// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sme -target-feature +sme2 -target-feature +lut -O1 -Werror -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sve -target-feature +sve2 -target-feature +lut -O1 -Werror -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sve -target-feature +sve2 -target-feature +lut -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sve -target-feature +sve2 -target-feature +lut -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme -target-feature +sme2 -target-feature +lut -O1 -Werror -Wall -o /dev/null %s
#include <arm_sve.h>

#if defined __ARM_FEATURE_SME
#define MODE_ATTR __arm_streaming
#else
#define MODE_ATTR
#endif

#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.
#define SVE_ACLE_FUNC(A1,A2_UNUSED) A1
#else
#define SVE_ACLE_FUNC(A1,A2) A1##A2
#endif

// SME-CHECK-LABEL: @test_svluti2_lane_s8(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// SME-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
// CHECK-LABEL: @test_svluti2_lane_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svluti2_lane_s8u10__SVInt8_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svint8_t test_svluti2_lane_s8(svint8_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti2_lane,_s8)(table, indices, 0);
}

// SME-CHECK-LABEL: @test_svluti2_lane_u8(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
// SME-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
// CHECK-LABEL: @test_svluti2_lane_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svluti2_lane_u8u11__SVUint8_tS_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svluti2_lane_u8(svuint8_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti2_lane,_u8)(table, indices, 3);
}

// SME-CHECK-LABEL: @test_svluti2_lane_s16(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// SME-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
// CHECK-LABEL: @test_svluti2_lane_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z21test_svluti2_lane_s16u11__SVInt16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svint16_t test_svluti2_lane_s16(svint16_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti2_lane,_s16)(table, indices, 0);
}

// SME-CHECK-LABEL: @test_svluti2_lane_u16(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
// SME-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
// CHECK-LABEL: @test_svluti2_lane_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z21test_svluti2_lane_u16u12__SVUint16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svluti2_lane_u16(svuint16_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti2_lane,_u16)(table, indices, 7);
}

// SME-CHECK-LABEL: @test_svluti2_lane_f16(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti2.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
// SME-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
// CHECK-LABEL: @test_svluti2_lane_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti2.lane.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z21test_svluti2_lane_f16u13__SVFloat16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti2.lane.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
svfloat16_t test_svluti2_lane_f16(svfloat16_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti2_lane,_f16)(table, indices, 5);
}

// SME-CHECK-LABEL: @test_svluti2_lane_bf16(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti2.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// SME-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
// CHECK-LABEL: @test_svluti2_lane_bf16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti2.lane.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z22test_svluti2_lane_bf16u14__SVBfloat16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti2.lane.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
svbfloat16_t test_svluti2_lane_bf16(svbfloat16_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti2_lane,_bf16)(table, indices, 2);
}

// SME-CHECK-LABEL: @test_svluti4_lane_s8(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// SME-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
// CHECK-LABEL: @test_svluti4_lane_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svluti4_lane_s8u10__SVInt8_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svint8_t test_svluti4_lane_s8(svint8_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_s8)(table, indices, 0);
}

// SME-CHECK-LABEL: @test_svluti4_lane_u8(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
// SME-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
// CHECK-LABEL: @test_svluti4_lane_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svluti4_lane_u8u11__SVUint8_tS_(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svluti4_lane_u8(svuint8_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_u8)(table, indices, 1);
}

// SME-CHECK-LABEL: @test_svluti4_lane_s16(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// SME-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
// CHECK-LABEL: @test_svluti4_lane_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z21test_svluti4_lane_s16u11__SVInt16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svint16_t test_svluti4_lane_s16(svint16_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_s16)(table, indices, 0);
}

// SME-CHECK-LABEL: @test_svluti4_lane_u16(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
// SME-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
// CHECK-LABEL: @test_svluti4_lane_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z21test_svluti4_lane_u16u12__SVUint16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svluti4_lane_u16(svuint16_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_u16)(table, indices, 3);
}

// SME-CHECK-LABEL: @test_svluti4_lane_f16(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
// SME-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
// CHECK-LABEL: @test_svluti4_lane_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.lane.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z21test_svluti4_lane_f16u13__SVFloat16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.lane.nxv8f16(<vscale x 8 x half> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
svfloat16_t test_svluti4_lane_f16(svfloat16_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_f16)(table, indices, 2);
}

// SME-CHECK-LABEL: @test_svluti4_lane_bf16(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// SME-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
// CHECK-LABEL: @test_svluti4_lane_bf16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.lane.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z22test_svluti4_lane_bf16u14__SVBfloat16_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.lane.nxv8bf16(<vscale x 8 x bfloat> [[TABLE:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
svbfloat16_t test_svluti4_lane_bf16(svbfloat16_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_bf16)(table, indices, 1);
}

