// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -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 -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 -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 -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 -DTEST_SME -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +sme -S -disable-O0-optnone -Werror -Wall -o /dev/null %s

// 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

#ifndef TEST_SME
#define ATTR
#else
#define ATTR __arm_streaming
#endif

// CHECK-LABEL: @test_svset4_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv16i8(<vscale x 64 x i8> [[TUPLE:%.*]], <vscale x 16 x i8> [[X:%.*]], i64 16)
// CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z14test_svset4_s810svint8x4_tu10__SVInt8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv16i8(<vscale x 64 x i8> [[TUPLE:%.*]], <vscale x 16 x i8> [[X:%.*]], i64 16)
// CPP-CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
svint8x4_t test_svset4_s8(svint8x4_t tuple, svint8_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_s8,,)(tuple, 1, x);
}

// CHECK-LABEL: @test_svset4_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv8i16(<vscale x 32 x i16> [[TUPLE:%.*]], <vscale x 8 x i16> [[X:%.*]], i64 24)
// CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_s1611svint16x4_tu11__SVInt16_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv8i16(<vscale x 32 x i16> [[TUPLE:%.*]], <vscale x 8 x i16> [[X:%.*]], i64 24)
// CPP-CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
svint16x4_t test_svset4_s16(svint16x4_t tuple, svint16_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_s16,,)(tuple, 3, x);
}

// CHECK-LABEL: @test_svset4_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> [[TUPLE:%.*]], <vscale x 4 x i32> [[X:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_s3211svint32x4_tu11__SVInt32_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> [[TUPLE:%.*]], <vscale x 4 x i32> [[X:%.*]], i64 4)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
svint32x4_t test_svset4_s32(svint32x4_t tuple, svint32_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_s32,,)(tuple, 1, x);
}

// CHECK-LABEL: @test_svset4_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv2i64(<vscale x 8 x i64> [[TUPLE:%.*]], <vscale x 2 x i64> [[X:%.*]], i64 2)
// CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_s6411svint64x4_tu11__SVInt64_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv2i64(<vscale x 8 x i64> [[TUPLE:%.*]], <vscale x 2 x i64> [[X:%.*]], i64 2)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
svint64x4_t test_svset4_s64(svint64x4_t tuple, svint64_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_s64,,)(tuple, 1, x);
}

// CHECK-LABEL: @test_svset4_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv16i8(<vscale x 64 x i8> [[TUPLE:%.*]], <vscale x 16 x i8> [[X:%.*]], i64 48)
// CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z14test_svset4_u811svuint8x4_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 64 x i8> @llvm.vector.insert.nxv64i8.nxv16i8(<vscale x 64 x i8> [[TUPLE:%.*]], <vscale x 16 x i8> [[X:%.*]], i64 48)
// CPP-CHECK-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
//
svuint8x4_t test_svset4_u8(svuint8x4_t tuple, svuint8_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_u8,,)(tuple, 3, x);
}

// CHECK-LABEL: @test_svset4_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv8i16(<vscale x 32 x i16> [[TUPLE:%.*]], <vscale x 8 x i16> [[X:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_u1612svuint16x4_tu12__SVUint16_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 32 x i16> @llvm.vector.insert.nxv32i16.nxv8i16(<vscale x 32 x i16> [[TUPLE:%.*]], <vscale x 8 x i16> [[X:%.*]], i64 8)
// CPP-CHECK-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
//
svuint16x4_t test_svset4_u16(svuint16x4_t tuple, svuint16_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_u16,,)(tuple, 1, x);
}

// CHECK-LABEL: @test_svset4_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> [[TUPLE:%.*]], <vscale x 4 x i32> [[X:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_u3212svuint32x4_tu12__SVUint32_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> [[TUPLE:%.*]], <vscale x 4 x i32> [[X:%.*]], i64 4)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
//
svuint32x4_t test_svset4_u32(svuint32x4_t tuple, svuint32_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_u32,,)(tuple, 1, x);
}

// CHECK-LABEL: @test_svset4_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv2i64(<vscale x 8 x i64> [[TUPLE:%.*]], <vscale x 2 x i64> [[X:%.*]], i64 6)
// CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_u6412svuint64x4_tu12__SVUint64_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i64> @llvm.vector.insert.nxv8i64.nxv2i64(<vscale x 8 x i64> [[TUPLE:%.*]], <vscale x 2 x i64> [[X:%.*]], i64 6)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
//
svuint64x4_t test_svset4_u64(svuint64x4_t tuple, svuint64_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_u64,,)(tuple, 3, x);
}

// CHECK-LABEL: @test_svset4_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 32 x half> @llvm.vector.insert.nxv32f16.nxv8f16(<vscale x 32 x half> [[TUPLE:%.*]], <vscale x 8 x half> [[X:%.*]], i64 8)
// CHECK-NEXT:    ret <vscale x 32 x half> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_f1613svfloat16x4_tu13__SVFloat16_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 32 x half> @llvm.vector.insert.nxv32f16.nxv8f16(<vscale x 32 x half> [[TUPLE:%.*]], <vscale x 8 x half> [[X:%.*]], i64 8)
// CPP-CHECK-NEXT:    ret <vscale x 32 x half> [[TMP0]]
//
svfloat16x4_t test_svset4_f16(svfloat16x4_t tuple, svfloat16_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_f16,,)(tuple, 1, x);
}

// CHECK-LABEL: @test_svset4_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x float> @llvm.vector.insert.nxv16f32.nxv4f32(<vscale x 16 x float> [[TUPLE:%.*]], <vscale x 4 x float> [[X:%.*]], i64 4)
// CHECK-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_f3213svfloat32x4_tu13__SVFloat32_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x float> @llvm.vector.insert.nxv16f32.nxv4f32(<vscale x 16 x float> [[TUPLE:%.*]], <vscale x 4 x float> [[X:%.*]], i64 4)
// CPP-CHECK-NEXT:    ret <vscale x 16 x float> [[TMP0]]
//
svfloat32x4_t test_svset4_f32(svfloat32x4_t tuple, svfloat32_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_f32,,)(tuple, 1, x);
}

// CHECK-LABEL: @test_svset4_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nxv2f64(<vscale x 8 x double> [[TUPLE:%.*]], <vscale x 2 x double> [[X:%.*]], i64 6)
// CHECK-NEXT:    ret <vscale x 8 x double> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svset4_f6413svfloat64x4_tu13__SVFloat64_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nxv2f64(<vscale x 8 x double> [[TUPLE:%.*]], <vscale x 2 x double> [[X:%.*]], i64 6)
// CPP-CHECK-NEXT:    ret <vscale x 8 x double> [[TMP0]]
//
svfloat64x4_t test_svset4_f64(svfloat64x4_t tuple, svfloat64_t x) ATTR
{
  return SVE_ACLE_FUNC(svset4,_f64,,)(tuple, 3, x);
}