_nxv1i64_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv1i64_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmulsu.nxv1i64.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmulsu.mask.nxv1i64.nxv1i32.nxv1i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmulsu_mask_vv_nxv1i64_nxv1i32_nxv1i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv1i64_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmulsu.mask.nxv1i64.nxv1i32.nxv1i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmulsu.nxv2i64.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmulsu_vv_nxv2i64_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv2i64_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmulsu.nxv2i64.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmulsu.mask.nxv2i64.nxv2i32.nxv2i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmulsu_mask_vv_nxv2i64_nxv2i32_nxv2i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv2i64_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmulsu.mask.nxv2i64.nxv2i32.nxv2i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmulsu.nxv4i64.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmulsu_vv_nxv4i64_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv4i64_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmulsu.nxv4i64.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmulsu.mask.nxv4i64.nxv4i32.nxv4i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmulsu_mask_vv_nxv4i64_nxv4i32_nxv4i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv4i64_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmulsu.mask.nxv4i64.nxv4i32.nxv4i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmulsu.nxv8i64.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmulsu_vv_nxv8i64_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vv_nxv8i64_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmulsu.nxv8i64.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmulsu.mask.nxv8i64.nxv8i32.nxv8i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmulsu_mask_vv_nxv8i64_nxv8i32_nxv8i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vv_nxv8i64_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmulsu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmulsu.mask.nxv8i64.nxv8i32.nxv8i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulsu.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmulsu_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulsu.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulsu.mask.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmulsu_mask_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulsu.mask.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulsu.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmulsu_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulsu.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulsu.mask.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmulsu_mask_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulsu.mask.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulsu.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmulsu_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulsu.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulsu.mask.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmulsu_mask_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulsu.mask.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulsu.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmulsu_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulsu.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulsu.mask.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmulsu_mask_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulsu.mask.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulsu.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmulsu_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulsu.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulsu.mask.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmulsu_mask_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulsu.mask.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulsu.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmulsu_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulsu.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulsu.mask.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmulsu_mask_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulsu.mask.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulsu.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmulsu_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulsu.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulsu.mask.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmulsu_mask_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulsu.mask.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulsu.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmulsu_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulsu.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulsu.mask.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmulsu_mask_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulsu.mask.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulsu.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmulsu_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulsu.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulsu.mask.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmulsu_mask_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulsu.mask.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulsu.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmulsu_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulsu.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulsu.mask.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmulsu_mask_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulsu.mask.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulsu.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmulsu_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulsu.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulsu.mask.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmulsu_mask_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulsu.mask.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmulsu.nxv1i64.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  i32,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmulsu_vx_nxv1i64_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv1i64_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmulsu.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmulsu.mask.nxv1i64.nxv1i32.i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmulsu_mask_vx_nxv1i64_nxv1i32_i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv1i64_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmulsu.mask.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmulsu.nxv2i64.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  i32,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmulsu_vx_nxv2i64_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv2i64_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmulsu.