// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple aarch64 -target-feature +neon \
// RUN:  -target-feature +rcpc3 -disable-O0-optnone -emit-llvm -o - %s \
// RUN: | opt -S -passes=mem2reg | FileCheck %s

// REQUIRES: aarch64-registered-target

#include <arm_neon.h>


// CHECK-LABEL: @test_vldap1q_lane_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT:    [[VLDAP1_LANE:%.*]] = insertelement <2 x i64> [[TMP1]], i64 [[TMP2]], i32 1
// CHECK-NEXT:    ret <2 x i64> [[VLDAP1_LANE]]
//
uint64x2_t test_vldap1q_lane_u64(uint64_t  *a, uint64x2_t b) {
  return vldap1q_lane_u64(a, b, 1);
}

// CHECK-LABEL: @test_vldap1q_lane_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT:    [[VLDAP1_LANE:%.*]] = insertelement <2 x i64> [[TMP1]], i64 [[TMP2]], i32 1
// CHECK-NEXT:    ret <2 x i64> [[VLDAP1_LANE]]
//
int64x2_t test_vldap1q_lane_s64(int64_t  *a, int64x2_t b) {
  return vldap1q_lane_s64(a, b, 1);
}

// CHECK-LABEL: @test_vldap1q_lane_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x double> [[B:%.*]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x double>
// CHECK-NEXT:    [[TMP2:%.*]] = load atomic double, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT:    [[VLDAP1_LANE:%.*]] = insertelement <2 x double> [[TMP1]], double [[TMP2]], i32 1
// CHECK-NEXT:    ret <2 x double> [[VLDAP1_LANE]]
//
float64x2_t test_vldap1q_lane_f64(float64_t  *a, float64x2_t b) {
  return vldap1q_lane_f64(a, b, 1);
}

// CHECK-LABEL: @test_vldap1q_lane_p64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT:    [[VLDAP1_LANE:%.*]] = insertelement <2 x i64> [[TMP1]], i64 [[TMP2]], i32 1
// CHECK-NEXT:    ret <2 x i64> [[VLDAP1_LANE]]
//
poly64x2_t test_vldap1q_lane_p64(poly64_t  *a, poly64x2_t b) {
  return vldap1q_lane_p64(a, b, 1);
}

// CHECK-LABEL: @test_vldap1_lane_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT:    [[VLDAP1_LANE:%.*]] = insertelement <1 x i64> [[TMP1]], i64 [[TMP2]], i32 0
// CHECK-NEXT:    ret <1 x i64> [[VLDAP1_LANE]]
//
uint64x1_t test_vldap1_lane_u64(uint64_t  *a, uint64x1_t b) {
  return vldap1_lane_u64(a, b, 0);
}

// CHECK-LABEL: @test_vldap1_lane_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT:    [[VLDAP1_LANE:%.*]] = insertelement <1 x i64> [[TMP1]], i64 [[TMP2]], i32 0
// CHECK-NEXT:    ret <1 x i64> [[VLDAP1_LANE]]
//
int64x1_t test_vldap1_lane_s64(int64_t  *a, int64x1_t b) {
  return vldap1_lane_s64(a, b, 0);
}

// CHECK-LABEL: @test_vldap1_lane_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <1 x double> [[B:%.*]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x double>
// CHECK-NEXT:    [[TMP2:%.*]] = load atomic double, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT:    [[VLDAP1_LANE:%.*]] = insertelement <1 x double> [[TMP1]], double [[TMP2]], i32 0
// CHECK-NEXT:    ret <1 x double> [[VLDAP1_LANE]]
//
float64x1_t test_vldap1_lane_f64(float64_t  *a, float64x1_t b) {
  return vldap1_lane_f64(a, b, 0);
}

// CHECK-LABEL: @test_vldap1_lane_p64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = load atomic i64, ptr [[A:%.*]] acquire, align 8
// CHECK-NEXT:    [[VLDAP1_LANE:%.*]] = insertelement <1 x i64> [[TMP1]], i64 [[TMP2]], i32 0
// CHECK-NEXT:    ret <1 x i64> [[VLDAP1_LANE]]
//
poly64x1_t test_vldap1_lane_p64(poly64_t  *a, poly64x1_t b) {
  return vldap1_lane_p64(a, b, 0);
}

// CHECK-LABEL: @test_vstl1q_lane_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x i64> [[TMP1]], i32 1
// CHECK-NEXT:    store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT:    ret void
//
void test_vstl1q_lane_u64(uint64_t  *a, uint64x2_t b) {
  vstl1q_lane_u64(a, b, 1);
}

// CHECK-LABEL: @test_vstl1q_lane_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x i64> [[TMP1]], i32 1
// CHECK-NEXT:    store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT:    ret void
//
void test_vstl1q_lane_s64(int64_t  *a, int64x2_t b) {
  vstl1q_lane_s64(a, b, 1);
}

// CHECK-LABEL: @test_vstl1q_lane_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x double> [[B:%.*]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x double>
// CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[TMP1]], i32 1
// CHECK-NEXT:    store atomic double [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT:    ret void
//
void test_vstl1q_lane_f64(float64_t  *a, float64x2_t b) {
  vstl1q_lane_f64(a, b, 1);
}

// CHECK-LABEL: @test_vstl1q_lane_p64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <2 x i64> [[B:%.*]] to <16 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <16 x i8> [[TMP0]] to <2 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x i64> [[TMP1]], i32 1
// CHECK-NEXT:    store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT:    ret void
//
void test_vstl1q_lane_p64(poly64_t  *a, poly64x2_t b) {
  vstl1q_lane_p64(a, b, 1);
}

// CHECK-LABEL: @test_vstl1_lane_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = extractelement <1 x i64> [[TMP1]], i32 0
// CHECK-NEXT:    store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT:    ret void
//
void test_vstl1_lane_u64(uint64_t  *a, uint64x1_t b) {
  vstl1_lane_u64(a, b, 0);
}

// CHECK-LABEL: @test_vstl1_lane_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = extractelement <1 x i64> [[TMP1]], i32 0
// CHECK-NEXT:    store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT:    ret void
//
void test_vstl1_lane_s64(int64_t  *a, int64x1_t b) {
  vstl1_lane_s64(a, b, 0);
}

// CHECK-LABEL: @test_vstl1_lane_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <1 x double> [[B:%.*]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x double>
// CHECK-NEXT:    [[TMP2:%.*]] = extractelement <1 x double> [[TMP1]], i32 0
// CHECK-NEXT:    store atomic double [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT:    ret void
//
void test_vstl1_lane_f64(float64_t  *a, float64x1_t b) {
  vstl1_lane_f64(a, b, 0);
}

// CHECK-LABEL: @test_vstl1_lane_p64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <1 x i64> [[B:%.*]] to <8 x i8>
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i8> [[TMP0]] to <1 x i64>
// CHECK-NEXT:    [[TMP2:%.*]] = extractelement <1 x i64> [[TMP1]], i32 0
// CHECK-NEXT:    store atomic i64 [[TMP2]], ptr [[A:%.*]] release, align 8
// CHECK-NEXT:    ret void
//
void test_vstl1_lane_p64(poly64_t  *a, poly64x1_t b) {
  vstl1_lane_p64(a, b, 0);
}