xref: /llvm-project/clang/test/CodeGen/AArch64/sve-intrinsics/acle_sve_dupq.c (revision 207e5ccceec8d3cc3f32723e78f2a142bc61b07d)

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -S -disable-O0-optnone -Werror -o /dev/null %s
// RUN: %clang_cc1 -triple aarch64 -target-feature +sme -S -disable-O0-optnone -Werror -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,A3,A4_UNUSED) A1##A3
#else
#define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
#endif

// CHECK-LABEL: @test_svdupq_lane_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z19test_svdupq_lane_s8u10__SVInt8_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svint8_t test_svdupq_lane_s8(svint8_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_s8,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_s16u11__SVInt16_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svint16_t test_svdupq_lane_s16(svint16_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_s16,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_s32u11__SVInt32_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svint32_t test_svdupq_lane_s32(svint32_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_s32,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_s64u11__SVInt64_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
svint64_t test_svdupq_lane_s64(svint64_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_s64,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z19test_svdupq_lane_u8u11__SVUint8_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svdupq_lane_u8(svuint8_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_u8,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_u16u12__SVUint16_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svdupq_lane_u16(svuint16_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_u16,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_u32u12__SVUint32_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svdupq_lane_u32(svuint32_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_u32,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_u64u12__SVUint64_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svdupq_lane_u64(svuint64_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_u64,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.dupq.lane.nxv8f16(<vscale x 8 x half> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_f16u13__SVFloat16_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.dupq.lane.nxv8f16(<vscale x 8 x half> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP0]]
//
svfloat16_t test_svdupq_lane_f16(svfloat16_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_f16,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_f32u13__SVFloat32_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP0]]
//
svfloat32_t test_svdupq_lane_f32(svfloat32_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_f32,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_lane_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.dupq.lane.nxv2f64(<vscale x 2 x double> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z20test_svdupq_lane_f64u13__SVFloat64_tm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.dupq.lane.nxv2f64(<vscale x 2 x double> [[DATA:%.*]], i64 [[INDEX:%.*]])
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP0]]
//
svfloat64_t test_svdupq_lane_f64(svfloat64_t data, uint64_t index) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq_lane,_f64,,)(data, index);
}

// CHECK-LABEL: @test_svdupq_n_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <16 x i8> poison, i8 [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <16 x i8> [[TMP0]], i8 [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i8> [[TMP1]], i8 [[X2:%.*]], i64 2
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <16 x i8> [[TMP2]], i8 [[X3:%.*]], i64 3
// CHECK-NEXT:    [[TMP4:%.*]] = insertelement <16 x i8> [[TMP3]], i8 [[X4:%.*]], i64 4
// CHECK-NEXT:    [[TMP5:%.*]] = insertelement <16 x i8> [[TMP4]], i8 [[X5:%.*]], i64 5
// CHECK-NEXT:    [[TMP6:%.*]] = insertelement <16 x i8> [[TMP5]], i8 [[X6:%.*]], i64 6
// CHECK-NEXT:    [[TMP7:%.*]] = insertelement <16 x i8> [[TMP6]], i8 [[X7:%.*]], i64 7
// CHECK-NEXT:    [[TMP8:%.*]] = insertelement <16 x i8> [[TMP7]], i8 [[X8:%.*]], i64 8
// CHECK-NEXT:    [[TMP9:%.*]] = insertelement <16 x i8> [[TMP8]], i8 [[X9:%.*]], i64 9
// CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i8> [[TMP9]], i8 [[X10:%.*]], i64 10
// CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x i8> [[TMP10]], i8 [[X11:%.*]], i64 11
// CHECK-NEXT:    [[TMP12:%.*]] = insertelement <16 x i8> [[TMP11]], i8 [[X12:%.*]], i64 12
// CHECK-NEXT:    [[TMP13:%.*]] = insertelement <16 x i8> [[TMP12]], i8 [[X13:%.*]], i64 13
// CHECK-NEXT:    [[TMP14:%.*]] = insertelement <16 x i8> [[TMP13]], i8 [[X14:%.*]], i64 14
// CHECK-NEXT:    [[TMP15:%.*]] = insertelement <16 x i8> [[TMP14]], i8 [[X15:%.*]], i64 15
// CHECK-NEXT:    [[TMP16:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> [[TMP15]], i64 0)
// CHECK-NEXT:    [[TMP17:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP16]], i64 0)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP17]]
//
// CPP-CHECK-LABEL: @_Z16test_svdupq_n_s8aaaaaaaaaaaaaaaa(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <16 x i8> poison, i8 [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <16 x i8> [[TMP0]], i8 [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i8> [[TMP1]], i8 [[X2:%.*]], i64 2
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <16 x i8> [[TMP2]], i8 [[X3:%.*]], i64 3
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = insertelement <16 x i8> [[TMP3]], i8 [[X4:%.*]], i64 4
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = insertelement <16 x i8> [[TMP4]], i8 [[X5:%.*]], i64 5
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = insertelement <16 x i8> [[TMP5]], i8 [[X6:%.*]], i64 6
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = insertelement <16 x i8> [[TMP6]], i8 [[X7:%.*]], i64 7
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = insertelement <16 x i8> [[TMP7]], i8 [[X8:%.*]], i64 8
// CPP-CHECK-NEXT:    [[TMP9:%.*]] = insertelement <16 x i8> [[TMP8]], i8 [[X9:%.*]], i64 9
// CPP-CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i8> [[TMP9]], i8 [[X10:%.*]], i64 10
// CPP-CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x i8> [[TMP10]], i8 [[X11:%.*]], i64 11
// CPP-CHECK-NEXT:    [[TMP12:%.*]] = insertelement <16 x i8> [[TMP11]], i8 [[X12:%.*]], i64 12
// CPP-CHECK-NEXT:    [[TMP13:%.*]] = insertelement <16 x i8> [[TMP12]], i8 [[X13:%.*]], i64 13
// CPP-CHECK-NEXT:    [[TMP14:%.*]] = insertelement <16 x i8> [[TMP13]], i8 [[X14:%.*]], i64 14
// CPP-CHECK-NEXT:    [[TMP15:%.*]] = insertelement <16 x i8> [[TMP14]], i8 [[X15:%.*]], i64 15
// CPP-CHECK-NEXT:    [[TMP16:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> [[TMP15]], i64 0)
// CPP-CHECK-NEXT:    [[TMP17:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP16]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP17]]
//
svint8_t test_svdupq_n_s8(int8_t x0, int8_t x1, int8_t x2, int8_t x3,
                          int8_t x4, int8_t x5, int8_t x6, int8_t x7,
                          int8_t x8, int8_t x9, int8_t x10, int8_t x11,
                          int8_t x12, int8_t x13, int8_t x14, int8_t x15) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_s8,)(x0, x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14, x15);
}