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmulsu.mask.nxv2i64.nxv2i32.i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmulsu_mask_vx_nxv2i64_nxv2i32_i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv2i64_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmulsu.mask.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmulsu.nxv4i64.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  i32,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmulsu_vx_nxv4i64_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv4i64_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmulsu.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmulsu.mask.nxv4i64.nxv4i32.i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmulsu_mask_vx_nxv4i64_nxv4i32_i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv4i64_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmulsu.mask.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmulsu.nxv8i64.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  i32,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmulsu_vx_nxv8i64_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_vx_nxv8i64_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmulsu.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmulsu.mask.nxv8i64.nxv8i32.i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmulsu_mask_vx_nxv8i64_nxv8i32_i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulsu_mask_vx_nxv8i64_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmulsu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmulsu.mask.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
diff --git a/test/CodeGen/RISCV/rvv/vwmulu-rv32.ll b/test/CodeGen/RISCV/rvv/vwmulu-rv32.ll
new file mode 100644
index 00000000000..3d8954401e8
--- /dev/null
+++ b/test/CodeGen/RISCV/rvv/vwmulu-rv32.ll
@@ -0,0 +1,881 @@
+; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i16> @llvm.riscv.vwmulu.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmulu_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulu.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulu.mask.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmulu_mask_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulu.mask.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulu.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmulu_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulu.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulu.mask.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmulu_mask_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulu.mask.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulu.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmulu_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulu.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulu.mask.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmulu_mask_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulu.mask.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulu.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmulu_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulu.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulu.mask.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmulu_mask_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulu.mask.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulu.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmulu_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulu.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulu.mask.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmulu_mask_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulu.mask.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulu.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmulu_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulu.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i32 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulu.mask.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmulu_mask_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulu.mask.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulu.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmulu_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulu.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulu.mask.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmulu_mask_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulu.mask.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulu.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmulu_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulu.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulu.mask.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmulu_mask_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulu.mask.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulu.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmulu_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulu.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulu.mask.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmulu_mask_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulu.mask.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulu.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmulu_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulu.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulu.mask.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmulu_mask_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulu.mask.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulu.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmulu_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulu.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulu.mask.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmulu_mask_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulu.mask.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulu.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmulu_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulu.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulu.mask.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i16> @intrinsic_vwmulu_mask_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulu.mask.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulu.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmulu_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulu.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulu.mask.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i16> @intrinsic_vwmulu_mask_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulu.mask.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulu.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmulu_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulu.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulu.mask.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i16> @intrinsic_vwmulu_mask_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulu.mask.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulu.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmulu_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulu.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulu.mask.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i16> @intrinsic_vwmulu_mask_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulu.mask.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulu.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmulu_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulu.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulu.mask.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i16> @intrinsic_vwmulu_mask_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulu.mask.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulu.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmulu_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulu.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i32 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulu.mask.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i32);