// SME-CHECK-LABEL: @test_svluti4_lane_s16_x2(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE:%.*]], i64 0)
// SME-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE]], i64 8)
// SME-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.x2.nxv8i16(<vscale x 8 x i16> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// SME-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
// CHECK-LABEL: @test_svluti4_lane_s16_x2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.x2.nxv8i16(<vscale x 8 x i16> [[TABLE_COERCE0:%.*]], <vscale x 8 x i16> [[TABLE_COERCE1:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z24test_svluti4_lane_s16_x211svint16x2_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.x2.nxv8i16(<vscale x 8 x i16> [[TABLE_COERCE0:%.*]], <vscale x 8 x i16> [[TABLE_COERCE1:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svint16_t test_svluti4_lane_s16_x2(svint16x2_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_s16_x2)(table, indices, 0);
}

// SME-CHECK-LABEL: @test_svluti4_lane_u16_x2(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE:%.*]], i64 0)
// SME-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv16i16(<vscale x 16 x i16> [[TABLE]], i64 8)
// SME-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.x2.nxv8i16(<vscale x 8 x i16> [[TMP0]], <vscale x 8 x i16> [[TMP1]], <vscale x 16 x i8> [[INDICES:%.*]], i32 7)
// SME-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP2]]
// CHECK-LABEL: @test_svluti4_lane_u16_x2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.x2.nxv8i16(<vscale x 8 x i16> [[TABLE_COERCE0:%.*]], <vscale x 8 x i16> [[TABLE_COERCE1:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z24test_svluti4_lane_u16_x212svuint16x2_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.x2.nxv8i16(<vscale x 8 x i16> [[TABLE_COERCE0:%.*]], <vscale x 8 x i16> [[TABLE_COERCE1:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 3)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svluti4_lane_u16_x2(svuint16x2_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_u16_x2)(table, indices, 3);
}

// SME-CHECK-LABEL: @test_svluti4_lane_f16_x2(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.vector.extract.nxv8f16.nxv16f16(<vscale x 16 x half> [[TABLE:%.*]], i64 0)
// SME-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.vector.extract.nxv8f16.nxv16f16(<vscale x 16 x half> [[TABLE]], i64 8)
// SME-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.x2.nxv8f16(<vscale x 8 x half> [[TMP0]], <vscale x 8 x half> [[TMP1]], <vscale x 16 x i8> [[INDICES:%.*]], i32 5)
// SME-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP2]]
// CHECK-LABEL: @test_svluti4_lane_f16_x2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.lane.x2.nxv8f16(<vscale x 8 x half> [[TABLE_COERCE0:%.*]], <vscale x 8 x half> [[TABLE_COERCE1:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z24test_svluti4_lane_f16_x213svfloat16x2_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.lane.x2.nxv8f16(<vscale x 8 x half> [[TABLE_COERCE0:%.*]], <vscale x 8 x half> [[TABLE_COERCE1:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
svfloat16_t test_svluti4_lane_f16_x2(svfloat16x2_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_f16_x2)(table, indices, 2);
}

// SME-CHECK-LABEL: @test_svluti4_lane_bf16_x2(
// SME-CHECK-NEXT:  entry:
// SME-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.vector.extract.nxv8bf16.nxv16bf16(<vscale x 16 x bfloat> [[TABLE:%.*]], i64 0)
// SME-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.vector.extract.nxv8bf16.nxv16bf16(<vscale x 16 x bfloat> [[TABLE]], i64 8)
// SME-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.x2.nxv8bf16(<vscale x 8 x bfloat> [[TMP0]], <vscale x 8 x bfloat> [[TMP1]], <vscale x 16 x i8> [[INDICES:%.*]], i32 2)
// SME-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP2]]
// CHECK-LABEL: @test_svluti4_lane_bf16_x2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.lane.x2.nxv8bf16(<vscale x 8 x bfloat> [[TABLE_COERCE0:%.*]], <vscale x 8 x bfloat> [[TABLE_COERCE1:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z25test_svluti4_lane_bf16_x214svbfloat16x2_tu11__SVUint8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.lane.x2.nxv8bf16(<vscale x 8 x bfloat> [[TABLE_COERCE0:%.*]], <vscale x 8 x bfloat> [[TABLE_COERCE1:%.*]], <vscale x 16 x i8> [[INDICES:%.*]], i32 1)
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP0]]
//
svbfloat16_t test_svluti4_lane_bf16_x2(svbfloat16x2_t table, svuint8_t indices) MODE_ATTR{
    return SVE_ACLE_FUNC(svluti4_lane,_bf16_x2)(table, indices, 1);
}