// CHECK-LABEL: @test_svdupq_n_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <8 x i16> poison, i16 [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x i16> [[TMP0]], i16 [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i16> [[TMP1]], i16 [[X2:%.*]], i64 2
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <8 x i16> [[TMP2]], i16 [[X3:%.*]], i64 3
// CHECK-NEXT:    [[TMP4:%.*]] = insertelement <8 x i16> [[TMP3]], i16 [[X4:%.*]], i64 4
// CHECK-NEXT:    [[TMP5:%.*]] = insertelement <8 x i16> [[TMP4]], i16 [[X5:%.*]], i64 5
// CHECK-NEXT:    [[TMP6:%.*]] = insertelement <8 x i16> [[TMP5]], i16 [[X6:%.*]], i64 6
// CHECK-NEXT:    [[TMP7:%.*]] = insertelement <8 x i16> [[TMP6]], i16 [[X7:%.*]], i64 7
// CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> [[TMP7]], i64 0)
// CHECK-NEXT:    [[TMP9:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP8]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP9]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_s16ssssssss(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <8 x i16> poison, i16 [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x i16> [[TMP0]], i16 [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i16> [[TMP1]], i16 [[X2:%.*]], i64 2
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <8 x i16> [[TMP2]], i16 [[X3:%.*]], i64 3
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = insertelement <8 x i16> [[TMP3]], i16 [[X4:%.*]], i64 4
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = insertelement <8 x i16> [[TMP4]], i16 [[X5:%.*]], i64 5
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = insertelement <8 x i16> [[TMP5]], i16 [[X6:%.*]], i64 6
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = insertelement <8 x i16> [[TMP6]], i16 [[X7:%.*]], i64 7
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> [[TMP7]], i64 0)
// CPP-CHECK-NEXT:    [[TMP9:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP8]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP9]]
//
svint16_t test_svdupq_n_s16(int16_t x0, int16_t x1, int16_t x2, int16_t x3,
                            int16_t x4, int16_t x5, int16_t x6, int16_t x7) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_s16,)(x0, x1, x2, x3, x4, x5, x6, x7);
}

// CHECK-LABEL: @test_svdupq_n_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32> [[TMP0]], i32 [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[X2:%.*]], i64 2
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[X3:%.*]], i64 3
// CHECK-NEXT:    [[TMP4:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> [[TMP3]], i64 0)
// CHECK-NEXT:    [[TMP5:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP4]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP5]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_s32iiii(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32> [[TMP0]], i32 [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[X2:%.*]], i64 2
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[X3:%.*]], i64 3
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> [[TMP3]], i64 0)
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP4]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP5]]
//
svint32_t test_svdupq_n_s32(int32_t x0, int32_t x1, int32_t x2, int32_t x3) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_s32,)(x0, x1, x2, x3);
}

// CHECK-LABEL: @test_svdupq_n_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i64> poison, i64 [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> [[TMP1]], i64 0)
// CHECK-NEXT:    [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_s64ll(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i64> poison, i64 [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> [[TMP1]], i64 0)
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
//
svint64_t test_svdupq_n_s64(int64_t x0, int64_t x1) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq,_n,_s64,)(x0, x1);
}