+
+define <vscale x 32 x i16> @intrinsic_vwmulu_mask_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulu.mask.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulu.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmulu_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulu.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulu.mask.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i32);
+
+define <vscale x 1 x i32> @intrinsic_vwmulu_mask_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulu.mask.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulu.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmulu_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulu.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulu.mask.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i32);
+
+define <vscale x 2 x i32> @intrinsic_vwmulu_mask_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulu.mask.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulu.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmulu_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulu.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulu.mask.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i32);
+
+define <vscale x 4 x i32> @intrinsic_vwmulu_mask_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulu.mask.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulu.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmulu_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulu.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulu.mask.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i32);
+
+define <vscale x 8 x i32> @intrinsic_vwmulu_mask_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulu.mask.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulu.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmulu_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i32 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulu.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i32 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulu.mask.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i32);
+
+define <vscale x 16 x i32> @intrinsic_vwmulu_mask_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i32 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulu.mask.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i32 %4)
+
+  ret <vscale x 16 x i32> %a
+}
diff --git a/test/CodeGen/RISCV/rvv/vwmulu-rv64.ll b/test/CodeGen/RISCV/rvv/vwmulu-rv64.ll
new file mode 100644
index 00000000000..3d9bff312eb
--- /dev/null
+++ b/test/CodeGen/RISCV/rvv/vwmulu-rv64.ll
@@ -0,0 +1,1201 @@
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   --riscv-no-aliases < %s | FileCheck %s
+declare <vscale x 1 x i16> @llvm.riscv.vwmulu.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmulu_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulu.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulu.mask.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmulu_mask_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv1i16_nxv1i8_nxv1i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulu.mask.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulu.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmulu_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i8> %0, <vscale x 2 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulu.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i8> %0,
+    <vscale x 2 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulu.mask.nxv2i16.nxv2i8.nxv2i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i8>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmulu_mask_vv_nxv2i16_nxv2i8_nxv2i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, <vscale x 2 x i8> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv2i16_nxv2i8_nxv2i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulu.mask.nxv2i16.nxv2i8.nxv2i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    <vscale x 2 x i8> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulu.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmulu_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i8> %0, <vscale x 4 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulu.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i8> %0,
+    <vscale x 4 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulu.mask.nxv4i16.nxv4i8.nxv4i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i8>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmulu_mask_vv_nxv4i16_nxv4i8_nxv4i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv4i16_nxv4i8_nxv4i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulu.mask.nxv4i16.nxv4i8.nxv4i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    <vscale x 4 x i8> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulu.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmulu_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i8> %0, <vscale x 8 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulu.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i8> %0,
+    <vscale x 8 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulu.mask.nxv8i16.nxv8i8.nxv8i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i8>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmulu_mask_vv_nxv8i16_nxv8i8_nxv8i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv8i16_nxv8i8_nxv8i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulu.mask.nxv8i16.nxv8i8.nxv8i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    <vscale x 8 x i8> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulu.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmulu_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i8> %0, <vscale x 16 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulu.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i8> %0,
