// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: riscv-registered-target
// RUN: %clang_cc1 -triple riscv32 -target-feature +f -target-feature +d \
// RUN:   -target-feature +v -target-feature +zfh -target-feature +experimental-zvfh \
// RUN:   -disable-O0-optnone -emit-llvm %s -o - | opt -S -mem2reg | FileCheck --check-prefix=CHECK %s
// RUN: %clang_cc1 -triple riscv64 -target-feature +f -target-feature +d \
// RUN:   -target-feature +v -target-feature +zfh -target-feature +experimental-zvfh \
// RUN:   -disable-O0-optnone -emit-llvm %s -o - | opt -S -mem2reg | FileCheck --check-prefix=CHECK %s

#include <riscv_vector.h>

// CHECK-LABEL: @test_vset_v_i8m1_i8m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.nxv8i8(<vscale x 16 x i8> [[DEST:%.*]], <vscale x 8 x i8> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
vint8m2_t test_vset_v_i8m1_i8m2(vint8m2_t dest, vint8m1_t val) {
  return vset_v_i8m1_i8m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i8m1_i8m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.vector.insert.nxv32i8.nxv8i8(<vscale x 32 x i8> [[DEST:%.*]], <vscale x 8 x i8> [[VAL:%.*]], i64 24)
// CHECK-NEXT:    ret <vscale x 32 x i8> [[TMP0]]
//
vint8m4_t test_vset_v_i8m1_i8m4(vint8m4_t dest, vint8m1_t val) {
  return vset_v_i8m1_i8m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_i8m2_i8m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.vector.insert.nxv32i8.nxv16i8(<vscale x 32 x i8> [[DEST:%.*]], <vscale x 16 x i8> [[VAL:%.*]], i64 16)
// CHECK-NEXT:    ret <vscale x 32 x i8> [[TMP0]]
//
vint8m4_t test_vset_v_i8m2_i8m4(vint8m4_t dest, vint8m2_t val) {
  return vset_v_i8m2_i8m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i8m1_i8m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv8i8(<vscale x 64 x i8> [[DEST:%.*]], <vscale x 8 x i8> [[VAL:%.*]], i64 56)
// CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
vint8m8_t test_vset_v_i8m1_i8m8(vint8m8_t dest, vint8m1_t val) {
  return vset_v_i8m1_i8m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_i8m2_i8m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv16i8(<vscale x 64 x i8> [[DEST:%.*]], <vscale x 16 x i8> [[VAL:%.*]], i64 32)
// CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
vint8m8_t test_vset_v_i8m2_i8m8(vint8m8_t dest, vint8m2_t val) {
  return vset_v_i8m2_i8m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_i8m4_i8m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv32i8(<vscale x 64 x i8> [[DEST:%.*]], <vscale x 32 x i8> [[VAL:%.*]], i64 32)
// CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
vint8m8_t test_vset_v_i8m4_i8m8(vint8m8_t dest, vint8m4_t val) {
  return vset_v_i8m4_i8m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i16m1_i16m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.nxv4i16(<vscale x 8 x i16> [[DEST:%.*]], <vscale x 4 x i16> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
vint16m2_t test_vset_v_i16m1_i16m2(vint16m2_t dest, vint16m1_t val) {
  return vset_v_i16m1_i16m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i16m1_i16m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.vector.insert.nxv16i16.nxv4i16(<vscale x 16 x i16> [[DEST:%.*]], <vscale x 4 x i16> [[VAL:%.*]], i64 12)
// CHECK-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
//
vint16m4_t test_vset_v_i16m1_i16m4(vint16m4_t dest, vint16m1_t val) {
  return vset_v_i16m1_i16m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_i16m2_i16m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.vector.insert.nxv16i16.nxv8i16(<vscale x 16 x i16> [[DEST:%.*]], <vscale x 8 x i16> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
//
vint16m4_t test_vset_v_i16m2_i16m4(vint16m4_t dest, vint16m2_t val) {
  return vset_v_i16m2_i16m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i16m1_i16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv4i16(<vscale x 32 x i16> [[DEST:%.*]], <vscale x 4 x i16> [[VAL:%.*]], i64 28)
// CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
vint16m8_t test_vset_v_i16m1_i16m8(vint16m8_t dest, vint16m1_t val) {
  return vset_v_i16m1_i16m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_i16m2_i16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv8i16(<vscale x 32 x i16> [[DEST:%.*]], <vscale x 8 x i16> [[VAL:%.*]], i64 16)
// CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
vint16m8_t test_vset_v_i16m2_i16m8(vint16m8_t dest, vint16m2_t val) {
  return vset_v_i16m2_i16m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_i16m4_i16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv16i16(<vscale x 32 x i16> [[DEST:%.*]], <vscale x 16 x i16> [[VAL:%.*]], i64 16)
// CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
vint16m8_t test_vset_v_i16m4_i16m8(vint16m8_t dest, vint16m4_t val) {
  return vset_v_i16m4_i16m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i32m1_i32m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.nxv2i32(<vscale x 4 x i32> [[DEST:%.*]], <vscale x 2 x i32> [[VAL:%.*]], i64 2)
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
vint32m2_t test_vset_v_i32m1_i32m2(vint32m2_t dest, vint32m1_t val) {
