// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 4
// REQUIRES: aarch64-registered-target
//RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sme2p1 -target-feature +sme -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sme2p1 -target-feature +sme -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-none-linux-gnu -target-feature +sme2p1 -target-feature +sme -S -disable-O0-optnone -Werror -Wall -o /dev/null %s

#include <arm_sme.h>

//
// X2- hor
// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_hor_za8_s8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z26test_svreadz_hor_za8_s8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0:[0-9]+]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svint8x2_t test_svreadz_hor_za8_s8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_s8_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_hor_za8_u8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z26test_svreadz_hor_za8_u8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svuint8x2_t test_svreadz_hor_za8_u8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_u8_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_hor_za8_mf8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z27test_svreadz_hor_za8_mf8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svmfloat8x2_t test_svreadz_hor_za8_mf8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_mf8_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_hor_za16_s16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.horiz.x2.nxv8i16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z28test_svreadz_hor_za16_s16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.horiz.x2.nxv8i16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svint16x2_t test_svreadz_hor_za16_s16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_s16_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_hor_za16_u16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.horiz.x2.nxv8i16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z28test_svreadz_hor_za16_u16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.horiz.x2.nxv8i16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svuint16x2_t test_svreadz_hor_za16_u16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_u16_vg2(1, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half> } @test_svreadz_hor_za16_f16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.horiz.x2.nxv8f16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half> } @_Z28test_svreadz_hor_za16_f16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.horiz.x2.nxv8f16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
svfloat16x2_t test_svreadz_hor_za16_f16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_f16_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @test_svreadz_hor_za16_bf16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.horiz.x2.nxv8bf16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @_Z29test_svreadz_hor_za16_bf16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.horiz.x2.nxv8bf16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
svbfloat16x2_t test_svreadz_hor_za16_bf16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_bf16_vg2(1, slice);
}


// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_hor_za32_s32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.horiz.x2.nxv4i32(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z28test_svreadz_hor_za32_s32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.horiz.x2.nxv4i32(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svint32x2_t test_svreadz_hor_za32_s32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_s32_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_hor_za32_u32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.horiz.x2.nxv4i32(i32 2, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z28test_svreadz_hor_za32_u32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.horiz.x2.nxv4i32(i32 2, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svuint32x2_t test_svreadz_hor_za32_u32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_u32_vg2(2, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float> } @test_svreadz_hor_za32_f32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.horiz.x2.nxv4f32(i32 3, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float> } @_Z28test_svreadz_hor_za32_f32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.horiz.x2.nxv4f32(i32 3, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
svfloat32x2_t test_svreadz_hor_za32_f32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_f32_vg2(3, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_hor_za64_s64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.horiz.x2.nxv2i64(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z28test_svreadz_hor_za64_s64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.horiz.x2.nxv2i64(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svint64x2_t test_svreadz_hor_za64_s64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_s64_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_hor_za64_u64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.horiz.x2.nxv2i64(i32 4, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z28test_svreadz_hor_za64_u64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.horiz.x2.nxv2i64(i32 4, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svuint64x2_t test_svreadz_hor_za64_u64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_u64_vg2(4, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double> } @test_svreadz_hor_za64_f64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.horiz.x2.nxv2f64(i32 7, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double> } @_Z28test_svreadz_hor_za64_f64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.horiz.x2.nxv2f64(i32 7, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
svfloat64x2_t test_svreadz_hor_za64_f64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_f64_vg2(7, slice);
}