// CHECK-LABEL: @test_svdupq_n_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <16 x i8> poison, i8 [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <16 x i8> [[TMP0]], i8 [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i8> [[TMP1]], i8 [[X2:%.*]], i64 2
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <16 x i8> [[TMP2]], i8 [[X3:%.*]], i64 3
// CHECK-NEXT:    [[TMP4:%.*]] = insertelement <16 x i8> [[TMP3]], i8 [[X4:%.*]], i64 4
// CHECK-NEXT:    [[TMP5:%.*]] = insertelement <16 x i8> [[TMP4]], i8 [[X5:%.*]], i64 5
// CHECK-NEXT:    [[TMP6:%.*]] = insertelement <16 x i8> [[TMP5]], i8 [[X6:%.*]], i64 6
// CHECK-NEXT:    [[TMP7:%.*]] = insertelement <16 x i8> [[TMP6]], i8 [[X7:%.*]], i64 7
// CHECK-NEXT:    [[TMP8:%.*]] = insertelement <16 x i8> [[TMP7]], i8 [[X8:%.*]], i64 8
// CHECK-NEXT:    [[TMP9:%.*]] = insertelement <16 x i8> [[TMP8]], i8 [[X9:%.*]], i64 9
// CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i8> [[TMP9]], i8 [[X10:%.*]], i64 10
// CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x i8> [[TMP10]], i8 [[X11:%.*]], i64 11
// CHECK-NEXT:    [[TMP12:%.*]] = insertelement <16 x i8> [[TMP11]], i8 [[X12:%.*]], i64 12
// CHECK-NEXT:    [[TMP13:%.*]] = insertelement <16 x i8> [[TMP12]], i8 [[X13:%.*]], i64 13
// CHECK-NEXT:    [[TMP14:%.*]] = insertelement <16 x i8> [[TMP13]], i8 [[X14:%.*]], i64 14
// CHECK-NEXT:    [[TMP15:%.*]] = insertelement <16 x i8> [[TMP14]], i8 [[X15:%.*]], i64 15
// CHECK-NEXT:    [[TMP16:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> [[TMP15]], i64 0)
// CHECK-NEXT:    [[TMP17:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP16]], i64 0)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP17]]
//
// CPP-CHECK-LABEL: @_Z16test_svdupq_n_u8hhhhhhhhhhhhhhhh(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <16 x i8> poison, i8 [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <16 x i8> [[TMP0]], i8 [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i8> [[TMP1]], i8 [[X2:%.*]], i64 2
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <16 x i8> [[TMP2]], i8 [[X3:%.*]], i64 3
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = insertelement <16 x i8> [[TMP3]], i8 [[X4:%.*]], i64 4
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = insertelement <16 x i8> [[TMP4]], i8 [[X5:%.*]], i64 5
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = insertelement <16 x i8> [[TMP5]], i8 [[X6:%.*]], i64 6
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = insertelement <16 x i8> [[TMP6]], i8 [[X7:%.*]], i64 7
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = insertelement <16 x i8> [[TMP7]], i8 [[X8:%.*]], i64 8
// CPP-CHECK-NEXT:    [[TMP9:%.*]] = insertelement <16 x i8> [[TMP8]], i8 [[X9:%.*]], i64 9
// CPP-CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i8> [[TMP9]], i8 [[X10:%.*]], i64 10
// CPP-CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x i8> [[TMP10]], i8 [[X11:%.*]], i64 11
// CPP-CHECK-NEXT:    [[TMP12:%.*]] = insertelement <16 x i8> [[TMP11]], i8 [[X12:%.*]], i64 12
// CPP-CHECK-NEXT:    [[TMP13:%.*]] = insertelement <16 x i8> [[TMP12]], i8 [[X13:%.*]], i64 13
// CPP-CHECK-NEXT:    [[TMP14:%.*]] = insertelement <16 x i8> [[TMP13]], i8 [[X14:%.*]], i64 14
// CPP-CHECK-NEXT:    [[TMP15:%.*]] = insertelement <16 x i8> [[TMP14]], i8 [[X15:%.*]], i64 15
// CPP-CHECK-NEXT:    [[TMP16:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> [[TMP15]], i64 0)
// CPP-CHECK-NEXT:    [[TMP17:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP16]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP17]]
//
svuint8_t test_svdupq_n_u8(uint8_t x0, uint8_t x1, uint8_t x2, uint8_t x3,
                           uint8_t x4, uint8_t x5, uint8_t x6, uint8_t x7,
                           uint8_t x8, uint8_t x9, uint8_t x10, uint8_t x11,
                           uint8_t x12, uint8_t x13, uint8_t x14, uint8_t x15) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_u8,)(x0, x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14, x15);
}

// CHECK-LABEL: @test_svdupq_n_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <8 x i16> poison, i16 [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x i16> [[TMP0]], i16 [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i16> [[TMP1]], i16 [[X2:%.*]], i64 2
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <8 x i16> [[TMP2]], i16 [[X3:%.*]], i64 3
// CHECK-NEXT:    [[TMP4:%.*]] = insertelement <8 x i16> [[TMP3]], i16 [[X4:%.*]], i64 4
// CHECK-NEXT:    [[TMP5:%.*]] = insertelement <8 x i16> [[TMP4]], i16 [[X5:%.*]], i64 5
// CHECK-NEXT:    [[TMP6:%.*]] = insertelement <8 x i16> [[TMP5]], i16 [[X6:%.*]], i64 6
// CHECK-NEXT:    [[TMP7:%.*]] = insertelement <8 x i16> [[TMP6]], i16 [[X7:%.*]], i64 7
// CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> [[TMP7]], i64 0)
// CHECK-NEXT:    [[TMP9:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP8]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP9]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_u16tttttttt(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <8 x i16> poison, i16 [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x i16> [[TMP0]], i16 [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i16> [[TMP1]], i16 [[X2:%.*]], i64 2
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <8 x i16> [[TMP2]], i16 [[X3:%.*]], i64 3
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = insertelement <8 x i16> [[TMP3]], i16 [[X4:%.*]], i64 4
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = insertelement <8 x i16> [[TMP4]], i16 [[X5:%.*]], i64 5
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = insertelement <8 x i16> [[TMP5]], i16 [[X6:%.*]], i64 6
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = insertelement <8 x i16> [[TMP6]], i16 [[X7:%.*]], i64 7
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> [[TMP7]], i64 0)
// CPP-CHECK-NEXT:    [[TMP9:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP8]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP9]]
//
svuint16_t test_svdupq_n_u16(uint16_t x0, uint16_t x1, uint16_t x2, uint16_t x3,
                             uint16_t x4, uint16_t x5, uint16_t x6, uint16_t x7) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_u16,)(x0, x1, x2, x3, x4, x5, x6, x7);
}

