// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 4
// REQUIRES: riscv-registered-target
// RUN: %clang_cc1 -triple riscv64 -target-feature +zve64x \
// RUN:   -target-feature +zvfbfmin -disable-O0-optnone \
// RUN:   -emit-llvm %s -o - | opt -S -passes=mem2reg | \
// RUN:   FileCheck --check-prefix=CHECK-RV64 %s

#include <riscv_vector.h>

// CHECK-RV64-LABEL: define dso_local <vscale x 1 x float> @test_vfwcvtbf16_f_f_v_f32mf2_tu(
// CHECK-RV64-SAME: <vscale x 1 x float> [[VD:%.*]], <vscale x 1 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x float> @llvm.riscv.vfwcvtbf16.f.f.v.nxv1f32.nxv1bf16.i64(<vscale x 1 x float> [[VD]], <vscale x 1 x bfloat> [[VS2]], i64 [[VL]])
// CHECK-RV64-NEXT:    ret <vscale x 1 x float> [[TMP0]]
//
vfloat32mf2_t test_vfwcvtbf16_f_f_v_f32mf2_tu(vfloat32mf2_t vd,
                                              vbfloat16mf4_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tu(vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 2 x float> @test_vfwcvtbf16_f_f_v_f32m1_tu(
// CHECK-RV64-SAME: <vscale x 2 x float> [[VD:%.*]], <vscale x 2 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x float> @llvm.riscv.vfwcvtbf16.f.f.v.nxv2f32.nxv2bf16.i64(<vscale x 2 x float> [[VD]], <vscale x 2 x bfloat> [[VS2]], i64 [[VL]])
// CHECK-RV64-NEXT:    ret <vscale x 2 x float> [[TMP0]]
//
vfloat32m1_t test_vfwcvtbf16_f_f_v_f32m1_tu(vfloat32m1_t vd, vbfloat16mf2_t vs2,
                                            size_t vl) {
  return __riscv_vfwcvtbf16_f_tu(vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 4 x float> @test_vfwcvtbf16_f_f_v_f32m2_tu(
// CHECK-RV64-SAME: <vscale x 4 x float> [[VD:%.*]], <vscale x 4 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.riscv.vfwcvtbf16.f.f.v.nxv4f32.nxv4bf16.i64(<vscale x 4 x float> [[VD]], <vscale x 4 x bfloat> [[VS2]], i64 [[VL]])
// CHECK-RV64-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
vfloat32m2_t test_vfwcvtbf16_f_f_v_f32m2_tu(vfloat32m2_t vd, vbfloat16m1_t vs2,
                                            size_t vl) {
  return __riscv_vfwcvtbf16_f_tu(vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 8 x float> @test_vfwcvtbf16_f_f_v_f32m4_tu(
// CHECK-RV64-SAME: <vscale x 8 x float> [[VD:%.*]], <vscale x 8 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x float> @llvm.riscv.vfwcvtbf16.f.f.v.nxv8f32.nxv8bf16.i64(<vscale x 8 x float> [[VD]], <vscale x 8 x bfloat> [[VS2]], i64 [[VL]])
// CHECK-RV64-NEXT:    ret <vscale x 8 x float> [[TMP0]]
//
vfloat32m4_t test_vfwcvtbf16_f_f_v_f32m4_tu(vfloat32m4_t vd, vbfloat16m2_t vs2,
                                            size_t vl) {
  return __riscv_vfwcvtbf16_f_tu(vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 16 x float> @test_vfwcvtbf16_f_f_v_f32m8_tu(
// CHECK-RV64-SAME: <vscale x 16 x float> [[VD:%.*]], <vscale x 16 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x float> @llvm.riscv.vfwcvtbf16.f.f.v.nxv16f32.nxv16bf16.i64(<vscale x 16 x float> [[VD]], <vscale x 16 x bfloat> [[VS2]], i64 [[VL]])
// CHECK-RV64-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
vfloat32m8_t test_vfwcvtbf16_f_f_v_f32m8_tu(vfloat32m8_t vd, vbfloat16m4_t vs2,
                                            size_t vl) {