//
// X2- ver
//

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_ver_za8_s8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z26test_svreadz_ver_za8_s8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svint8x2_t test_svreadz_ver_za8_s8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za8_s8_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_ver_za8_u8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z26test_svreadz_ver_za8_u8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svuint8x2_t test_svreadz_ver_za8_u8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za8_u8_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_ver_za8_mf8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z27test_svreadz_ver_za8_mf8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x2.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svmfloat8x2_t test_svreadz_ver_za8_mf8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za8_mf8_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_ver_za16_s16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.vert.x2.nxv8i16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z28test_svreadz_ver_za16_s16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.vert.x2.nxv8i16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svint16x2_t test_svreadz_ver_za16_s16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za16_s16_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_ver_za16_u16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.vert.x2.nxv8i16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z28test_svreadz_ver_za16_u16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.vert.x2.nxv8i16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svuint16x2_t test_svreadz_ver_za16_u16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za16_u16_vg2(1, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half> } @test_svreadz_ver_za16_f16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.vert.x2.nxv8f16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half> } @_Z28test_svreadz_ver_za16_f16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.vert.x2.nxv8f16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
svfloat16x2_t test_svreadz_ver_za16_f16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za16_f16_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @test_svreadz_ver_za16_bf16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.vert.x2.nxv8bf16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @_Z29test_svreadz_ver_za16_bf16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.vert.x2.nxv8bf16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
svbfloat16x2_t test_svreadz_ver_za16_bf16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za16_bf16_vg2(1, slice);
}


// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_ver_za32_s32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.vert.x2.nxv4i32(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z28test_svreadz_ver_za32_s32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.vert.x2.nxv4i32(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svint32x2_t test_svreadz_ver_za32_s32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za32_s32_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_ver_za32_u32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.vert.x2.nxv4i32(i32 2, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z28test_svreadz_ver_za32_u32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.vert.x2.nxv4i32(i32 2, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svuint32x2_t test_svreadz_ver_za32_u32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za32_u32_vg2(2, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float> } @test_svreadz_ver_za32_f32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.vert.x2.nxv4f32(i32 3, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float> } @_Z28test_svreadz_ver_za32_f32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.vert.x2.nxv4f32(i32 3, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
svfloat32x2_t test_svreadz_ver_za32_f32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za32_f32_vg2(3, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_ver_za64_s64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.vert.x2.nxv2i64(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z28test_svreadz_ver_za64_s64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.vert.x2.nxv2i64(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svint64x2_t test_svreadz_ver_za64_s64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za64_s64_vg2(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_ver_za64_u64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.vert.x2.nxv2i64(i32 4, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z28test_svreadz_ver_za64_u64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.vert.x2.nxv2i64(i32 4, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svuint64x2_t test_svreadz_ver_za64_u64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za64_u64_vg2(4, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double> } @test_svreadz_ver_za64_f64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.vert.x2.nxv2f64(i32 7, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double> } @_Z28test_svreadz_ver_za64_f64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.vert.x2.nxv2f64(i32 7, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
svfloat64x2_t test_svreadz_ver_za64_f64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za64_f64_vg2(7, slice);
}


//
// X4 - hor
// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_hor_za8_s8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z26test_svreadz_hor_za8_s8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svint8x4_t test_svreadz_hor_za8_s8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_s8_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_hor_za8_u8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z26test_svreadz_hor_za8_u8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svuint8x4_t test_svreadz_hor_za8_u8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_u8_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_hor_za8_mf8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z27test_svreadz_hor_za8_mf8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.horiz.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svmfloat8x4_t test_svreadz_hor_za8_mf8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_mf8_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_hor_za16_s16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.horiz.x4.nxv8i16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z28test_svreadz_hor_za16_s16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.horiz.x4.nxv8i16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svint16x4_t test_svreadz_hor_za16_s16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_s16_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_hor_za16_u16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.horiz.x4.nxv8i16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z28test_svreadz_hor_za16_u16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.horiz.x4.nxv8i16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svuint16x4_t test_svreadz_hor_za16_u16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_u16_vg4(1, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @test_svreadz_hor_za16_f16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.horiz.x4.nxv8f16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @_Z28test_svreadz_hor_za16_f16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.horiz.x4.nxv8f16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
svfloat16x4_t test_svreadz_hor_za16_f16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_f16_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @test_svreadz_hor_za16_bf16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.horiz.x4.nxv8bf16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @_Z29test_svreadz_hor_za16_bf16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.horiz.x4.nxv8bf16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
svbfloat16x4_t test_svreadz_hor_za16_bf16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_bf16_vg4(1, slice);
}


// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_hor_za32_s32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.horiz.x4.nxv4i32(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z28test_svreadz_hor_za32_s32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.horiz.x4.nxv4i32(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svint32x4_t test_svreadz_hor_za32_s32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_s32_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_hor_za32_u32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.horiz.x4.nxv4i32(i32 2, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z28test_svreadz_hor_za32_u32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.horiz.x4.nxv4i32(i32 2, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svuint32x4_t test_svreadz_hor_za32_u32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_u32_vg4(2, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @test_svreadz_hor_za32_f32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.horiz.x4.nxv4f32(i32 3, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @_Z28test_svreadz_hor_za32_f32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.horiz.x4.nxv4f32(i32 3, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
svfloat32x4_t test_svreadz_hor_za32_f32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_f32_vg4(3, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_hor_za64_s64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.horiz.x4.nxv2i64(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z28test_svreadz_hor_za64_s64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.horiz.x4.nxv2i64(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svint64x4_t test_svreadz_hor_za64_s64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_s64_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_hor_za64_u64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.horiz.x4.nxv2i64(i32 4, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z28test_svreadz_hor_za64_u64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.horiz.x4.nxv2i64(i32 4, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svuint64x4_t test_svreadz_hor_za64_u64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_u64_vg4(4, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @test_svreadz_hor_za64_f64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.horiz.x4.nxv2f64(i32 7, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @_Z28test_svreadz_hor_za64_f64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.horiz.x4.nxv2f64(i32 7, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
svfloat64x4_t test_svreadz_hor_za64_f64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_f64_vg4(7, slice);
}

//
// X4 - ver
// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_ver_za8_s8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z26test_svreadz_ver_za8_s8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svint8x4_t test_svreadz_ver_za8_s8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za8_s8_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_ver_za8_u8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z26test_svreadz_ver_za8_u8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svuint8x4_t test_svreadz_ver_za8_u8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za8_u8_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_ver_za8_mf8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z27test_svreadz_ver_za8_mf8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.vert.x4.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svmfloat8x4_t test_svreadz_ver_za8_mf8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za8_mf8_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_ver_za16_s16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.vert.x4.nxv8i16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z28test_svreadz_ver_za16_s16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.vert.x4.nxv8i16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svint16x4_t test_svreadz_ver_za16_s16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za16_s16_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_ver_za16_u16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.vert.x4.nxv8i16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z28test_svreadz_ver_za16_u16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.vert.x4.nxv8i16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svuint16x4_t test_svreadz_ver_za16_u16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za16_u16_vg4(1, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @test_svreadz_ver_za16_f16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.vert.x4.nxv8f16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @_Z28test_svreadz_ver_za16_f16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.vert.x4.nxv8f16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
svfloat16x4_t test_svreadz_ver_za16_f16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za16_f16_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @test_svreadz_ver_za16_bf16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.vert.x4.nxv8bf16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @_Z29test_svreadz_ver_za16_bf16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.vert.x4.nxv8bf16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
svbfloat16x4_t test_svreadz_ver_za16_bf16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za16_bf16_vg4(1, slice);
}


// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_ver_za32_s32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.vert.x4.nxv4i32(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z28test_svreadz_ver_za32_s32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.vert.x4.nxv4i32(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svint32x4_t test_svreadz_ver_za32_s32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za32_s32_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_ver_za32_u32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.vert.x4.nxv4i32(i32 2, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z28test_svreadz_ver_za32_u32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.vert.x4.nxv4i32(i32 2, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svuint32x4_t test_svreadz_ver_za32_u32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za32_u32_vg4(2, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @test_svreadz_ver_za32_f32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.vert.x4.nxv4f32(i32 3, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @_Z28test_svreadz_ver_za32_f32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.vert.x4.nxv4f32(i32 3, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
svfloat32x4_t test_svreadz_ver_za32_f32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za32_f32_vg4(3, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_ver_za64_s64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.vert.x4.nxv2i64(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z28test_svreadz_ver_za64_s64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.vert.x4.nxv2i64(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svint64x4_t test_svreadz_ver_za64_s64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za64_s64_vg4(0, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_ver_za64_u64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.vert.x4.nxv2i64(i32 4, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z28test_svreadz_ver_za64_u64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.vert.x4.nxv2i64(i32 4, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svuint64x4_t test_svreadz_ver_za64_u64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za64_u64_vg4(4, slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @test_svreadz_ver_za64_f64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.vert.x4.nxv2f64(i32 7, i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @_Z28test_svreadz_ver_za64_f64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.vert.x4.nxv2f64(i32 7, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
svfloat64x4_t test_svreadz_ver_za64_f64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_ver_za64_f64_vg4(7, slice);
}

// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svreadz_hor_za8_s8(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z23test_svreadz_hor_za8_s8j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svint8_t test_svreadz_hor_za8_s8(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_s8(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svreadz_hor_za8_u8(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z23test_svreadz_hor_za8_u8j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svreadz_hor_za8_u8(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_u8(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svreadz_hor_za8_mf8(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z24test_svreadz_hor_za8_mf8j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svmfloat8_t test_svreadz_hor_za8_mf8(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za8_mf8(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 8 x i16> @test_svreadz_hor_za16_s16(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sme.readz.horiz.nxv8i16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 8 x i16> @_Z25test_svreadz_hor_za16_s16j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sme.readz.horiz.nxv8i16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svint16_t test_svreadz_hor_za16_s16(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_s16(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 8 x i16> @test_svreadz_hor_za16_u16(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sme.readz.horiz.nxv8i16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 8 x i16> @_Z25test_svreadz_hor_za16_u16j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sme.readz.horiz.nxv8i16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svreadz_hor_za16_u16(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_u16(1, slice);
}

// CHECK-LABEL: define dso_local <vscale x 8 x half> @test_svreadz_hor_za16_f16(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sme.readz.horiz.nxv8f16(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 8 x half> @_Z25test_svreadz_hor_za16_f16j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sme.readz.horiz.nxv8f16(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
svfloat16_t test_svreadz_hor_za16_f16(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_f16(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 8 x bfloat> @test_svreadz_hor_za16_bf16(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sme.readz.horiz.nxv8bf16(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 8 x bfloat> @_Z26test_svreadz_hor_za16_bf16j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sme.readz.horiz.nxv8bf16(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
svbfloat16_t test_svreadz_hor_za16_bf16(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za16_bf16(1, slice);
}


// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svreadz_hor_za32_s32(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sme.readz.horiz.nxv4i32(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z25test_svreadz_hor_za32_s32j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sme.readz.horiz.nxv4i32(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svint32_t test_svreadz_hor_za32_s32(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_s32(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svreadz_hor_za32_u32(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sme.readz.horiz.nxv4i32(i32 2, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z25test_svreadz_hor_za32_u32j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sme.readz.horiz.nxv4i32(i32 2, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svreadz_hor_za32_u32(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_u32(2, slice);
}

// CHECK-LABEL: define dso_local <vscale x 4 x float> @test_svreadz_hor_za32_f32(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sme.readz.horiz.nxv4f32(i32 3, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 4 x float> @_Z25test_svreadz_hor_za32_f32j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sme.readz.horiz.nxv4f32(i32 3, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
svfloat32_t test_svreadz_hor_za32_f32(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za32_f32(3, slice);
}

