// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature
// RUN: %clang_cc1 -triple thumbv7-none-linux-gnueabihf \
// RUN:   -target-abi aapcs \
// RUN:   -target-cpu cortex-a7 \
// RUN:   -mfloat-abi hard \
// RUN:   -ffreestanding \
// RUN:   -disable-O0-optnone -emit-llvm -o - %s | opt -S -passes=mem2reg | FileCheck %s

// REQUIRES: aarch64-registered-target || arm-registered-target

#include <arm_neon.h>

// CHECK-LABEL: define {{[^@]+}}@test_fma_order
// CHECK-SAME: (<2 x float> noundef [[ACCUM:%.*]], <2 x float> noundef [[LHS:%.*]], <2 x float> noundef [[RHS:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x float> [[ACCUM]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <2 x float> [[LHS]] to <8 x i8>
// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <2 x float> [[RHS]] to <8 x i8>
// CHECK-NEXT:    [[TMP3:%.*]] = call <2 x float> @llvm.fma.v2f32(<2 x float> [[LHS]], <2 x float> [[RHS]], <2 x float> [[ACCUM]])
// CHECK-NEXT:    ret <2 x float> [[TMP3]]
//
float32x2_t test_fma_order(float32x2_t accum, float32x2_t lhs, float32x2_t rhs) {
  return vfma_f32(accum, lhs, rhs);
}

// CHECK-LABEL: define {{[^@]+}}@test_fmaq_order
// CHECK-SAME: (<4 x float> noundef [[ACCUM:%.*]], <4 x float> noundef [[LHS:%.*]], <4 x float> noundef [[RHS:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[ACCUM]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <4 x float> [[LHS]] to <16 x i8>
// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x float> [[RHS]] to <16 x i8>
// CHECK-NEXT:    [[TMP3:%.*]] = call <4 x float> @llvm.fma.v4f32(<4 x float> [[LHS]], <4 x float> [[RHS]], <4 x float> [[ACCUM]])
// CHECK-NEXT:    ret <4 x float> [[TMP3]]
//
float32x4_t test_fmaq_order(float32x4_t accum, float32x4_t lhs, float32x4_t rhs) {
  return vfmaq_f32(accum, lhs, rhs);
}

// CHECK-LABEL: define {{[^@]+}}@test_vfma_n_f32
// CHECK-SAME: (<2 x float> noundef [[A:%.*]], <2 x float> noundef [[B:%.*]], float noundef [[N:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VECINIT_I:%.*]] = insertelement <2 x float> undef, float [[N]], i32 0
// CHECK-NEXT:    [[VECINIT1_I:%.*]] = insertelement <2 x float> [[VECINIT_I]], float [[N]], i32 1
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x float> [[A]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <2 x float> [[B]] to <8 x i8>
// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <2 x float> [[VECINIT1_I]] to <8 x i8>
// CHECK-NEXT:    [[TMP3:%.*]] = call <2 x float> @llvm.fma.v2f32(<2 x float> [[B]], <2 x float> [[VECINIT1_I]], <2 x float> [[A]])
// CHECK-NEXT:    ret <2 x float> [[TMP3]]
//
float32x2_t test_vfma_n_f32(float32x2_t a, float32x2_t b, float32_t n) {
  return vfma_n_f32(a, b, n);
}

// CHECK-LABEL: define {{[^@]+}}@test_vfmaq_n_f32
// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]], float noundef [[N:%.*]]) #[[ATTR1]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[VECINIT_I:%.*]] = insertelement <4 x float> undef, float [[N]], i32 0
// CHECK-NEXT:    [[VECINIT1_I:%.*]] = insertelement <4 x float> [[VECINIT_I]], float [[N]], i32 1
// CHECK-NEXT:    [[VECINIT2_I:%.*]] = insertelement <4 x float> [[VECINIT1_I]], float [[N]], i32 2
// CHECK-NEXT:    [[VECINIT3_I:%.*]] = insertelement <4 x float> [[VECINIT2_I]], float [[N]], i32 3
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x float> [[A]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <4 x float> [[B]] to <16 x i8>
// CHECK-NEXT:    [[TMP2:%.*]] = bitcast <4 x float> [[VECINIT3_I]] to <16 x i8>
// CHECK-NEXT:    [[TMP3:%.*]] = call <4 x float> @llvm.fma.v4f32(<4 x float> [[B]], <4 x float> [[VECINIT3_I]], <4 x float> [[A]])
// CHECK-NEXT:    ret <4 x float> [[TMP3]]
//
float32x4_t test_vfmaq_n_f32(float32x4_t a, float32x4_t b, float32_t n) {
  return vfmaq_n_f32(a, b, n);
}