// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
// REQUIRES: aarch64-registered-target

// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sme -target-feature +sme-f8f16 -target-feature +sme-f8f32 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sme -target-feature +sme-f8f16 -target-feature +sme-f8f32 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -DSME_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sme -target-feature +sme-f8f16 -target-feature +sme-f8f32 -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -DSME_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sme -target-feature +sme-f8f16 -target-feature +sme-f8f32 -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sme -target-feature +sme-f8f16 -target-feature +sme-f8f32 -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, A4_UNUSED, A5) A1##A3##A5
#else
#define SME_ACLE_FUNC(A1, A2, A3, A4, A5) A1##A2##A3##A4##A5
#endif

// FMLAL (indexed)

// CHECK-LABEL: define dso_local void @test_svmla_lane_za16_vg2x1(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.lane.za16.vg2x1(i32 [[SLICE]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 0)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z26test_svmla_lane_za16_vg2x1ju13__SVMfloat8_tS_m(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0:[0-9]+]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.lane.za16.vg2x1(i32 [[SLICE]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 0)
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_lane_za16_vg2x1(uint32_t slice, svmfloat8_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_lane_za16,_mf8,_vg2x1_fpm,,)(slice, zn, zm, 0, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_lane_za16_vg2x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.lane.za16.vg2x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM]], i32 15)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z26test_svmla_lane_za16_vg2x2j13svmfloat8x2_tu13__SVMfloat8_tm(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.lane.za16.vg2x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM]], i32 15)
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_lane_za16_vg2x2(uint32_t slice, svmfloat8x2_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_lane_za16,_mf8,_vg2x2_fpm,,)(slice, zn, zm, 15, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_lane_za16_vg2x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.lane.za16.vg2x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM]], i32 7)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z26test_svmla_lane_za16_vg2x4j13svmfloat8x4_tu13__SVMfloat8_tm(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.lane.za16.vg2x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM]], i32 7)
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_lane_za16_vg2x4(uint32_t slice, svmfloat8x4_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_lane_za16,_mf8,_vg2x4_fpm,,)(slice, zn, zm, 7, fpm);
}

// FMLALL (indexed)

// CHECK-LABEL: define dso_local void @test_svmla_lane_za32_vg4x1(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.lane.za32.vg4x1(i32 [[SLICE]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 0)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z26test_svmla_lane_za32_vg4x1ju13__SVMfloat8_tS_m(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.lane.za32.vg4x1(i32 [[SLICE]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]], i32 0)
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_lane_za32_vg4x1(uint32_t slice, svmfloat8_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_lane_za32,_mf8,_vg4x1_fpm,,)(slice, zn, zm, 0, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_lane_za32_vg4x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.lane.za32.vg4x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM]], i32 15)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z26test_svmla_lane_za32_vg4x2j13svmfloat8x2_tu13__SVMfloat8_tm(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.lane.za32.vg4x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM]], i32 15)
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_lane_za32_vg4x2(uint32_t slice, svmfloat8x2_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_lane_za32,_mf8,_vg4x2_fpm,,)(slice, zn, zm, 15, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_lane_za32_vg4x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.lane.za32.vg4x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM]], i32 7)
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z26test_svmla_lane_za32_vg4x4j13svmfloat8x4_tu13__SVMfloat8_tm(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.lane.za32.vg4x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM]], i32 7)
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_lane_za32_vg4x4(uint32_t slice, svmfloat8x4_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_lane_za32,_mf8,_vg4x4_fpm,,)(slice, zn, zm, 7, fpm);
}

// FMLAL (single)

// CHECK-LABEL: define dso_local void @test_svmla_single_za16_vg2x1(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.single.za16.vg2x1(i32 [[SLICE]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z28test_svmla_single_za16_vg2x1ju13__SVMfloat8_tS_m(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0:[0-9]+]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.single.za16.vg2x1(i32 [[SLICE]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_single_za16_vg2x1(uint32_t slice, svmfloat8_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla,_single,_za16,_mf8,_vg2x1_fpm)(slice, zn, zm, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_single_za16_vg2x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.single.za16.vg2x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z28test_svmla_single_za16_vg2x2j13svmfloat8x2_tu13__SVMfloat8_tm(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.single.za16.vg2x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_single_za16_vg2x2(uint32_t slice, svmfloat8x2_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla,_single,_za16,_mf8,_vg2x2_fpm)(slice, zn, zm, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_single_za16_vg2x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.single.za16.vg2x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z28test_svmla_single_za16_vg2x4j13svmfloat8x4_tu13__SVMfloat8_tm(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.single.za16.vg2x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_single_za16_vg2x4(uint32_t slice, svmfloat8x4_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla,_single,_za16,_mf8,_vg2x4_fpm)(slice, zn, zm, fpm);
}

// FMLALL (single)

// CHECK-LABEL: define dso_local void @test_svmla_single_za32_vg4x1(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.single.za32.vg4x1(i32 [[SLICE]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z28test_svmla_single_za32_vg4x1ju13__SVMfloat8_tS_m(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.single.za32.vg4x1(i32 [[SLICE]], <vscale x 16 x i8> [[ZN]], <vscale x 16 x i8> [[ZM]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_single_za32_vg4x1(uint32_t slice, svmfloat8_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla,_single,_za32,_mf8,_vg4x1_fpm)(slice, zn, zm, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_single_za32_vg4x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.single.za32.vg4x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z28test_svmla_single_za32_vg4x2j13svmfloat8x2_tu13__SVMfloat8_tm(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.single.za32.vg4x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_single_za32_vg4x2(uint32_t slice, svmfloat8x2_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla,_single,_za32,_mf8,_vg4x2_fpm)(slice, zn, zm, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_single_za32_vg4x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.single.za32.vg4x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z28test_svmla_single_za32_vg4x4j13svmfloat8x4_tu13__SVMfloat8_tm(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.single.za32.vg4x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_single_za32_vg4x4(uint32_t slice, svmfloat8x4_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla,_single,_za32,_mf8,_vg4x4_fpm)(slice, zn, zm, fpm);
}