// CHECK-LABEL: define dso_local <vscale x 2 x i64> @test_svreadz_hor_za64_s64(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sme.readz.horiz.nxv2i64(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 2 x i64> @_Z25test_svreadz_hor_za64_s64j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sme.readz.horiz.nxv2i64(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
svint64_t test_svreadz_hor_za64_s64(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_s64(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 2 x i64> @test_svreadz_hor_za64_u64(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sme.readz.horiz.nxv2i64(i32 4, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 2 x i64> @_Z25test_svreadz_hor_za64_u64j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sme.readz.horiz.nxv2i64(i32 4, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svreadz_hor_za64_u64(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_u64(4, slice);
}

// CHECK-LABEL: define dso_local <vscale x 2 x double> @test_svreadz_hor_za64_f64(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sme.readz.horiz.nxv2f64(i32 7, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 2 x double> @_Z25test_svreadz_hor_za64_f64j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sme.readz.horiz.nxv2f64(i32 7, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
//
svfloat64_t test_svreadz_hor_za64_f64(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za64_f64(7, slice);
}

// ZA128
// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svreadz_hor_za128_s8(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.q.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z25test_svreadz_hor_za128_s8j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.q.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svint8_t test_svreadz_hor_za128_s8(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_s8(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svreadz_hor_za128_u8(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.q.horiz.nxv16i8(i32 1, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z25test_svreadz_hor_za128_u8j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.q.horiz.nxv16i8(i32 1, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svreadz_hor_za128_u8(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_u8(1, slice);
}

// CHECK-LABEL: define dso_local <vscale x 16 x i8> @test_svreadz_hor_za128_mf8(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.q.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 16 x i8> @_Z26test_svreadz_hor_za128_mf8j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sme.readz.q.horiz.nxv16i8(i32 0, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svmfloat8_t test_svreadz_hor_za128_mf8(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_mf8(0, slice);
}

// CHECK-LABEL: define dso_local <vscale x 8 x i16> @test_svreadz_hor_za128_s16(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sme.readz.q.horiz.nxv8i16(i32 2, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 8 x i16> @_Z26test_svreadz_hor_za128_s16j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sme.readz.q.horiz.nxv8i16(i32 2, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svint16_t test_svreadz_hor_za128_s16(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_s16(2, slice);
}

// CHECK-LABEL: define dso_local <vscale x 8 x i16> @test_svreadz_hor_za128_u16(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sme.readz.q.horiz.nxv8i16(i32 3, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 8 x i16> @_Z26test_svreadz_hor_za128_u16j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sme.readz.q.horiz.nxv8i16(i32 3, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svreadz_hor_za128_u16(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_u16(3, slice);
}

// CHECK-LABEL: define dso_local <vscale x 8 x half> @test_svreadz_hor_za128_f16(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sme.readz.q.horiz.nxv8f16(i32 4, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 8 x half> @_Z26test_svreadz_hor_za128_f16j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sme.readz.q.horiz.nxv8f16(i32 4, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
svfloat16_t test_svreadz_hor_za128_f16(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_f16(4, slice);
}

// CHECK-LABEL: define dso_local <vscale x 8 x bfloat> @test_svreadz_hor_za128_bf16(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sme.readz.q.horiz.nxv8bf16(i32 5, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 8 x bfloat> @_Z27test_svreadz_hor_za128_bf16j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sme.readz.q.horiz.nxv8bf16(i32 5, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
svbfloat16_t test_svreadz_hor_za128_bf16(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_bf16(5, slice);
}


// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svreadz_hor_za128_s32(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sme.readz.q.horiz.nxv4i32(i32 6, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z26test_svreadz_hor_za128_s32j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sme.readz.q.horiz.nxv4i32(i32 6, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svint32_t test_svreadz_hor_za128_s32(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_s32(6, slice);
}

// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svreadz_hor_za128_u32(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sme.readz.q.horiz.nxv4i32(i32 7, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z26test_svreadz_hor_za128_u32j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sme.readz.q.horiz.nxv4i32(i32 7, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svreadz_hor_za128_u32(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_u32(7, slice);
}