  return vset_v_i32m1_i32m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i32m1_i32m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.vector.insert.nxv8i32.nxv2i32(<vscale x 8 x i32> [[DEST:%.*]], <vscale x 2 x i32> [[VAL:%.*]], i64 6)
// CHECK-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
//
vint32m4_t test_vset_v_i32m1_i32m4(vint32m4_t dest, vint32m1_t val) {
  return vset_v_i32m1_i32m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_i32m2_i32m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.vector.insert.nxv8i32.nxv4i32(<vscale x 8 x i32> [[DEST:%.*]], <vscale x 4 x i32> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
//
vint32m4_t test_vset_v_i32m2_i32m4(vint32m4_t dest, vint32m2_t val) {
  return vset_v_i32m2_i32m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i32m1_i32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv2i32(<vscale x 16 x i32> [[DEST:%.*]], <vscale x 2 x i32> [[VAL:%.*]], i64 14)
// CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
vint32m8_t test_vset_v_i32m1_i32m8(vint32m8_t dest, vint32m1_t val) {
  return vset_v_i32m1_i32m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_i32m2_i32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> [[DEST:%.*]], <vscale x 4 x i32> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
vint32m8_t test_vset_v_i32m2_i32m8(vint32m8_t dest, vint32m2_t val) {
  return vset_v_i32m2_i32m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_i32m4_i32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv8i32(<vscale x 16 x i32> [[DEST:%.*]], <vscale x 8 x i32> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
vint32m8_t test_vset_v_i32m4_i32m8(vint32m8_t dest, vint32m4_t val) {
  return vset_v_i32m4_i32m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i64m1_i64m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.nxv1i64(<vscale x 2 x i64> [[DEST:%.*]], <vscale x 1 x i64> [[VAL:%.*]], i64 1)
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
vint64m2_t test_vset_v_i64m1_i64m2(vint64m2_t dest, vint64m1_t val) {
  return vset_v_i64m1_i64m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i64m1_i64m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.vector.insert.nxv4i64.nxv1i64(<vscale x 4 x i64> [[DEST:%.*]], <vscale x 1 x i64> [[VAL:%.*]], i64 3)
// CHECK-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
//
vint64m4_t test_vset_v_i64m1_i64m4(vint64m4_t dest, vint64m1_t val) {
  return vset_v_i64m1_i64m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_i64m2_i64m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.vector.insert.nxv4i64.nxv2i64(<vscale x 4 x i64> [[DEST:%.*]], <vscale x 2 x i64> [[VAL:%.*]], i64 2)
// CHECK-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
//
vint64m4_t test_vset_v_i64m2_i64m4(vint64m4_t dest, vint64m2_t val) {
  return vset_v_i64m2_i64m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_i64m1_i64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv1i64(<vscale x 8 x i64> [[DEST:%.*]], <vscale x 1 x i64> [[VAL:%.*]], i64 7)
// CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
vint64m8_t test_vset_v_i64m1_i64m8(vint64m8_t dest, vint64m1_t val) {
  return vset_v_i64m1_i64m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_i64m2_i64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv2i64(<vscale x 8 x i64> [[DEST:%.*]], <vscale x 2 x i64> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
vint64m8_t test_vset_v_i64m2_i64m8(vint64m8_t dest, vint64m2_t val) {
  return vset_v_i64m2_i64m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_i64m4_i64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv4i64(<vscale x 8 x i64> [[DEST:%.*]], <vscale x 4 x i64> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
vint64m8_t test_vset_v_i64m4_i64m8(vint64m8_t dest, vint64m4_t val) {
  return vset_v_i64m4_i64m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u8m1_u8m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.nxv8i8(<vscale x 16 x i8> [[DEST:%.*]], <vscale x 8 x i8> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
vuint8m2_t test_vset_v_u8m1_u8m2(vuint8m2_t dest, vuint8m1_t val) {
  return vset_v_u8m1_u8m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u8m1_u8m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.vector.insert.nxv32i8.nxv8i8(<vscale x 32 x i8> [[DEST:%.*]], <vscale x 8 x i8> [[VAL:%.*]], i64 24)
// CHECK-NEXT:    ret <vscale x 32 x i8> [[TMP0]]
//
vuint8m4_t test_vset_v_u8m1_u8m4(vuint8m4_t dest, vuint8m1_t val) {
  return vset_v_u8m1_u8m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_u8m2_u8m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.vector.insert.nxv32i8.nxv16i8(<vscale x 32 x i8> [[DEST:%.*]], <vscale x 16 x i8> [[VAL:%.*]], i64 16)
// CHECK-NEXT:    ret <vscale x 32 x i8> [[TMP0]]
//
vuint8m4_t test_vset_v_u8m2_u8m4(vuint8m4_t dest, vuint8m2_t val) {
  return vset_v_u8m2_u8m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u8m1_u8m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv8i8(<vscale x 64 x i8> [[DEST:%.*]], <vscale x 8 x i8> [[VAL:%.*]], i64 56)
// CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