// CHECK-LABEL: @test_svdupq_n_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32> [[TMP0]], i32 [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[X2:%.*]], i64 2
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[X3:%.*]], i64 3
// CHECK-NEXT:    [[TMP4:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> [[TMP3]], i64 0)
// CHECK-NEXT:    [[TMP5:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP4]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP5]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_u32jjjj(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32> [[TMP0]], i32 [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[X2:%.*]], i64 2
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[X3:%.*]], i64 3
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> [[TMP3]], i64 0)
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP4]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP5]]
//
svuint32_t test_svdupq_n_u32(uint32_t x0, uint32_t x1, uint32_t x2, uint32_t x3) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_u32,)(x0, x1, x2, x3);
}

// CHECK-LABEL: @test_svdupq_n_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i64> poison, i64 [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> [[TMP1]], i64 0)
// CHECK-NEXT:    [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_u64mm(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i64> poison, i64 [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> [[TMP0]], i64 [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> [[TMP1]], i64 0)
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP2]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP3]]
//
svuint64_t test_svdupq_n_u64(uint64_t x0, uint64_t x1) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq,_n,_u64,)(x0, x1);
}

// CHECK-LABEL: @test_svdupq_n_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <8 x half> poison, half [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x half> [[TMP0]], half [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x half> [[TMP1]], half [[X2:%.*]], i64 2
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <8 x half> [[TMP2]], half [[X3:%.*]], i64 3
// CHECK-NEXT:    [[TMP4:%.*]] = insertelement <8 x half> [[TMP3]], half [[X4:%.*]], i64 4
// CHECK-NEXT:    [[TMP5:%.*]] = insertelement <8 x half> [[TMP4]], half [[X5:%.*]], i64 5
// CHECK-NEXT:    [[TMP6:%.*]] = insertelement <8 x half> [[TMP5]], half [[X6:%.*]], i64 6
// CHECK-NEXT:    [[TMP7:%.*]] = insertelement <8 x half> [[TMP6]], half [[X7:%.*]], i64 7
// CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 8 x half> @llvm.vector.insert.nxv8f16.v8f16(<vscale x 8 x half> poison, <8 x half> [[TMP7]], i64 0)
// CHECK-NEXT:    [[TMP9:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.dupq.lane.nxv8f16(<vscale x 8 x half> [[TMP8]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP9]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_f16DhDhDhDhDhDhDhDh(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <8 x half> poison, half [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x half> [[TMP0]], half [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x half> [[TMP1]], half [[X2:%.*]], i64 2
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <8 x half> [[TMP2]], half [[X3:%.*]], i64 3
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = insertelement <8 x half> [[TMP3]], half [[X4:%.*]], i64 4
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = insertelement <8 x half> [[TMP4]], half [[X5:%.*]], i64 5
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = insertelement <8 x half> [[TMP5]], half [[X6:%.*]], i64 6
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = insertelement <8 x half> [[TMP6]], half [[X7:%.*]], i64 7
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 8 x half> @llvm.vector.insert.nxv8f16.v8f16(<vscale x 8 x half> poison, <8 x half> [[TMP7]], i64 0)
// CPP-CHECK-NEXT:    [[TMP9:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.dupq.lane.nxv8f16(<vscale x 8 x half> [[TMP8]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP9]]
//
svfloat16_t test_svdupq_n_f16(float16_t x0, float16_t x1, float16_t x2, float16_t x3,
                              float16_t x4, float16_t x5, float16_t x6, float16_t x7) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_f16,)(x0, x1, x2, x3, x4, x5, x6, x7);
}

// CHECK-LABEL: @test_svdupq_n_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x float> poison, float [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x float> [[TMP0]], float [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x float> [[TMP1]], float [[X2:%.*]], i64 2
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x float> [[TMP2]], float [[X3:%.*]], i64 3
// CHECK-NEXT:    [[TMP4:%.*]] = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> [[TMP3]], i64 0)
// CHECK-NEXT:    [[TMP5:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> [[TMP4]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP5]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_f32ffff(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x float> poison, float [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x float> [[TMP0]], float [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x float> [[TMP1]], float [[X2:%.*]], i64 2
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x float> [[TMP2]], float [[X3:%.*]], i64 3
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> [[TMP3]], i64 0)
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> [[TMP4]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP5]]
//
svfloat32_t test_svdupq_n_f32(float32_t x0, float32_t x1, float32_t x2, float32_t x3) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_f32,)(x0, x1, x2, x3);
}

// CHECK-LABEL: @test_svdupq_n_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> poison, double [[X0:%.*]], i64 0
// CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[X1:%.*]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x double> @llvm.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> poison, <2 x double> [[TMP1]], i64 0)
// CHECK-NEXT:    [[TMP3:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.dupq.lane.nxv2f64(<vscale x 2 x double> [[TMP2]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_f64dd(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x double> poison, double [[X0:%.*]], i64 0
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[X1:%.*]], i64 1
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = tail call <vscale x 2 x double> @llvm.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> poison, <2 x double> [[TMP1]], i64 0)
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.dupq.lane.nxv2f64(<vscale x 2 x double> [[TMP2]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP3]]
//
svfloat64_t test_svdupq_n_f64(float64_t x0, float64_t x1) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq,_n,_f64,)(x0, x1);
}