// CHECK-LABEL: define dso_local <vscale x 4 x float> @test_svreadz_hor_za128_f32(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sme.readz.q.horiz.nxv4f32(i32 8, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 4 x float> @_Z26test_svreadz_hor_za128_f32j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sme.readz.q.horiz.nxv4f32(i32 8, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
svfloat32_t test_svreadz_hor_za128_f32(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_f32(8, slice);
}

// CHECK-LABEL: define dso_local <vscale x 2 x i64> @test_svreadz_hor_za128_s64(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sme.readz.q.horiz.nxv2i64(i32 13, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 2 x i64> @_Z26test_svreadz_hor_za128_s64j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sme.readz.q.horiz.nxv2i64(i32 13, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
svint64_t test_svreadz_hor_za128_s64(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_s64(13, slice);
}
// CHECK-LABEL: define dso_local <vscale x 2 x i64> @test_svreadz_hor_za128_u64(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sme.readz.q.horiz.nxv2i64(i32 14, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 2 x i64> @_Z26test_svreadz_hor_za128_u64j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sme.readz.q.horiz.nxv2i64(i32 14, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svreadz_hor_za128_u64(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_u64(14, slice);
}

// CHECK-LABEL: define dso_local <vscale x 2 x double> @test_svreadz_hor_za128_f64(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sme.readz.q.horiz.nxv2f64(i32 15, i32 [[SLICE]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local <vscale x 2 x double> @_Z26test_svreadz_hor_za128_f64j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sme.readz.q.horiz.nxv2f64(i32 15, i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
//
svfloat64_t test_svreadz_hor_za128_f64(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_hor_za128_f64(15, slice);
}

// MOVAZ Array to Tile
//
// X2
//

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_za8_s8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x2.nxv16i8(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z22test_svreadz_za8_s8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x2.nxv16i8(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svint8x2_t test_svreadz_za8_s8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za8_s8_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_za8_u8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x2.nxv16i8(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z22test_svreadz_za8_u8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x2.nxv16i8(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svuint8x2_t test_svreadz_za8_u8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za8_u8_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_za8_mf8_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x2.nxv16i8(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z23test_svreadz_za8_mf8_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x2.nxv16i8(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svmfloat8x2_t test_svreadz_za8_mf8_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za8_mf8_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_za16_s16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.x2.nxv8i16(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z24test_svreadz_za16_s16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.x2.nxv8i16(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svint16x2_t test_svreadz_za16_s16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za16_s16_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_za16_u16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.x2.nxv8i16(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z24test_svreadz_za16_u16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.x2.nxv8i16(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svuint16x2_t test_svreadz_za16_u16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za16_u16_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_za32_s32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.x2.nxv4i32(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z24test_svreadz_za32_s32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.x2.nxv4i32(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svint32x2_t test_svreadz_za32_s32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za32_s32_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_za32_u32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.x2.nxv4i32(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z24test_svreadz_za32_u32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.x2.nxv4i32(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svuint32x2_t test_svreadz_za32_u32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za32_u32_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_za64_s64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.x2.nxv2i64(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z24test_svreadz_za64_s64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.x2.nxv2i64(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svint64x2_t test_svreadz_za64_s64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za64_s64_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_za64_u64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.x2.nxv2i64(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z24test_svreadz_za64_u64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.x2.nxv2i64(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svuint64x2_t test_svreadz_za64_u64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za64_u64_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @test_svreadz_za16_bf16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.x2.nxv8bf16(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @_Z25test_svreadz_za16_bf16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.x2.nxv8bf16(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
svbfloat16x2_t test_svreadz_za16_bf16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za16_bf16_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half> } @test_svreadz_za16_f16_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.x2.nxv8f16(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half> } @_Z24test_svreadz_za16_f16_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.x2.nxv8f16(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
svfloat16x2_t test_svreadz_za16_f16_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za16_f16_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float> } @test_svreadz_za32_f32_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.x2.nxv4f32(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float> } @_Z24test_svreadz_za32_f32_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.x2.nxv4f32(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
svfloat32x2_t test_svreadz_za32_f32_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za32_f32_vg1x2(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double> } @test_svreadz_za64_f64_x2(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.x2.nxv2f64(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double> } @_Z24test_svreadz_za64_f64_x2j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.x2.nxv2f64(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
svfloat64x2_t test_svreadz_za64_f64_x2(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za64_f64_vg1x2(slice);
}