vuint8m8_t test_vset_v_u8m1_u8m8(vuint8m8_t dest, vuint8m1_t val) {
  return vset_v_u8m1_u8m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_u8m2_u8m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv16i8(<vscale x 64 x i8> [[DEST:%.*]], <vscale x 16 x i8> [[VAL:%.*]], i64 32)
// CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
vuint8m8_t test_vset_v_u8m2_u8m8(vuint8m8_t dest, vuint8m2_t val) {
  return vset_v_u8m2_u8m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_u8m4_u8m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv32i8(<vscale x 64 x i8> [[DEST:%.*]], <vscale x 32 x i8> [[VAL:%.*]], i64 32)
// CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
vuint8m8_t test_vset_v_u8m4_u8m8(vuint8m8_t dest, vuint8m4_t val) {
  return vset_v_u8m4_u8m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u16m1_u16m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.nxv4i16(<vscale x 8 x i16> [[DEST:%.*]], <vscale x 4 x i16> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
vuint16m2_t test_vset_v_u16m1_u16m2(vuint16m2_t dest, vuint16m1_t val) {
  return vset_v_u16m1_u16m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u16m1_u16m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.vector.insert.nxv16i16.nxv4i16(<vscale x 16 x i16> [[DEST:%.*]], <vscale x 4 x i16> [[VAL:%.*]], i64 12)
// CHECK-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
//
vuint16m4_t test_vset_v_u16m1_u16m4(vuint16m4_t dest, vuint16m1_t val) {
  return vset_v_u16m1_u16m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_u16m2_u16m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.vector.insert.nxv16i16.nxv8i16(<vscale x 16 x i16> [[DEST:%.*]], <vscale x 8 x i16> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
//
vuint16m4_t test_vset_v_u16m2_u16m4(vuint16m4_t dest, vuint16m2_t val) {
  return vset_v_u16m2_u16m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u16m1_u16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv4i16(<vscale x 32 x i16> [[DEST:%.*]], <vscale x 4 x i16> [[VAL:%.*]], i64 28)
// CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
vuint16m8_t test_vset_v_u16m1_u16m8(vuint16m8_t dest, vuint16m1_t val) {
  return vset_v_u16m1_u16m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_u16m2_u16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv8i16(<vscale x 32 x i16> [[DEST:%.*]], <vscale x 8 x i16> [[VAL:%.*]], i64 16)
// CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
vuint16m8_t test_vset_v_u16m2_u16m8(vuint16m8_t dest, vuint16m2_t val) {
  return vset_v_u16m2_u16m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_u16m4_u16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv16i16(<vscale x 32 x i16> [[DEST:%.*]], <vscale x 16 x i16> [[VAL:%.*]], i64 16)
// CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
vuint16m8_t test_vset_v_u16m4_u16m8(vuint16m8_t dest, vuint16m4_t val) {
  return vset_v_u16m4_u16m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u32m1_u32m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.nxv2i32(<vscale x 4 x i32> [[DEST:%.*]], <vscale x 2 x i32> [[VAL:%.*]], i64 2)
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
vuint32m2_t test_vset_v_u32m1_u32m2(vuint32m2_t dest, vuint32m1_t val) {
  return vset_v_u32m1_u32m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u32m1_u32m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.vector.insert.nxv8i32.nxv2i32(<vscale x 8 x i32> [[DEST:%.*]], <vscale x 2 x i32> [[VAL:%.*]], i64 6)
// CHECK-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
//
vuint32m4_t test_vset_v_u32m1_u32m4(vuint32m4_t dest, vuint32m1_t val) {
  return vset_v_u32m1_u32m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_u32m2_u32m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.vector.insert.nxv8i32.nxv4i32(<vscale x 8 x i32> [[DEST:%.*]], <vscale x 4 x i32> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
//
vuint32m4_t test_vset_v_u32m2_u32m4(vuint32m4_t dest, vuint32m2_t val) {
  return vset_v_u32m2_u32m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u32m1_u32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv2i32(<vscale x 16 x i32> [[DEST:%.*]], <vscale x 2 x i32> [[VAL:%.*]], i64 14)
// CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
vuint32m8_t test_vset_v_u32m1_u32m8(vuint32m8_t dest, vuint32m1_t val) {
  return vset_v_u32m1_u32m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_u32m2_u32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> [[DEST:%.*]], <vscale x 4 x i32> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
vuint32m8_t test_vset_v_u32m2_u32m8(vuint32m8_t dest, vuint32m2_t val) {
  return vset_v_u32m2_u32m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_u32m4_u32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv8i32(<vscale x 16 x i32> [[DEST:%.*]], <vscale x 8 x i32> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
vuint32m8_t test_vset_v_u32m4_u32m8(vuint32m8_t dest, vuint32m4_t val) {
  return vset_v_u32m4_u32m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u64m1_u64m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.nxv1i64(<vscale x 2 x i64> [[DEST:%.*]], <vscale x 1 x i64> [[VAL:%.*]], i64 1)
