// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +f64mm -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +f64mm -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +f64mm -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +f64mm -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK

// REQUIRES: aarch64-registered-target

#include <arm_sve.h>

#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.
#define SVE_ACLE_FUNC(A1, A2_UNUSED, A3, A4_UNUSED) A1##A3
#else
#define SVE_ACLE_FUNC(A1, A2, A3, A4) A1##A2##A3##A4
#endif

// CHECK-LABEL: @test_svld1ro_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1ro.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svld1ro_s8u10__SVBool_tPKa(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1ro.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svint8_t test_svld1ro_s8(svbool_t pg, const int8_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _s8, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1ro.nxv8i16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_s16u10__SVBool_tPKs(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1ro.nxv8i16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
svint16_t test_svld1ro_s16(svbool_t pg, const int16_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _s16, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1ro.nxv4i32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_s32u10__SVBool_tPKi(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1ro.nxv4i32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
svint32_t test_svld1ro_s32(svbool_t pg, const int32_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _s32, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1ro.nxv2i64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_s64u10__SVBool_tPKl(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1ro.nxv2i64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
svint64_t test_svld1ro_s64(svbool_t pg, const int64_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _s64, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1ro.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svld1ro_u8u10__SVBool_tPKh(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1ro.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svld1ro_u8(svbool_t pg, const uint8_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _u8, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1ro.nxv8i16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_u16u10__SVBool_tPKt(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1ro.nxv8i16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
svuint16_t test_svld1ro_u16(svbool_t pg, const uint16_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _u16, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1ro.nxv4i32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_u32u10__SVBool_tPKj(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1ro.nxv4i32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
svuint32_t test_svld1ro_u32(svbool_t pg, const uint32_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _u32, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1ro.nxv2i64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_u64u10__SVBool_tPKm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1ro.nxv2i64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
svuint64_t test_svld1ro_u64(svbool_t pg, const uint64_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _u64, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.ld1ro.nxv8f16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_f16u10__SVBool_tPKDh(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.ld1ro.nxv8f16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
svfloat16_t test_svld1ro_f16(svbool_t pg, const float16_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _f16, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.ld1ro.nxv4f32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_f32u10__SVBool_tPKf(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.ld1ro.nxv4f32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
svfloat32_t test_svld1ro_f32(svbool_t pg, const float32_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _f32, , )(pg, base);
}

// CHECK-LABEL: @test_svld1ro_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1ro.nxv2f64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1ro_f64u10__SVBool_tPKd(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1ro.nxv2f64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
svfloat64_t test_svld1ro_f64(svbool_t pg, const float64_t *base) {
  return SVE_ACLE_FUNC(svld1ro, _f64, , )(pg, base);
}