//
// X4
//

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_za8_s8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x4.nxv16i8(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z22test_svreadz_za8_s8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x4.nxv16i8(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svint8x4_t test_svreadz_za8_s8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za8_s8_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_za8_u8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x4.nxv16i8(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z22test_svreadz_za8_u8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x4.nxv16i8(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svuint8x4_t test_svreadz_za8_u8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za8_u8_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @test_svreadz_za8_mf8_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x4.nxv16i8(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @_Z23test_svreadz_za8_mf8_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sme.readz.x4.nxv16i8(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[TMP0]]
//
svmfloat8x4_t test_svreadz_za8_mf8_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za8_mf8_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_za16_s16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.x4.nxv8i16(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z24test_svreadz_za16_s16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.x4.nxv8i16(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svint16x4_t test_svreadz_za16_s16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za16_s16_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @test_svreadz_za16_u16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.x4.nxv8i16(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @_Z24test_svreadz_za16_u16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } @llvm.aarch64.sme.readz.x4.nxv8i16(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16> } [[TMP0]]
//
svuint16x4_t test_svreadz_za16_u16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za16_u16_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_za32_s32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.x4.nxv4i32(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z24test_svreadz_za32_s32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.x4.nxv4i32(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svint32x4_t test_svreadz_za32_s32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za32_s32_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @test_svreadz_za32_u32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.x4.nxv4i32(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @_Z24test_svreadz_za32_u32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.aarch64.sme.readz.x4.nxv4i32(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP0]]
//
svuint32x4_t test_svreadz_za32_u32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za32_u32_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_za64_s64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.x4.nxv2i64(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z24test_svreadz_za64_s64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.x4.nxv2i64(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svint64x4_t test_svreadz_za64_s64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za64_s64_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @test_svreadz_za64_u64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.x4.nxv2i64(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @_Z24test_svreadz_za64_u64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sme.readz.x4.nxv2i64(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[TMP0]]
//
svuint64x4_t test_svreadz_za64_u64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za64_u64_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @test_svreadz_za16_bf16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.x4.nxv8bf16(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @_Z25test_svreadz_za16_bf16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.readz.x4.nxv8bf16(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } [[TMP0]]
//
svbfloat16x4_t test_svreadz_za16_bf16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za16_bf16_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @test_svreadz_za16_f16_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.x4.nxv8f16(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @_Z24test_svreadz_za16_f16_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.readz.x4.nxv8f16(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } [[TMP0]]
//
svfloat16x4_t test_svreadz_za16_f16_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za16_f16_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @test_svreadz_za32_f32_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.x4.nxv4f32(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @_Z24test_svreadz_za32_f32_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sme.readz.x4.nxv4f32(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } [[TMP0]]
//
svfloat32x4_t test_svreadz_za32_f32_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za32_f32_vg1x4(slice);
}

// CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @test_svreadz_za64_f64_x4(
// CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.x4.nxv2f64(i32 [[SLICE]])
// CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
// CPP-CHECK-LABEL: define dso_local { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @_Z24test_svreadz_za64_f64_x4j(
// CPP-CHECK-SAME: i32 noundef [[SLICE:%.*]]) #[[ATTR0]] {
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sme.readz.x4.nxv2f64(i32 [[SLICE]])
// CPP-CHECK-NEXT:    ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } [[TMP0]]
//
svfloat64x4_t test_svreadz_za64_f64_x4(uint32_t slice) __arm_streaming __arm_inout("za")
{
   return svreadz_za64_f64_vg1x4(slice);
}