+    <vscale x 16 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulu.mask.nxv16i16.nxv16i8.nxv16i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i8>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmulu_mask_vv_nxv16i16_nxv16i8_nxv16i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv16i16_nxv16i8_nxv16i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulu.mask.nxv16i16.nxv16i8.nxv16i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    <vscale x 16 x i8> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulu.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmulu_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i8> %0, <vscale x 32 x i8> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulu.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i8> %0,
+    <vscale x 32 x i8> %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulu.mask.nxv32i16.nxv32i8.nxv32i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i8>,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmulu_mask_vv_nxv32i16_nxv32i8_nxv32i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv32i16_nxv32i8_nxv32i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulu.mask.nxv32i16.nxv32i8.nxv32i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    <vscale x 32 x i8> %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulu.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmulu_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i16> %0, <vscale x 1 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulu.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulu.mask.nxv1i32.nxv1i16.nxv1i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i16>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmulu_mask_vv_nxv1i32_nxv1i16_nxv1i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv1i32_nxv1i16_nxv1i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulu.mask.nxv1i32.nxv1i16.nxv1i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    <vscale x 1 x i16> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulu.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmulu_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i16> %0, <vscale x 2 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulu.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulu.mask.nxv2i32.nxv2i16.nxv2i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i16>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmulu_mask_vv_nxv2i32_nxv2i16_nxv2i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv2i32_nxv2i16_nxv2i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulu.mask.nxv2i32.nxv2i16.nxv2i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    <vscale x 2 x i16> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulu.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmulu_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i16> %0, <vscale x 4 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulu.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulu.mask.nxv4i32.nxv4i16.nxv4i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i16>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmulu_mask_vv_nxv4i32_nxv4i16_nxv4i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv4i32_nxv4i16_nxv4i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulu.mask.nxv4i32.nxv4i16.nxv4i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    <vscale x 4 x i16> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulu.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmulu_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i16> %0, <vscale x 8 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulu.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulu.mask.nxv8i32.nxv8i16.nxv8i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i16>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmulu_mask_vv_nxv8i32_nxv8i16_nxv8i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv8i32_nxv8i16_nxv8i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulu.mask.nxv8i32.nxv8i16.nxv8i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    <vscale x 8 x i16> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulu.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmulu_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i16> %0, <vscale x 16 x i16> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulu.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i16> %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulu.mask.nxv16i32.nxv16i16.nxv16i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i16>,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmulu_mask_vv_nxv16i32_nxv16i16_nxv16i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv16i32_nxv16i16_nxv16i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulu.mask.nxv16i32.nxv16i16.nxv16i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    <vscale x 16 x i16> %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmulu.nxv1i64.nxv1i32.nxv1i32(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmulu_vv_nxv1i64_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 1 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv1i64_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmulu.nxv1i64.nxv1i32.nxv1i32(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmulu.mask.nxv1i64.nxv1i32.nxv1i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i32>,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmulu_mask_vv_nxv1i64_nxv1i32_nxv1i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, <vscale x 1 x i32> %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv1i64_nxv1i32_nxv1i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmulu.mask.nxv1i64.nxv1i32.nxv1i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    <vscale x 1 x i32> %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmulu.nxv2i64.nxv2i32.nxv2i32(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmulu_vv_nxv2i64_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 2 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv2i64_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmulu.nxv2i64.nxv2i32.nxv2i32(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmulu.mask.nxv2i64.nxv2i32.nxv2i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i32>,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmulu_mask_vv_nxv2i64_nxv2i32_nxv2i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, <vscale x 2 x i32> %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv2i64_nxv2i32_nxv2i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmulu.mask.nxv2i64.nxv2i32.nxv2i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    <vscale x 2 x i32> %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmulu.nxv4i64.nxv4i32.nxv4i32(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmulu_vv_nxv4i64_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv4i64_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmulu.nxv4i64.nxv4i32.nxv4i32(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmulu.mask.nxv4i64.nxv4i32.nxv4i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i32>,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmulu_mask_vv_nxv4i64_nxv4i32_nxv4i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv4i64_nxv4i32_nxv4i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmulu.mask.nxv4i64.nxv4i32.nxv4i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    <vscale x 4 x i32> %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmulu.nxv8i64.nxv8i32.nxv8i32(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmulu_vv_nxv8i64_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vv_nxv8i64_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmulu.nxv8i64.nxv8i32.nxv8i32(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i32> %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmulu.mask.nxv8i64.nxv8i32.nxv8i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i32>,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmulu_mask_vv_nxv8i64_nxv8i32_nxv8i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vv_nxv8i64_nxv8i32_nxv8i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmulu.vv {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmulu.mask.nxv8i64.nxv8i32.nxv8i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    <vscale x 8 x i32> %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulu.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i8>,