// CHECK-LABEL: @test_svdupq_n_b8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[FROMBOOL:%.*]] = zext i1 [[X0:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL1:%.*]] = zext i1 [[X1:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL2:%.*]] = zext i1 [[X2:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL3:%.*]] = zext i1 [[X3:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL4:%.*]] = zext i1 [[X4:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL5:%.*]] = zext i1 [[X5:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL6:%.*]] = zext i1 [[X6:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL7:%.*]] = zext i1 [[X7:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL8:%.*]] = zext i1 [[X8:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL9:%.*]] = zext i1 [[X9:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL10:%.*]] = zext i1 [[X10:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL11:%.*]] = zext i1 [[X11:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL12:%.*]] = zext i1 [[X12:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL13:%.*]] = zext i1 [[X13:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL14:%.*]] = zext i1 [[X14:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL15:%.*]] = zext i1 [[X15:%.*]] to i8
// CHECK-NEXT:    [[TOBOOL:%.*]] = trunc i8 [[FROMBOOL]] to i1
// CHECK-NEXT:    [[TOBOOL16:%.*]] = trunc i8 [[FROMBOOL1]] to i1
// CHECK-NEXT:    [[TOBOOL17:%.*]] = trunc i8 [[FROMBOOL2]] to i1
// CHECK-NEXT:    [[TOBOOL18:%.*]] = trunc i8 [[FROMBOOL3]] to i1
// CHECK-NEXT:    [[TOBOOL19:%.*]] = trunc i8 [[FROMBOOL4]] to i1
// CHECK-NEXT:    [[TOBOOL20:%.*]] = trunc i8 [[FROMBOOL5]] to i1
// CHECK-NEXT:    [[TOBOOL21:%.*]] = trunc i8 [[FROMBOOL6]] to i1
// CHECK-NEXT:    [[TOBOOL22:%.*]] = trunc i8 [[FROMBOOL7]] to i1
// CHECK-NEXT:    [[TOBOOL23:%.*]] = trunc i8 [[FROMBOOL8]] to i1
// CHECK-NEXT:    [[TOBOOL24:%.*]] = trunc i8 [[FROMBOOL9]] to i1
// CHECK-NEXT:    [[TOBOOL25:%.*]] = trunc i8 [[FROMBOOL10]] to i1
// CHECK-NEXT:    [[TOBOOL26:%.*]] = trunc i8 [[FROMBOOL11]] to i1
// CHECK-NEXT:    [[TOBOOL27:%.*]] = trunc i8 [[FROMBOOL12]] to i1
// CHECK-NEXT:    [[TOBOOL28:%.*]] = trunc i8 [[FROMBOOL13]] to i1
// CHECK-NEXT:    [[TOBOOL29:%.*]] = trunc i8 [[FROMBOOL14]] to i1
// CHECK-NEXT:    [[TOBOOL30:%.*]] = trunc i8 [[FROMBOOL15]] to i1
// CHECK-NEXT:    [[TMP0:%.*]] = zext i1 [[TOBOOL]] to i8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i1 [[TOBOOL16]] to i8
// CHECK-NEXT:    [[TMP2:%.*]] = zext i1 [[TOBOOL17]] to i8
// CHECK-NEXT:    [[TMP3:%.*]] = zext i1 [[TOBOOL18]] to i8
// CHECK-NEXT:    [[TMP4:%.*]] = zext i1 [[TOBOOL19]] to i8
// CHECK-NEXT:    [[TMP5:%.*]] = zext i1 [[TOBOOL20]] to i8
// CHECK-NEXT:    [[TMP6:%.*]] = zext i1 [[TOBOOL21]] to i8
// CHECK-NEXT:    [[TMP7:%.*]] = zext i1 [[TOBOOL22]] to i8
// CHECK-NEXT:    [[TMP8:%.*]] = zext i1 [[TOBOOL23]] to i8
// CHECK-NEXT:    [[TMP9:%.*]] = zext i1 [[TOBOOL24]] to i8
// CHECK-NEXT:    [[TMP10:%.*]] = zext i1 [[TOBOOL25]] to i8
// CHECK-NEXT:    [[TMP11:%.*]] = zext i1 [[TOBOOL26]] to i8
// CHECK-NEXT:    [[TMP12:%.*]] = zext i1 [[TOBOOL27]] to i8
// CHECK-NEXT:    [[TMP13:%.*]] = zext i1 [[TOBOOL28]] to i8
// CHECK-NEXT:    [[TMP14:%.*]] = zext i1 [[TOBOOL29]] to i8
// CHECK-NEXT:    [[TMP15:%.*]] = zext i1 [[TOBOOL30]] to i8
// CHECK-NEXT:    [[TMP16:%.*]] = insertelement <16 x i8> poison, i8 [[TMP0]], i64 0
// CHECK-NEXT:    [[TMP17:%.*]] = insertelement <16 x i8> [[TMP16]], i8 [[TMP1]], i64 1
// CHECK-NEXT:    [[TMP18:%.*]] = insertelement <16 x i8> [[TMP17]], i8 [[TMP2]], i64 2
// CHECK-NEXT:    [[TMP19:%.*]] = insertelement <16 x i8> [[TMP18]], i8 [[TMP3]], i64 3
// CHECK-NEXT:    [[TMP20:%.*]] = insertelement <16 x i8> [[TMP19]], i8 [[TMP4]], i64 4
// CHECK-NEXT:    [[TMP21:%.*]] = insertelement <16 x i8> [[TMP20]], i8 [[TMP5]], i64 5
// CHECK-NEXT:    [[TMP22:%.*]] = insertelement <16 x i8> [[TMP21]], i8 [[TMP6]], i64 6
// CHECK-NEXT:    [[TMP23:%.*]] = insertelement <16 x i8> [[TMP22]], i8 [[TMP7]], i64 7
// CHECK-NEXT:    [[TMP24:%.*]] = insertelement <16 x i8> [[TMP23]], i8 [[TMP8]], i64 8
// CHECK-NEXT:    [[TMP25:%.*]] = insertelement <16 x i8> [[TMP24]], i8 [[TMP9]], i64 9
// CHECK-NEXT:    [[TMP26:%.*]] = insertelement <16 x i8> [[TMP25]], i8 [[TMP10]], i64 10
// CHECK-NEXT:    [[TMP27:%.*]] = insertelement <16 x i8> [[TMP26]], i8 [[TMP11]], i64 11
// CHECK-NEXT:    [[TMP28:%.*]] = insertelement <16 x i8> [[TMP27]], i8 [[TMP12]], i64 12
// CHECK-NEXT:    [[TMP29:%.*]] = insertelement <16 x i8> [[TMP28]], i8 [[TMP13]], i64 13
// CHECK-NEXT:    [[TMP30:%.*]] = insertelement <16 x i8> [[TMP29]], i8 [[TMP14]], i64 14
// CHECK-NEXT:    [[TMP31:%.*]] = insertelement <16 x i8> [[TMP30]], i8 [[TMP15]], i64 15
// CHECK-NEXT:    [[TMP32:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> [[TMP31]], i64 0)
// CHECK-NEXT:    [[TMP33:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP32]], i64 0)
// CHECK-NEXT:    [[TMP34:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
// CHECK-NEXT:    [[TMP35:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> [[TMP34]], <vscale x 16 x i8> [[TMP33]], <vscale x 2 x i64> zeroinitializer)
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP35]]
//
