// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -fclang-abi-compat=latest -target-feature +i8mm -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 -fclang-abi-compat=latest -target-feature +i8mm -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 -fclang-abi-compat=latest -target-feature +i8mm -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 -fclang-abi-compat=latest -target-feature +i8mm -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

// 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_svmmla_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smmla.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[Y:%.*]], <vscale x 16 x i8> [[Z:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svmmla_s32u11__SVInt32_tu10__SVInt8_tS0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.smmla.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[Y:%.*]], <vscale x 16 x i8> [[Z:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svint32_t test_svmmla_s32(svint32_t x, svint8_t y, svint8_t z) {
  return SVE_ACLE_FUNC(svmmla,_s32,,)(x, y, z);
}

// CHECK-LABEL: @test_svmmla_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ummla.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[Y:%.*]], <vscale x 16 x i8> [[Z:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svmmla_u32u12__SVUint32_tu11__SVUint8_tS0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ummla.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[Y:%.*]], <vscale x 16 x i8> [[Z:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svmmla_u32(svuint32_t x, svuint8_t y, svuint8_t z) {
  return SVE_ACLE_FUNC(svmmla,_u32,,)(x, y, z);
}

// CHECK-LABEL: @test_svusmmla_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.usmmla.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[Y:%.*]], <vscale x 16 x i8> [[Z:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z17test_svusmmla_s32u11__SVInt32_tu11__SVUint8_tu10__SVInt8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.usmmla.nxv4i32(<vscale x 4 x i32> [[X:%.*]], <vscale x 16 x i8> [[Y:%.*]], <vscale x 16 x i8> [[Z:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svint32_t test_svusmmla_s32(svint32_t x, svuint8_t y, svint8_t z) {
  return SVE_ACLE_FUNC(svusmmla,_s32,,)(x, y, z);
}