+  i8,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmulu_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulu.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwmulu.mask.nxv1i16.nxv1i8.i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  i8,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i16> @intrinsic_vwmulu_mask_vx_nxv1i16_nxv1i8_i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, i8 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv1i16_nxv1i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf8,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwmulu.mask.nxv1i16.nxv1i8.i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    i8 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulu.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i8>,
+  i8,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmulu_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulu.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 2 x i16> @llvm.riscv.vwmulu.mask.nxv2i16.nxv2i8.i8(
+  <vscale x 2 x i16>,
+  <vscale x 2 x i8>,
+  i8,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i16> @intrinsic_vwmulu_mask_vx_nxv2i16_nxv2i8_i8(<vscale x 2 x i16> %0, <vscale x 2 x i8> %1, i8 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv2i16_nxv2i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i16> @llvm.riscv.vwmulu.mask.nxv2i16.nxv2i8.i8(
+    <vscale x 2 x i16> %0,
+    <vscale x 2 x i8> %1,
+    i8 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulu.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i8>,
+  i8,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmulu_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulu.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 4 x i16> @llvm.riscv.vwmulu.mask.nxv4i16.nxv4i8.i8(
+  <vscale x 4 x i16>,
+  <vscale x 4 x i8>,
+  i8,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i16> @intrinsic_vwmulu_mask_vx_nxv4i16_nxv4i8_i8(<vscale x 4 x i16> %0, <vscale x 4 x i8> %1, i8 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv4i16_nxv4i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i16> @llvm.riscv.vwmulu.mask.nxv4i16.nxv4i8.i8(
+    <vscale x 4 x i16> %0,
+    <vscale x 4 x i8> %1,
+    i8 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulu.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i8>,
+  i8,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmulu_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulu.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 8 x i16> @llvm.riscv.vwmulu.mask.nxv8i16.nxv8i8.i8(
+  <vscale x 8 x i16>,
+  <vscale x 8 x i8>,
+  i8,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i16> @intrinsic_vwmulu_mask_vx_nxv8i16_nxv8i8_i8(<vscale x 8 x i16> %0, <vscale x 8 x i8> %1, i8 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv8i16_nxv8i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i16> @llvm.riscv.vwmulu.mask.nxv8i16.nxv8i8.i8(
+    <vscale x 8 x i16> %0,
+    <vscale x 8 x i8> %1,
+    i8 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulu.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i8>,
+  i8,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmulu_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulu.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 16 x i16> @llvm.riscv.vwmulu.mask.nxv16i16.nxv16i8.i8(
+  <vscale x 16 x i16>,
+  <vscale x 16 x i8>,
+  i8,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i16> @intrinsic_vwmulu_mask_vx_nxv16i16_nxv16i8_i8(<vscale x 16 x i16> %0, <vscale x 16 x i8> %1, i8 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv16i16_nxv16i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i16> @llvm.riscv.vwmulu.mask.nxv16i16.nxv16i8.i8(
+    <vscale x 16 x i16> %0,
+    <vscale x 16 x i8> %1,
+    i8 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulu.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i8>,
+  i8,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmulu_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i8> %0, i8 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulu.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i8> %0,
+    i8 %1,
+    i64 %2)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 32 x i16> @llvm.riscv.vwmulu.mask.nxv32i16.nxv32i8.i8(
+  <vscale x 32 x i16>,
+  <vscale x 32 x i8>,
+  i8,
+  <vscale x 32 x i1>,
+  i64);
+
+define <vscale x 32 x i16> @intrinsic_vwmulu_mask_vx_nxv32i16_nxv32i8_i8(<vscale x 32 x i16> %0, <vscale x 32 x i8> %1, i8 %2, <vscale x 32 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv32i16_nxv32i8_i8
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e8,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 32 x i16> @llvm.riscv.vwmulu.mask.nxv32i16.nxv32i8.i8(
+    <vscale x 32 x i16> %0,
+    <vscale x 32 x i8> %1,
+    i8 %2,
+    <vscale x 32 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 32 x i16> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulu.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i16>,
+  i16,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmulu_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulu.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 1 x i32> @llvm.riscv.vwmulu.mask.nxv1i32.nxv1i16.i16(
+  <vscale x 1 x i32>,
+  <vscale x 1 x i16>,
+  i16,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i32> @intrinsic_vwmulu_mask_vx_nxv1i32_nxv1i16_i16(<vscale x 1 x i32> %0, <vscale x 1 x i16> %1, i16 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv1i32_nxv1i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i32> @llvm.riscv.vwmulu.mask.nxv1i32.nxv1i16.i16(
+    <vscale x 1 x i32> %0,
+    <vscale x 1 x i16> %1,
+    i16 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulu.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i16>,
+  i16,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmulu_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulu.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 2 x i32> @llvm.riscv.vwmulu.mask.nxv2i32.nxv2i16.i16(
+  <vscale x 2 x i32>,
+  <vscale x 2 x i16>,
+  i16,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i32> @intrinsic_vwmulu_mask_vx_nxv2i32_nxv2i16_i16(<vscale x 2 x i32> %0, <vscale x 2 x i16> %1, i16 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv2i32_nxv2i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i32> @llvm.riscv.vwmulu.mask.nxv2i32.nxv2i16.i16(