// CPP-CHECK-LABEL: @_Z16test_svdupq_n_b8bbbbbbbbbbbbbbbb(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[FROMBOOL:%.*]] = zext i1 [[X0:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL1:%.*]] = zext i1 [[X1:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL2:%.*]] = zext i1 [[X2:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL3:%.*]] = zext i1 [[X3:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL4:%.*]] = zext i1 [[X4:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL5:%.*]] = zext i1 [[X5:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL6:%.*]] = zext i1 [[X6:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL7:%.*]] = zext i1 [[X7:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL8:%.*]] = zext i1 [[X8:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL9:%.*]] = zext i1 [[X9:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL10:%.*]] = zext i1 [[X10:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL11:%.*]] = zext i1 [[X11:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL12:%.*]] = zext i1 [[X12:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL13:%.*]] = zext i1 [[X13:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL14:%.*]] = zext i1 [[X14:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL15:%.*]] = zext i1 [[X15:%.*]] to i8
// CPP-CHECK-NEXT:    [[TOBOOL:%.*]] = trunc i8 [[FROMBOOL]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL16:%.*]] = trunc i8 [[FROMBOOL1]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL17:%.*]] = trunc i8 [[FROMBOOL2]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL18:%.*]] = trunc i8 [[FROMBOOL3]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL19:%.*]] = trunc i8 [[FROMBOOL4]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL20:%.*]] = trunc i8 [[FROMBOOL5]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL21:%.*]] = trunc i8 [[FROMBOOL6]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL22:%.*]] = trunc i8 [[FROMBOOL7]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL23:%.*]] = trunc i8 [[FROMBOOL8]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL24:%.*]] = trunc i8 [[FROMBOOL9]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL25:%.*]] = trunc i8 [[FROMBOOL10]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL26:%.*]] = trunc i8 [[FROMBOOL11]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL27:%.*]] = trunc i8 [[FROMBOOL12]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL28:%.*]] = trunc i8 [[FROMBOOL13]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL29:%.*]] = trunc i8 [[FROMBOOL14]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL30:%.*]] = trunc i8 [[FROMBOOL15]] to i1
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = zext i1 [[TOBOOL]] to i8
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = zext i1 [[TOBOOL16]] to i8
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = zext i1 [[TOBOOL17]] to i8
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = zext i1 [[TOBOOL18]] to i8
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = zext i1 [[TOBOOL19]] to i8
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = zext i1 [[TOBOOL20]] to i8
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = zext i1 [[TOBOOL21]] to i8
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = zext i1 [[TOBOOL22]] to i8
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = zext i1 [[TOBOOL23]] to i8
// CPP-CHECK-NEXT:    [[TMP9:%.*]] = zext i1 [[TOBOOL24]] to i8
// CPP-CHECK-NEXT:    [[TMP10:%.*]] = zext i1 [[TOBOOL25]] to i8
// CPP-CHECK-NEXT:    [[TMP11:%.*]] = zext i1 [[TOBOOL26]] to i8
// CPP-CHECK-NEXT:    [[TMP12:%.*]] = zext i1 [[TOBOOL27]] to i8
// CPP-CHECK-NEXT:    [[TMP13:%.*]] = zext i1 [[TOBOOL28]] to i8
// CPP-CHECK-NEXT:    [[TMP14:%.*]] = zext i1 [[TOBOOL29]] to i8
// CPP-CHECK-NEXT:    [[TMP15:%.*]] = zext i1 [[TOBOOL30]] to i8
// CPP-CHECK-NEXT:    [[TMP16:%.*]] = insertelement <16 x i8> poison, i8 [[TMP0]], i64 0
// CPP-CHECK-NEXT:    [[TMP17:%.*]] = insertelement <16 x i8> [[TMP16]], i8 [[TMP1]], i64 1
// CPP-CHECK-NEXT:    [[TMP18:%.*]] = insertelement <16 x i8> [[TMP17]], i8 [[TMP2]], i64 2
// CPP-CHECK-NEXT:    [[TMP19:%.*]] = insertelement <16 x i8> [[TMP18]], i8 [[TMP3]], i64 3
// CPP-CHECK-NEXT:    [[TMP20:%.*]] = insertelement <16 x i8> [[TMP19]], i8 [[TMP4]], i64 4
// CPP-CHECK-NEXT:    [[TMP21:%.*]] = insertelement <16 x i8> [[TMP20]], i8 [[TMP5]], i64 5
// CPP-CHECK-NEXT:    [[TMP22:%.*]] = insertelement <16 x i8> [[TMP21]], i8 [[TMP6]], i64 6
// CPP-CHECK-NEXT:    [[TMP23:%.*]] = insertelement <16 x i8> [[TMP22]], i8 [[TMP7]], i64 7
// CPP-CHECK-NEXT:    [[TMP24:%.*]] = insertelement <16 x i8> [[TMP23]], i8 [[TMP8]], i64 8
// CPP-CHECK-NEXT:    [[TMP25:%.*]] = insertelement <16 x i8> [[TMP24]], i8 [[TMP9]], i64 9
// CPP-CHECK-NEXT:    [[TMP26:%.*]] = insertelement <16 x i8> [[TMP25]], i8 [[TMP10]], i64 10
// CPP-CHECK-NEXT:    [[TMP27:%.*]] = insertelement <16 x i8> [[TMP26]], i8 [[TMP11]], i64 11
// CPP-CHECK-NEXT:    [[TMP28:%.*]] = insertelement <16 x i8> [[TMP27]], i8 [[TMP12]], i64 12
// CPP-CHECK-NEXT:    [[TMP29:%.*]] = insertelement <16 x i8> [[TMP28]], i8 [[TMP13]], i64 13
// CPP-CHECK-NEXT:    [[TMP30:%.*]] = insertelement <16 x i8> [[TMP29]], i8 [[TMP14]], i64 14
// CPP-CHECK-NEXT:    [[TMP31:%.*]] = insertelement <16 x i8> [[TMP30]], i8 [[TMP15]], i64 15
// CPP-CHECK-NEXT:    [[TMP32:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> [[TMP31]], i64 0)
// CPP-CHECK-NEXT:    [[TMP33:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP32]], i64 0)
// CPP-CHECK-NEXT:    [[TMP34:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
// CPP-CHECK-NEXT:    [[TMP35:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.cmpne.wide.nxv16i8(<vscale x 16 x i1> [[TMP34]], <vscale x 16 x i8> [[TMP33]], <vscale x 2 x i64> zeroinitializer)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP35]]
//
svbool_t test_svdupq_n_b8(bool x0, bool x1, bool x2, bool x3,
                          bool x4, bool x5, bool x6, bool x7,
                          bool x8, bool x9, bool x10, bool x11,
                          bool x12, bool x13, bool x14, bool x15) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_b8,)(x0, x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14, x15);
}