  return __riscv_vfwcvtbf16_f_tu(vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 1 x float> @test_vfwcvtbf16_f_f_v_f32mf2_tum(
// CHECK-RV64-SAME: <vscale x 1 x i1> [[VM:%.*]], <vscale x 1 x float> [[VD:%.*]], <vscale x 1 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv1f32.nxv1bf16.i64(<vscale x 1 x float> [[VD]], <vscale x 1 x bfloat> [[VS2]], <vscale x 1 x i1> [[VM]], i64 [[VL]], i64 2)
// CHECK-RV64-NEXT:    ret <vscale x 1 x float> [[TMP0]]
//
vfloat32mf2_t test_vfwcvtbf16_f_f_v_f32mf2_tum(vbool64_t vm, vfloat32mf2_t vd,
                                               vbfloat16mf4_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tum(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 2 x float> @test_vfwcvtbf16_f_f_v_f32m1_tum(
// CHECK-RV64-SAME: <vscale x 2 x i1> [[VM:%.*]], <vscale x 2 x float> [[VD:%.*]], <vscale x 2 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv2f32.nxv2bf16.i64(<vscale x 2 x float> [[VD]], <vscale x 2 x bfloat> [[VS2]], <vscale x 2 x i1> [[VM]], i64 [[VL]], i64 2)
// CHECK-RV64-NEXT:    ret <vscale x 2 x float> [[TMP0]]
//
vfloat32m1_t test_vfwcvtbf16_f_f_v_f32m1_tum(vbool32_t vm, vfloat32m1_t vd,
                                             vbfloat16mf2_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tum(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 4 x float> @test_vfwcvtbf16_f_f_v_f32m2_tum(
// CHECK-RV64-SAME: <vscale x 4 x i1> [[VM:%.*]], <vscale x 4 x float> [[VD:%.*]], <vscale x 4 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv4f32.nxv4bf16.i64(<vscale x 4 x float> [[VD]], <vscale x 4 x bfloat> [[VS2]], <vscale x 4 x i1> [[VM]], i64 [[VL]], i64 2)
// CHECK-RV64-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
vfloat32m2_t test_vfwcvtbf16_f_f_v_f32m2_tum(vbool16_t vm, vfloat32m2_t vd,
                                             vbfloat16m1_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tum(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 8 x float> @test_vfwcvtbf16_f_f_v_f32m4_tum(
// CHECK-RV64-SAME: <vscale x 8 x i1> [[VM:%.*]], <vscale x 8 x float> [[VD:%.*]], <vscale x 8 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv8f32.nxv8bf16.i64(<vscale x 8 x float> [[VD]], <vscale x 8 x bfloat> [[VS2]], <vscale x 8 x i1> [[VM]], i64 [[VL]], i64 2)
// CHECK-RV64-NEXT:    ret <vscale x 8 x float> [[TMP0]]
//
vfloat32m4_t test_vfwcvtbf16_f_f_v_f32m4_tum(vbool8_t vm, vfloat32m4_t vd,
                                             vbfloat16m2_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tum(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 16 x float> @test_vfwcvtbf16_f_f_v_f32m8_tum(
// CHECK-RV64-SAME: <vscale x 16 x i1> [[VM:%.*]], <vscale x 16 x float> [[VD:%.*]], <vscale x 16 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv16f32.nxv16bf16.i64(<vscale x 16 x float> [[VD]], <vscale x 16 x bfloat> [[VS2]], <vscale x 16 x i1> [[VM]], i64 [[VL]], i64 2)
// CHECK-RV64-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
vfloat32m8_t test_vfwcvtbf16_f_f_v_f32m8_tum(vbool4_t vm, vfloat32m8_t vd,
                                             vbfloat16m4_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tum(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 1 x float> @test_vfwcvtbf16_f_f_v_f32mf2_tumu(
