// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py

// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme-tmop -target-feature +sme-f16f16 -target-feature +sme-f8f32 -target-feature +sme-b16b16 -target-feature +sme-f8f16 -target-feature +sme -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme-tmop -target-feature +sme-f16f16 -target-feature +sme-f8f32 -target-feature +sme-b16b16 -target-feature +sme-f8f16 -target-feature +sme -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -DSME_OVERLOADED_FORMS -triple aarch64 -target-feature +sme-tmop -target-feature +sme-f16f16 -target-feature +sme-f8f32 -target-feature +sme-b16b16 -target-feature +sme-f8f16 -target-feature +sme -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -DSME_OVERLOADED_FORMS -triple aarch64 -target-feature +sme-tmop -target-feature +sme-f16f16 -target-feature +sme-f8f32 -target-feature +sme-b16b16 -target-feature +sme-f8f16 -target-feature +sme -target-feature +sme2 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme-tmop -target-feature +sme-f16f16 -target-feature +sme-f8f32 -target-feature +sme-b16b16 -target-feature +sme-f8f16 -target-feature +sme -target-feature +sme2 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s

#include <arm_sme.h>

#ifdef SME_OVERLOADED_FORMS
#define SME_ACLE_FUNC(A1,A2_UNUSED,A3) A1##A3
#else
#define SME_ACLE_FUNC(A1,A2,A3) A1##A2##A3
#endif