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
vuint64m2_t test_vset_v_u64m1_u64m2(vuint64m2_t dest, vuint64m1_t val) {
  return vset_v_u64m1_u64m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u64m1_u64m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.vector.insert.nxv4i64.nxv1i64(<vscale x 4 x i64> [[DEST:%.*]], <vscale x 1 x i64> [[VAL:%.*]], i64 3)
// CHECK-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
//
vuint64m4_t test_vset_v_u64m1_u64m4(vuint64m4_t dest, vuint64m1_t val) {
  return vset_v_u64m1_u64m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_u64m2_u64m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.vector.insert.nxv4i64.nxv2i64(<vscale x 4 x i64> [[DEST:%.*]], <vscale x 2 x i64> [[VAL:%.*]], i64 2)
// CHECK-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
//
vuint64m4_t test_vset_v_u64m2_u64m4(vuint64m4_t dest, vuint64m2_t val) {
  return vset_v_u64m2_u64m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_u64m1_u64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv1i64(<vscale x 8 x i64> [[DEST:%.*]], <vscale x 1 x i64> [[VAL:%.*]], i64 7)
// CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
vuint64m8_t test_vset_v_u64m1_u64m8(vuint64m8_t dest, vuint64m1_t val) {
  return vset_v_u64m1_u64m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_u64m2_u64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv2i64(<vscale x 8 x i64> [[DEST:%.*]], <vscale x 2 x i64> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
vuint64m8_t test_vset_v_u64m2_u64m8(vuint64m8_t dest, vuint64m2_t val) {
  return vset_v_u64m2_u64m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_u64m4_u64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv4i64(<vscale x 8 x i64> [[DEST:%.*]], <vscale x 4 x i64> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
vuint64m8_t test_vset_v_u64m4_u64m8(vuint64m8_t dest, vuint64m4_t val) {
  return vset_v_u64m4_u64m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_f32m1_f32m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> [[DEST:%.*]], <vscale x 2 x float> [[VAL:%.*]], i64 2)
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
vfloat32m2_t test_vset_v_f32m1_f32m2(vfloat32m2_t dest, vfloat32m1_t val) {
  return vset_v_f32m1_f32m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_f32m1_f32m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x float> @llvm.vector.insert.nxv8f32.nxv2f32(<vscale x 8 x float> [[DEST:%.*]], <vscale x 2 x float> [[VAL:%.*]], i64 6)
// CHECK-NEXT:    ret <vscale x 8 x float> [[TMP0]]
//
vfloat32m4_t test_vset_v_f32m1_f32m4(vfloat32m4_t dest, vfloat32m1_t val) {
  return vset_v_f32m1_f32m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_f32m2_f32m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x float> @llvm.vector.insert.nxv8f32.nxv4f32(<vscale x 8 x float> [[DEST:%.*]], <vscale x 4 x float> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x float> [[TMP0]]
//
vfloat32m4_t test_vset_v_f32m2_f32m4(vfloat32m4_t dest, vfloat32m2_t val) {
  return vset_v_f32m2_f32m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_f32m1_f32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x float> @llvm.vector.insert.nxv16f32.nxv2f32(<vscale x 16 x float> [[DEST:%.*]], <vscale x 2 x float> [[VAL:%.*]], i64 14)
// CHECK-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
vfloat32m8_t test_vset_v_f32m1_f32m8(vfloat32m8_t dest, vfloat32m1_t val) {
  return vset_v_f32m1_f32m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_f32m2_f32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x float> @llvm.vector.insert.nxv16f32.nxv4f32(<vscale x 16 x float> [[DEST:%.*]], <vscale x 4 x float> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
vfloat32m8_t test_vset_v_f32m2_f32m8(vfloat32m8_t dest, vfloat32m2_t val) {
  return vset_v_f32m2_f32m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_f32m4_f32m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x float> @llvm.vector.insert.nxv16f32.nxv8f32(<vscale x 16 x float> [[DEST:%.*]], <vscale x 8 x float> [[VAL:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
vfloat32m8_t test_vset_v_f32m4_f32m8(vfloat32m8_t dest, vfloat32m4_t val) {
  return vset_v_f32m4_f32m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_f64m1_f64m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x double> @llvm.vector.insert.nxv2f64.nxv1f64(<vscale x 2 x double> [[DEST:%.*]], <vscale x 1 x double> [[VAL:%.*]], i64 1)
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
//
vfloat64m2_t test_vset_v_f64m1_f64m2(vfloat64m2_t dest, vfloat64m1_t val) {
  return vset_v_f64m1_f64m2(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_f64m1_f64m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x double> @llvm.vector.insert.nxv4f64.nxv1f64(<vscale x 4 x double> [[DEST:%.*]], <vscale x 1 x double> [[VAL:%.*]], i64 3)
// CHECK-NEXT:    ret <vscale x 4 x double> [[TMP0]]
//
vfloat64m4_t test_vset_v_f64m1_f64m4(vfloat64m4_t dest, vfloat64m1_t val) {
  return vset_v_f64m1_f64m4(dest, 3, val);
}

