// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: aarch64-registered-target

// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sve2 -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sve2 -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2 -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2 -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK

#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_svpmullb_pair_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z21test_svpmullb_pair_u8u11__SVUint8_tS_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svpmullb_pair_u8(svuint8_t op1, svuint8_t op2)
{
  return SVE_ACLE_FUNC(svpmullb_pair,_u8,,)(op1, op2);
}

// CHECK-LABEL: @test_svpmullb_pair_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z22test_svpmullb_pair_u32u12__SVUint32_tS_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svpmullb_pair_u32(svuint32_t op1, svuint32_t op2)
{
  return SVE_ACLE_FUNC(svpmullb_pair,_u32,,)(op1, op2);
}

// CHECK-LABEL: @test_svpmullb_pair_n_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z23test_svpmullb_pair_n_u8u11__SVUint8_th(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svpmullb_pair_n_u8(svuint8_t op1, uint8_t op2)
{
  return SVE_ACLE_FUNC(svpmullb_pair,_n_u8,,)(op1, op2);
}

// CHECK-LABEL: @test_svpmullb_pair_n_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[DOTSPLAT]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z24test_svpmullb_pair_n_u32u12__SVUint32_tj(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svpmullb_pair_n_u32(svuint32_t op1, uint32_t op2)
{
  return SVE_ACLE_FUNC(svpmullb_pair,_n_u32,,)(op1, op2);
}

// CHECK-LABEL: @test_svpmullb_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 16 x i8> [[TMP0]] to <vscale x 8 x i16>
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z17test_svpmullb_u16u11__SVUint8_tS_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 16 x i8> [[TMP0]] to <vscale x 8 x i16>
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
svuint16_t test_svpmullb_u16(svuint8_t op1, svuint8_t op2)
{
  return SVE_ACLE_FUNC(svpmullb,_u16,,)(op1, op2);
}

// CHECK-LABEL: @test_svpmullb_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 4 x i32> [[TMP0]] to <vscale x 2 x i64>
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z17test_svpmullb_u64u12__SVUint32_tS_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 4 x i32> [[TMP0]] to <vscale x 2 x i64>
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
svuint64_t test_svpmullb_u64(svuint32_t op1, svuint32_t op2)
{
  return SVE_ACLE_FUNC(svpmullb,_u64,,)(op1, op2);
}

// CHECK-LABEL: @test_svpmullb_n_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[DOTSPLAT]])
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 16 x i8> [[TMP0]] to <vscale x 8 x i16>
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svpmullb_n_u16u11__SVUint8_th(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 16 x i8> poison, i8 [[OP2:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 16 x i8> [[DOTSPLATINSERT]], <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.pmullb.pair.nxv16i8(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 16 x i8> [[TMP0]] to <vscale x 8 x i16>
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
svuint16_t test_svpmullb_n_u16(svuint8_t op1, uint8_t op2)
{
  return SVE_ACLE_FUNC(svpmullb,_n_u16,,)(op1, op2);
}

// CHECK-LABEL: @test_svpmullb_n_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i64 0
// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[DOTSPLAT]])
// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 4 x i32> [[TMP0]] to <vscale x 2 x i64>
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svpmullb_n_u64u12__SVUint32_tj(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[OP2:%.*]], i64 0
// CPP-CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[DOTSPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.pmullb.pair.nxv4i32(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[DOTSPLAT]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 4 x i32> [[TMP0]] to <vscale x 2 x i64>
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
svuint64_t test_svpmullb_n_u64(svuint32_t op1, uint32_t op2)
{
  return SVE_ACLE_FUNC(svpmullb,_n_u64,,)(op1, op2);
}