// FMLAL (multi)

// CHECK-LABEL: define dso_local void @test_svmla_multi_za16_vg2x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM_COERCE0:%.*]], <vscale x 16 x i8> [[ZM_COERCE1:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.multi.za16.vg2x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM_COERCE0]], <vscale x 16 x i8> [[ZM_COERCE1]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z27test_svmla_multi_za16_vg2x2j13svmfloat8x2_tS_m(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM_COERCE0:%.*]], <vscale x 16 x i8> [[ZM_COERCE1:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0:[0-9]+]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.multi.za16.vg2x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM_COERCE0]], <vscale x 16 x i8> [[ZM_COERCE1]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_multi_za16_vg2x2(uint32_t slice, svmfloat8x2_t zn, svmfloat8x2_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_za16,_mf8,_vg2x2_fpm,,)(slice, zn, zm, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_multi_za16_vg2x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM_COERCE0:%.*]], <vscale x 16 x i8> [[ZM_COERCE1:%.*]], <vscale x 16 x i8> [[ZM_COERCE2:%.*]], <vscale x 16 x i8> [[ZM_COERCE3:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.multi.za16.vg2x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM_COERCE0]], <vscale x 16 x i8> [[ZM_COERCE1]], <vscale x 16 x i8> [[ZM_COERCE2]], <vscale x 16 x i8> [[ZM_COERCE3]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z27test_svmla_multi_za16_vg2x4j13svmfloat8x4_tS_m(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM_COERCE0:%.*]], <vscale x 16 x i8> [[ZM_COERCE1:%.*]], <vscale x 16 x i8> [[ZM_COERCE2:%.*]], <vscale x 16 x i8> [[ZM_COERCE3:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlal.multi.za16.vg2x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM_COERCE0]], <vscale x 16 x i8> [[ZM_COERCE1]], <vscale x 16 x i8> [[ZM_COERCE2]], <vscale x 16 x i8> [[ZM_COERCE3]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_multi_za16_vg2x4(uint32_t slice, svmfloat8x4_t zn, svmfloat8x4_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_za16,_mf8,_vg2x4_fpm,,)(slice, zn, zm, fpm);
}

// FMLALL (multi)

// CHECK-LABEL: define dso_local void @test_svmla_multi_za32_vg4x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM_COERCE0:%.*]], <vscale x 16 x i8> [[ZM_COERCE1:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.multi.za32.vg4x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM_COERCE0]], <vscale x 16 x i8> [[ZM_COERCE1]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z27test_svmla_multi_za32_vg4x2j13svmfloat8x2_tS_m(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZM_COERCE0:%.*]], <vscale x 16 x i8> [[ZM_COERCE1:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.multi.za32.vg4x2(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZM_COERCE0]], <vscale x 16 x i8> [[ZM_COERCE1]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_multi_za32_vg4x2(uint32_t slice, svmfloat8x2_t zn, svmfloat8x2_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_za32,_mf8,_vg4x2_fpm,,)(slice, zn, zm, fpm);
}

// CHECK-LABEL: define dso_local void @test_svmla_multi_za32_vg4x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM_COERCE0:%.*]], <vscale x 16 x i8> [[ZM_COERCE1:%.*]], <vscale x 16 x i8> [[ZM_COERCE2:%.*]], <vscale x 16 x i8> [[ZM_COERCE3:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.multi.za32.vg4x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM_COERCE0]], <vscale x 16 x i8> [[ZM_COERCE1]], <vscale x 16 x i8> [[ZM_COERCE2]], <vscale x 16 x i8> [[ZM_COERCE3]])
// CHECK-NEXT:    ret void
//
// CPP-CHECK-LABEL: define dso_local void @_Z27test_svmla_multi_za32_vg4x4j13svmfloat8x4_tS_m(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]], <vscale x 16 x i8> [[ZN_COERCE0:%.*]], <vscale x 16 x i8> [[ZN_COERCE1:%.*]], <vscale x 16 x i8> [[ZN_COERCE2:%.*]], <vscale x 16 x i8> [[ZN_COERCE3:%.*]], <vscale x 16 x i8> [[ZM_COERCE0:%.*]], <vscale x 16 x i8> [[ZM_COERCE1:%.*]], <vscale x 16 x i8> [[ZM_COERCE2:%.*]], <vscale x 16 x i8> [[ZM_COERCE3:%.*]], i64 noundef [[FPM:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  [[ENTRY:.*:]]
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.set.fpmr(i64 [[FPM]])
// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sme.fp8.fmlall.multi.za32.vg4x4(i32 [[SLICE]], <vscale x 16 x i8> [[ZN_COERCE0]], <vscale x 16 x i8> [[ZN_COERCE1]], <vscale x 16 x i8> [[ZN_COERCE2]], <vscale x 16 x i8> [[ZN_COERCE3]], <vscale x 16 x i8> [[ZM_COERCE0]], <vscale x 16 x i8> [[ZM_COERCE1]], <vscale x 16 x i8> [[ZM_COERCE2]], <vscale x 16 x i8> [[ZM_COERCE3]])
// CPP-CHECK-NEXT:    ret void
//
void test_svmla_multi_za32_vg4x4(uint32_t slice, svmfloat8x4_t zn, svmfloat8x4_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
    SME_ACLE_FUNC(svmla_za32,_mf8,_vg4x4_fpm,,)(slice, zn, zm, fpm);
}