// CHECK-LABEL: @test_svdupq_n_b16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[FROMBOOL:%.*]] = zext i1 [[X0:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL1:%.*]] = zext i1 [[X1:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL2:%.*]] = zext i1 [[X2:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL3:%.*]] = zext i1 [[X3:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL4:%.*]] = zext i1 [[X4:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL5:%.*]] = zext i1 [[X5:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL6:%.*]] = zext i1 [[X6:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL7:%.*]] = zext i1 [[X7:%.*]] to i8
// CHECK-NEXT:    [[TOBOOL:%.*]] = trunc i8 [[FROMBOOL]] to i1
// CHECK-NEXT:    [[TOBOOL8:%.*]] = trunc i8 [[FROMBOOL1]] to i1
// CHECK-NEXT:    [[TOBOOL9:%.*]] = trunc i8 [[FROMBOOL2]] to i1
// CHECK-NEXT:    [[TOBOOL10:%.*]] = trunc i8 [[FROMBOOL3]] to i1
// CHECK-NEXT:    [[TOBOOL11:%.*]] = trunc i8 [[FROMBOOL4]] to i1
// CHECK-NEXT:    [[TOBOOL12:%.*]] = trunc i8 [[FROMBOOL5]] to i1
// CHECK-NEXT:    [[TOBOOL13:%.*]] = trunc i8 [[FROMBOOL6]] to i1
// CHECK-NEXT:    [[TOBOOL14:%.*]] = trunc i8 [[FROMBOOL7]] to i1
// CHECK-NEXT:    [[TMP0:%.*]] = zext i1 [[TOBOOL]] to i16
// CHECK-NEXT:    [[TMP1:%.*]] = zext i1 [[TOBOOL8]] to i16
// CHECK-NEXT:    [[TMP2:%.*]] = zext i1 [[TOBOOL9]] to i16
// CHECK-NEXT:    [[TMP3:%.*]] = zext i1 [[TOBOOL10]] to i16
// CHECK-NEXT:    [[TMP4:%.*]] = zext i1 [[TOBOOL11]] to i16
// CHECK-NEXT:    [[TMP5:%.*]] = zext i1 [[TOBOOL12]] to i16
// CHECK-NEXT:    [[TMP6:%.*]] = zext i1 [[TOBOOL13]] to i16
// CHECK-NEXT:    [[TMP7:%.*]] = zext i1 [[TOBOOL14]] to i16
// CHECK-NEXT:    [[TMP8:%.*]] = insertelement <8 x i16> poison, i16 [[TMP0]], i64 0
// CHECK-NEXT:    [[TMP9:%.*]] = insertelement <8 x i16> [[TMP8]], i16 [[TMP1]], i64 1
// CHECK-NEXT:    [[TMP10:%.*]] = insertelement <8 x i16> [[TMP9]], i16 [[TMP2]], i64 2
// CHECK-NEXT:    [[TMP11:%.*]] = insertelement <8 x i16> [[TMP10]], i16 [[TMP3]], i64 3
// CHECK-NEXT:    [[TMP12:%.*]] = insertelement <8 x i16> [[TMP11]], i16 [[TMP4]], i64 4
// CHECK-NEXT:    [[TMP13:%.*]] = insertelement <8 x i16> [[TMP12]], i16 [[TMP5]], i64 5
// CHECK-NEXT:    [[TMP14:%.*]] = insertelement <8 x i16> [[TMP13]], i16 [[TMP6]], i64 6
// CHECK-NEXT:    [[TMP15:%.*]] = insertelement <8 x i16> [[TMP14]], i16 [[TMP7]], i64 7
// CHECK-NEXT:    [[TMP16:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> [[TMP15]], i64 0)
// CHECK-NEXT:    [[TMP17:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP16]], i64 0)
// CHECK-NEXT:    [[TMP18:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
// CHECK-NEXT:    [[TMP19:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> [[TMP18]], <vscale x 8 x i16> [[TMP17]], <vscale x 2 x i64> zeroinitializer)
// CHECK-NEXT:    [[TMP20:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP19]])
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP20]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_b16bbbbbbbb(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[FROMBOOL:%.*]] = zext i1 [[X0:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL1:%.*]] = zext i1 [[X1:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL2:%.*]] = zext i1 [[X2:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL3:%.*]] = zext i1 [[X3:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL4:%.*]] = zext i1 [[X4:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL5:%.*]] = zext i1 [[X5:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL6:%.*]] = zext i1 [[X6:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL7:%.*]] = zext i1 [[X7:%.*]] to i8
// CPP-CHECK-NEXT:    [[TOBOOL:%.*]] = trunc i8 [[FROMBOOL]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL8:%.*]] = trunc i8 [[FROMBOOL1]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL9:%.*]] = trunc i8 [[FROMBOOL2]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL10:%.*]] = trunc i8 [[FROMBOOL3]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL11:%.*]] = trunc i8 [[FROMBOOL4]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL12:%.*]] = trunc i8 [[FROMBOOL5]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL13:%.*]] = trunc i8 [[FROMBOOL6]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL14:%.*]] = trunc i8 [[FROMBOOL7]] to i1
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = zext i1 [[TOBOOL]] to i16
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = zext i1 [[TOBOOL8]] to i16
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = zext i1 [[TOBOOL9]] to i16
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = zext i1 [[TOBOOL10]] to i16
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = zext i1 [[TOBOOL11]] to i16
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = zext i1 [[TOBOOL12]] to i16
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = zext i1 [[TOBOOL13]] to i16
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = zext i1 [[TOBOOL14]] to i16
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = insertelement <8 x i16> poison, i16 [[TMP0]], i64 0
// CPP-CHECK-NEXT:    [[TMP9:%.*]] = insertelement <8 x i16> [[TMP8]], i16 [[TMP1]], i64 1
// CPP-CHECK-NEXT:    [[TMP10:%.*]] = insertelement <8 x i16> [[TMP9]], i16 [[TMP2]], i64 2
// CPP-CHECK-NEXT:    [[TMP11:%.*]] = insertelement <8 x i16> [[TMP10]], i16 [[TMP3]], i64 3
// CPP-CHECK-NEXT:    [[TMP12:%.*]] = insertelement <8 x i16> [[TMP11]], i16 [[TMP4]], i64 4
// CPP-CHECK-NEXT:    [[TMP13:%.*]] = insertelement <8 x i16> [[TMP12]], i16 [[TMP5]], i64 5
// CPP-CHECK-NEXT:    [[TMP14:%.*]] = insertelement <8 x i16> [[TMP13]], i16 [[TMP6]], i64 6
// CPP-CHECK-NEXT:    [[TMP15:%.*]] = insertelement <8 x i16> [[TMP14]], i16 [[TMP7]], i64 7
// CPP-CHECK-NEXT:    [[TMP16:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> [[TMP15]], i64 0)
// CPP-CHECK-NEXT:    [[TMP17:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP16]], i64 0)
// CPP-CHECK-NEXT:    [[TMP18:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
// CPP-CHECK-NEXT:    [[TMP19:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.cmpne.wide.nxv8i16(<vscale x 8 x i1> [[TMP18]], <vscale x 8 x i16> [[TMP17]], <vscale x 2 x i64> zeroinitializer)
// CPP-CHECK-NEXT:    [[TMP20:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> [[TMP19]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP20]]
//
svbool_t test_svdupq_n_b16(bool x0, bool x1, bool x2, bool x3,
                           bool x4, bool x5, bool x6, bool x7) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_b16,)(x0, x1, x2, x3, x4, x5, x6, x7);
}