// CHECK-LABEL: @test_vset_v_f64m2_f64m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x double> @llvm.vector.insert.nxv4f64.nxv2f64(<vscale x 4 x double> [[DEST:%.*]], <vscale x 2 x double> [[VAL:%.*]], i64 2)
// CHECK-NEXT:    ret <vscale x 4 x double> [[TMP0]]
//
vfloat64m4_t test_vset_v_f64m2_f64m4(vfloat64m4_t dest, vfloat64m2_t val) {
  return vset_v_f64m2_f64m4(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_f64m1_f64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nxv1f64(<vscale x 8 x double> [[DEST:%.*]], <vscale x 1 x double> [[VAL:%.*]], i64 7)
// CHECK-NEXT:    ret <vscale x 8 x double> [[TMP0]]
//
vfloat64m8_t test_vset_v_f64m1_f64m8(vfloat64m8_t dest, vfloat64m1_t val) {
  return vset_v_f64m1_f64m8(dest, 7, val);
}

// CHECK-LABEL: @test_vset_v_f64m2_f64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nxv2f64(<vscale x 8 x double> [[DEST:%.*]], <vscale x 2 x double> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x double> [[TMP0]]
//
vfloat64m8_t test_vset_v_f64m2_f64m8(vfloat64m8_t dest, vfloat64m2_t val) {
  return vset_v_f64m2_f64m8(dest, 2, val);
}