// CHECK-LABEL: @test_svtmopa_lane_za32_s8_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.stmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z28test_svtmopa_lane_za32_s8_s810svint8x2_tu10__SVInt8_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.stmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_s8_s8(svint8x2_t zn, svint8_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_s8_s8,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_u8_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.utmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z28test_svtmopa_lane_za32_u8_u811svuint8x2_tu11__SVUint8_tS0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.utmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_u8_u8(svuint8x2_t zn, svuint8_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_u8_u8,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_s8_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.sutmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z28test_svtmopa_lane_za32_s8_u810svint8x2_tu11__SVUint8_tS0_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.sutmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_s8_u8(svint8x2_t zn, svuint8_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_s8_u8,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_u8_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.ustmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z28test_svtmopa_lane_za32_u8_s811svuint8x2_tu10__SVInt8_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.ustmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_u8_s8(svuint8x2_t zn, svint8_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_u8_s8,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_s16_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.stmopa.za32.nxv8i16(i32 1, <vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]], <vscale x 8 x i16> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z30test_svtmopa_lane_za32_s16_s1611svint16x2_tu11__SVInt16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.stmopa.za32.nxv8i16(i32 1, <vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]], <vscale x 8 x i16> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_s16_s16(svint16x2_t zn, svint16_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_s16_s16,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_u16_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.utmopa.za32.nxv8i16(i32 1, <vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]], <vscale x 8 x i16> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z30test_svtmopa_lane_za32_u16_u1612svuint16x2_tu12__SVUint16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.utmopa.za32.nxv8i16(i32 1, <vscale x 8 x i16> [[ZN_COERCE0:%.*]], <vscale x 8 x i16> [[ZN_COERCE1:%.*]], <vscale x 8 x i16> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_u16_u16(svuint16x2_t zn, svuint16_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_u16_u16,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_f16_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za32.nxv8f16(i32 1, <vscale x 8 x half> [[ZN_COERCE0:%.*]], <vscale x 8 x half> [[ZN_COERCE1:%.*]], <vscale x 8 x half> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z30test_svtmopa_lane_za32_f16_f1613svfloat16x2_tu13__SVFloat16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za32.nxv8f16(i32 1, <vscale x 8 x half> [[ZN_COERCE0:%.*]], <vscale x 8 x half> [[ZN_COERCE1:%.*]], <vscale x 8 x half> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_f16_f16(svfloat16x2_t zn, svfloat16_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_f16_f16,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_f32_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za32.nxv4f32(i32 1, <vscale x 4 x float> [[ZN_COERCE0:%.*]], <vscale x 4 x float> [[ZN_COERCE1:%.*]], <vscale x 4 x float> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z30test_svtmopa_lane_za32_f32_f3213svfloat32x2_tu13__SVFloat32_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za32.nxv4f32(i32 1, <vscale x 4 x float> [[ZN_COERCE0:%.*]], <vscale x 4 x float> [[ZN_COERCE1:%.*]], <vscale x 4 x float> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_f32_f32(svfloat32x2_t zn, svfloat32_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_f32_f32,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_bf16_bf16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za32.nxv8bf16(i32 1, <vscale x 8 x bfloat> [[ZN_COERCE0:%.*]], <vscale x 8 x bfloat> [[ZN_COERCE1:%.*]], <vscale x 8 x bfloat> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z32test_svtmopa_lane_za32_bf16_bf1614svbfloat16x2_tu14__SVBfloat16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za32.nxv8bf16(i32 1, <vscale x 8 x bfloat> [[ZN_COERCE0:%.*]], <vscale x 8 x bfloat> [[ZN_COERCE1:%.*]], <vscale x 8 x bfloat> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_bf16_bf16(svbfloat16x2_t zn, svbfloat16_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_bf16_bf16,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za16_f16_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za16.nxv8f16(i32 1, <vscale x 8 x half> [[ZN_COERCE0:%.*]], <vscale x 8 x half> [[ZN_COERCE1:%.*]], <vscale x 8 x half> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z30test_svtmopa_lane_za16_f16_f1613svfloat16x2_tu13__SVFloat16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za16.nxv8f16(i32 1, <vscale x 8 x half> [[ZN_COERCE0:%.*]], <vscale x 8 x half> [[ZN_COERCE1:%.*]], <vscale x 8 x half> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za16_f16_f16(svfloat16x2_t zn, svfloat16_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za16,_f16_f16,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za16_bf16_bf16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za16.nxv8bf16(i32 1, <vscale x 8 x bfloat> [[ZN_COERCE0:%.*]], <vscale x 8 x bfloat> [[ZN_COERCE1:%.*]], <vscale x 8 x bfloat> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z32test_svtmopa_lane_za16_bf16_bf1614svbfloat16x2_tu14__SVBfloat16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za16.nxv8bf16(i32 1, <vscale x 8 x bfloat> [[ZN_COERCE0:%.*]], <vscale x 8 x bfloat> [[ZN_COERCE1:%.*]], <vscale x 8 x bfloat> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za16_bf16_bf16(svbfloat16x2_t zn, svbfloat16_t zm, svuint8_t zk) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za16,_bf16_bf16,)(1, zn, zm, zk, 3);
}

// CHECK-LABEL: @test_svtmopa_lane_za16_mf8_mf8_fpm(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPMR:%.*]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za16.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z34test_svtmopa_lane_za16_mf8_mf8_fpm13svmfloat8x2_tu13__SVMfloat8_tu11__SVUint8_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPMR:%.*]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za16.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za16_mf8_mf8_fpm(svmfloat8x2_t zn, svmfloat8_t zm, svuint8_t zk, fpm_t fpmr) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za16,_mf8_mf8,_fpm)(1, zn, zm, zk, 3, fpmr);
}

// CHECK-LABEL: @test_svtmopa_lane_za32_mf8_mf8_fpm(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPMR:%.*]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: @_Z34test_svtmopa_lane_za32_mf8_mf8_fpm13svmfloat8x2_tu13__SVMfloat8_tu11__SVUint8_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPMR:%.*]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.ftmopa.za32.nxv16i8(i32 1, <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], <vscale x 16 x i8> [[ZK:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret void
//
void test_svtmopa_lane_za32_mf8_mf8_fpm(svmfloat8x2_t zn, svmfloat8_t zm, svuint8_t zk, fpm_t fpmr) __arm_streaming __arm_inout("za") {
  SME_ACLE_FUNC(svtmopa_lane_za32,_mf8_mf8,_fpm)(1, zn, zm, zk, 3, fpmr);
}