+    <vscale x 2 x i32> %0,
+    <vscale x 2 x i16> %1,
+    i16 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulu.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i16>,
+  i16,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmulu_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulu.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 4 x i32> @llvm.riscv.vwmulu.mask.nxv4i32.nxv4i16.i16(
+  <vscale x 4 x i32>,
+  <vscale x 4 x i16>,
+  i16,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i32> @intrinsic_vwmulu_mask_vx_nxv4i32_nxv4i16_i16(<vscale x 4 x i32> %0, <vscale x 4 x i16> %1, i16 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv4i32_nxv4i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i32> @llvm.riscv.vwmulu.mask.nxv4i32.nxv4i16.i16(
+    <vscale x 4 x i32> %0,
+    <vscale x 4 x i16> %1,
+    i16 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulu.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i16>,
+  i16,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmulu_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulu.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 8 x i32> @llvm.riscv.vwmulu.mask.nxv8i32.nxv8i16.i16(
+  <vscale x 8 x i32>,
+  <vscale x 8 x i16>,
+  i16,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i32> @intrinsic_vwmulu_mask_vx_nxv8i32_nxv8i16_i16(<vscale x 8 x i32> %0, <vscale x 8 x i16> %1, i16 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv8i32_nxv8i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i32> @llvm.riscv.vwmulu.mask.nxv8i32.nxv8i16.i16(
+    <vscale x 8 x i32> %0,
+    <vscale x 8 x i16> %1,
+    i16 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulu.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i16>,
+  i16,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmulu_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i16> %0, i16 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulu.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i16> %0,
+    i16 %1,
+    i64 %2)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 16 x i32> @llvm.riscv.vwmulu.mask.nxv16i32.nxv16i16.i16(
+  <vscale x 16 x i32>,
+  <vscale x 16 x i16>,
+  i16,
+  <vscale x 16 x i1>,
+  i64);
+
+define <vscale x 16 x i32> @intrinsic_vwmulu_mask_vx_nxv16i32_nxv16i16_i16(<vscale x 16 x i32> %0, <vscale x 16 x i16> %1, i16 %2, <vscale x 16 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv16i32_nxv16i16_i16
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e16,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 16 x i32> @llvm.riscv.vwmulu.mask.nxv16i32.nxv16i16.i16(
+    <vscale x 16 x i32> %0,
+    <vscale x 16 x i16> %1,
+    i16 %2,
+    <vscale x 16 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 16 x i32> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmulu.nxv1i64.nxv1i32.i32(
+  <vscale x 1 x i32>,
+  i32,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmulu_vx_nxv1i64_nxv1i32_i32(<vscale x 1 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv1i64_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmulu.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vwmulu.mask.nxv1i64.nxv1i32.i32(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i32>,
+  i32,
+  <vscale x 1 x i1>,
+  i64);
+
+define <vscale x 1 x i64> @intrinsic_vwmulu_mask_vx_nxv1i64_nxv1i32_i32(<vscale x 1 x i64> %0, <vscale x 1 x i32> %1, i32 %2, <vscale x 1 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv1i64_nxv1i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,mf2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 1 x i64> @llvm.riscv.vwmulu.mask.nxv1i64.nxv1i32.i32(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i32> %1,
+    i32 %2,
+    <vscale x 1 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 1 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmulu.nxv2i64.nxv2i32.i32(
+  <vscale x 2 x i32>,
+  i32,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmulu_vx_nxv2i64_nxv2i32_i32(<vscale x 2 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv2i64_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmulu.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 2 x i64> @llvm.riscv.vwmulu.mask.nxv2i64.nxv2i32.i32(
+  <vscale x 2 x i64>,
+  <vscale x 2 x i32>,
+  i32,
+  <vscale x 2 x i1>,
+  i64);
+
+define <vscale x 2 x i64> @intrinsic_vwmulu_mask_vx_nxv2i64_nxv2i32_i32(<vscale x 2 x i64> %0, <vscale x 2 x i32> %1, i32 %2, <vscale x 2 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv2i64_nxv2i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m1,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 2 x i64> @llvm.riscv.vwmulu.mask.nxv2i64.nxv2i32.i32(
+    <vscale x 2 x i64> %0,
+    <vscale x 2 x i32> %1,
+    i32 %2,
+    <vscale x 2 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 2 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmulu.nxv4i64.nxv4i32.i32(
+  <vscale x 4 x i32>,
+  i32,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmulu_vx_nxv4i64_nxv4i32_i32(<vscale x 4 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv4i64_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmulu.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 4 x i64> @llvm.riscv.vwmulu.mask.nxv4i64.nxv4i32.i32(
+  <vscale x 4 x i64>,
+  <vscale x 4 x i32>,
+  i32,
+  <vscale x 4 x i1>,
+  i64);
+
+define <vscale x 4 x i64> @intrinsic_vwmulu_mask_vx_nxv4i64_nxv4i32_i32(<vscale x 4 x i64> %0, <vscale x 4 x i32> %1, i32 %2, <vscale x 4 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv4i64_nxv4i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m2,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 4 x i64> @llvm.riscv.vwmulu.mask.nxv4i64.nxv4i32.i32(
+    <vscale x 4 x i64> %0,
+    <vscale x 4 x i32> %1,
+    i32 %2,
+    <vscale x 4 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 4 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmulu.nxv8i64.nxv8i32.i32(
+  <vscale x 8 x i32>,
+  i32,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmulu_vx_nxv8i64_nxv8i32_i32(<vscale x 8 x i32> %0, i32 %1, i64 %2) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_vx_nxv8i64_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmulu.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i32> %0,
+    i32 %1,
+    i64 %2)
+
+  ret <vscale x 8 x i64> %a
+}
+
+declare <vscale x 8 x i64> @llvm.riscv.vwmulu.mask.nxv8i64.nxv8i32.i32(
+  <vscale x 8 x i64>,
+  <vscale x 8 x i32>,
+  i32,
+  <vscale x 8 x i1>,
+  i64);
+
+define <vscale x 8 x i64> @intrinsic_vwmulu_mask_vx_nxv8i64_nxv8i32_i32(<vscale x 8 x i64> %0, <vscale x 8 x i32> %1, i32 %2, <vscale x 8 x i1> %3, i64 %4) nounwind {
+entry:
+; CHECK-LABEL: intrinsic_vwmulu_mask_vx_nxv8i64_nxv8i32_i32
+; CHECK:       vsetvli {{.*}}, {{a[0-9]+}}, e32,m4,ta,mu
+; CHECK:       vwmulu.vx {{v[0-9]+}}, {{v[0-9]+}}, {{a[0-9]+}}, v0.t
+  %a = call <vscale x 8 x i64> @llvm.riscv.vwmulu.mask.nxv8i64.nxv8i32.i32(
+    <vscale x 8 x i64> %0,
+    <vscale x 8 x i32> %1,
+    i32 %2,
+    <vscale x 8 x i1> %3,
+    i64 %4)
+
+  ret <vscale x 8 x i64> %a
+}