// CHECK-RV64-SAME: <vscale x 1 x i1> [[VM:%.*]], <vscale x 1 x float> [[VD:%.*]], <vscale x 1 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv1f32.nxv1bf16.i64(<vscale x 1 x float> [[VD]], <vscale x 1 x bfloat> [[VS2]], <vscale x 1 x i1> [[VM]], i64 [[VL]], i64 0)
// CHECK-RV64-NEXT:    ret <vscale x 1 x float> [[TMP0]]
//
vfloat32mf2_t test_vfwcvtbf16_f_f_v_f32mf2_tumu(vbool64_t vm, vfloat32mf2_t vd,
                                                vbfloat16mf4_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tumu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 2 x float> @test_vfwcvtbf16_f_f_v_f32m1_tumu(
// CHECK-RV64-SAME: <vscale x 2 x i1> [[VM:%.*]], <vscale x 2 x float> [[VD:%.*]], <vscale x 2 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv2f32.nxv2bf16.i64(<vscale x 2 x float> [[VD]], <vscale x 2 x bfloat> [[VS2]], <vscale x 2 x i1> [[VM]], i64 [[VL]], i64 0)
// CHECK-RV64-NEXT:    ret <vscale x 2 x float> [[TMP0]]
//
vfloat32m1_t test_vfwcvtbf16_f_f_v_f32m1_tumu(vbool32_t vm, vfloat32m1_t vd,
                                              vbfloat16mf2_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tumu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 4 x float> @test_vfwcvtbf16_f_f_v_f32m2_tumu(
// CHECK-RV64-SAME: <vscale x 4 x i1> [[VM:%.*]], <vscale x 4 x float> [[VD:%.*]], <vscale x 4 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv4f32.nxv4bf16.i64(<vscale x 4 x float> [[VD]], <vscale x 4 x bfloat> [[VS2]], <vscale x 4 x i1> [[VM]], i64 [[VL]], i64 0)
// CHECK-RV64-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
vfloat32m2_t test_vfwcvtbf16_f_f_v_f32m2_tumu(vbool16_t vm, vfloat32m2_t vd,
                                              vbfloat16m1_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tumu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 8 x float> @test_vfwcvtbf16_f_f_v_f32m4_tumu(
// CHECK-RV64-SAME: <vscale x 8 x i1> [[VM:%.*]], <vscale x 8 x float> [[VD:%.*]], <vscale x 8 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv8f32.nxv8bf16.i64(<vscale x 8 x float> [[VD]], <vscale x 8 x bfloat> [[VS2]], <vscale x 8 x i1> [[VM]], i64 [[VL]], i64 0)
// CHECK-RV64-NEXT:    ret <vscale x 8 x float> [[TMP0]]
//
vfloat32m4_t test_vfwcvtbf16_f_f_v_f32m4_tumu(vbool8_t vm, vfloat32m4_t vd,
                                              vbfloat16m2_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tumu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 16 x float> @test_vfwcvtbf16_f_f_v_f32m8_tumu(
// CHECK-RV64-SAME: <vscale x 16 x i1> [[VM:%.*]], <vscale x 16 x float> [[VD:%.*]], <vscale x 16 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv16f32.nxv16bf16.i64(<vscale x 16 x float> [[VD]], <vscale x 16 x bfloat> [[VS2]], <vscale x 16 x i1> [[VM]], i64 [[VL]], i64 0)
// CHECK-RV64-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
vfloat32m8_t test_vfwcvtbf16_f_f_v_f32m8_tumu(vbool4_t vm, vfloat32m8_t vd,
                                              vbfloat16m4_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_tumu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 1 x float> @test_vfwcvtbf16_f_f_v_f32mf2_mu(