// CHECK-LABEL: @test_vset_v_f64m4_f64m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nxv4f64(<vscale x 8 x double> [[DEST:%.*]], <vscale x 4 x double> [[VAL:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 8 x double> [[TMP0]]
//
vfloat64m8_t test_vset_v_f64m4_f64m8(vfloat64m8_t dest, vfloat64m4_t val) {
  return vset_v_f64m4_f64m8(dest, 1, val);
}

// CHECK-LABEL: @test_vset_v_f16m1_f16m2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x half> @llvm.vector.insert.nxv8f16.nxv4f16(<vscale x 8 x half> [[DEST:%.*]], <vscale x 4 x half> [[VAL:%.*]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
vfloat16m2_t test_vset_v_f16m1_f16m2 (vfloat16m2_t dest, vfloat16m1_t val) {
  return vset_v_f16m1_f16m2(dest, 0, val);
}

// CHECK-LABEL: @test_vset_v_f16m1_f16m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x half> @llvm.vector.insert.nxv16f16.nxv4f16(<vscale x 16 x half> [[DEST:%.*]], <vscale x 4 x half> [[VAL:%.*]], i64 0)
// CHECK-NEXT:    ret <vscale x 16 x half> [[TMP0]]
//
vfloat16m4_t test_vset_v_f16m1_f16m4 (vfloat16m4_t dest, vfloat16m1_t val) {
  return vset_v_f16m1_f16m4(dest, 0, val);
}

// CHECK-LABEL: @test_vset_v_f16m2_f16m4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x half> @llvm.vector.insert.nxv16f16.nxv8f16(<vscale x 16 x half> [[DEST:%.*]], <vscale x 8 x half> [[VAL:%.*]], i64 0)
// CHECK-NEXT:    ret <vscale x 16 x half> [[TMP0]]
//
vfloat16m4_t test_vset_v_f16m2_f16m4 (vfloat16m4_t dest, vfloat16m2_t val) {
  return vset_v_f16m2_f16m4(dest, 0, val);
}

// CHECK-LABEL: @test_vset_v_f16m1_f16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x half> @llvm.vector.insert.nxv32f16.nxv4f16(<vscale x 32 x half> [[DEST:%.*]], <vscale x 4 x half> [[VAL:%.*]], i64 0)
// CHECK-NEXT:    ret <vscale x 32 x half> [[TMP0]]
//
vfloat16m8_t test_vset_v_f16m1_f16m8 (vfloat16m8_t dest, vfloat16m1_t val) {
  return vset_v_f16m1_f16m8(dest, 0, val);
}

// CHECK-LABEL: @test_vset_v_f16m2_f16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x half> @llvm.vector.insert.nxv32f16.nxv8f16(<vscale x 32 x half> [[DEST:%.*]], <vscale x 8 x half> [[VAL:%.*]], i64 0)
// CHECK-NEXT:    ret <vscale x 32 x half> [[TMP0]]
//
vfloat16m8_t test_vset_v_f16m2_f16m8 (vfloat16m8_t dest, vfloat16m2_t val) {
  return vset_v_f16m2_f16m8(dest, 0, val);
}

// CHECK-LABEL: @test_vset_v_f16m4_f16m8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x half> @llvm.vector.insert.nxv32f16.nxv16f16(<vscale x 32 x half> [[DEST:%.*]], <vscale x 16 x half> [[VAL:%.*]], i64 0)
// CHECK-NEXT:    ret <vscale x 32 x half> [[TMP0]]
//
vfloat16m8_t test_vset_v_f16m4_f16m8 (vfloat16m8_t dest, vfloat16m4_t val) {
  return vset_v_f16m4_f16m8(dest, 0, val);
}