// CHECK-RV64-SAME: <vscale x 1 x i1> [[VM:%.*]], <vscale x 1 x float> [[VD:%.*]], <vscale x 1 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv1f32.nxv1bf16.i64(<vscale x 1 x float> [[VD]], <vscale x 1 x bfloat> [[VS2]], <vscale x 1 x i1> [[VM]], i64 [[VL]], i64 1)
// CHECK-RV64-NEXT:    ret <vscale x 1 x float> [[TMP0]]
//
vfloat32mf2_t test_vfwcvtbf16_f_f_v_f32mf2_mu(vbool64_t vm, vfloat32mf2_t vd,
                                              vbfloat16mf4_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_mu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 2 x float> @test_vfwcvtbf16_f_f_v_f32m1_mu(
// CHECK-RV64-SAME: <vscale x 2 x i1> [[VM:%.*]], <vscale x 2 x float> [[VD:%.*]], <vscale x 2 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv2f32.nxv2bf16.i64(<vscale x 2 x float> [[VD]], <vscale x 2 x bfloat> [[VS2]], <vscale x 2 x i1> [[VM]], i64 [[VL]], i64 1)
// CHECK-RV64-NEXT:    ret <vscale x 2 x float> [[TMP0]]
//
vfloat32m1_t test_vfwcvtbf16_f_f_v_f32m1_mu(vbool32_t vm, vfloat32m1_t vd,
                                            vbfloat16mf2_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_mu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 4 x float> @test_vfwcvtbf16_f_f_v_f32m2_mu(
// CHECK-RV64-SAME: <vscale x 4 x i1> [[VM:%.*]], <vscale x 4 x float> [[VD:%.*]], <vscale x 4 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv4f32.nxv4bf16.i64(<vscale x 4 x float> [[VD]], <vscale x 4 x bfloat> [[VS2]], <vscale x 4 x i1> [[VM]], i64 [[VL]], i64 1)
// CHECK-RV64-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
vfloat32m2_t test_vfwcvtbf16_f_f_v_f32m2_mu(vbool16_t vm, vfloat32m2_t vd,
                                            vbfloat16m1_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_mu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 8 x float> @test_vfwcvtbf16_f_f_v_f32m4_mu(
// CHECK-RV64-SAME: <vscale x 8 x i1> [[VM:%.*]], <vscale x 8 x float> [[VD:%.*]], <vscale x 8 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv8f32.nxv8bf16.i64(<vscale x 8 x float> [[VD]], <vscale x 8 x bfloat> [[VS2]], <vscale x 8 x i1> [[VM]], i64 [[VL]], i64 1)
// CHECK-RV64-NEXT:    ret <vscale x 8 x float> [[TMP0]]
//
vfloat32m4_t test_vfwcvtbf16_f_f_v_f32m4_mu(vbool8_t vm, vfloat32m4_t vd,
                                            vbfloat16m2_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_mu(vm, vd, vs2, vl);
}

// CHECK-RV64-LABEL: define dso_local <vscale x 16 x float> @test_vfwcvtbf16_f_f_v_f32m8_mu(
// CHECK-RV64-SAME: <vscale x 16 x i1> [[VM:%.*]], <vscale x 16 x float> [[VD:%.*]], <vscale x 16 x bfloat> [[VS2:%.*]], i64 noundef [[VL:%.*]]) #[[ATTR0]] {
// CHECK-RV64-NEXT:  entry:
// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x float> @llvm.riscv.vfwcvtbf16.f.f.v.mask.nxv16f32.nxv16bf16.i64(<vscale x 16 x float> [[VD]], <vscale x 16 x bfloat> [[VS2]], <vscale x 16 x i1> [[VM]], i64 [[VL]], i64 1)
// CHECK-RV64-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
vfloat32m8_t test_vfwcvtbf16_f_f_v_f32m8_mu(vbool4_t vm, vfloat32m8_t vd,
                                            vbfloat16m4_t vs2, size_t vl) {
  return __riscv_vfwcvtbf16_f_mu(vm, vd, vs2, vl);
}