// CHECK-LABEL: @test_svdupq_n_b32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[FROMBOOL:%.*]] = zext i1 [[X0:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL1:%.*]] = zext i1 [[X1:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL2:%.*]] = zext i1 [[X2:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL3:%.*]] = zext i1 [[X3:%.*]] to i8
// CHECK-NEXT:    [[TOBOOL:%.*]] = trunc i8 [[FROMBOOL]] to i1
// CHECK-NEXT:    [[TOBOOL4:%.*]] = trunc i8 [[FROMBOOL1]] to i1
// CHECK-NEXT:    [[TOBOOL5:%.*]] = trunc i8 [[FROMBOOL2]] to i1
// CHECK-NEXT:    [[TOBOOL6:%.*]] = trunc i8 [[FROMBOOL3]] to i1
// CHECK-NEXT:    [[TMP0:%.*]] = zext i1 [[TOBOOL]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = zext i1 [[TOBOOL4]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = zext i1 [[TOBOOL5]] to i32
// CHECK-NEXT:    [[TMP3:%.*]] = zext i1 [[TOBOOL6]] to i32
// CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP0]], i64 0
// CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x i32> [[TMP4]], i32 [[TMP1]], i64 1
// CHECK-NEXT:    [[TMP6:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[TMP2]], i64 2
// CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> [[TMP6]], i32 [[TMP3]], i64 3
// CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> [[TMP7]], i64 0)
// CHECK-NEXT:    [[TMP9:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP8]], i64 0)
// CHECK-NEXT:    [[TMP10:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
// CHECK-NEXT:    [[TMP11:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> [[TMP10]], <vscale x 4 x i32> [[TMP9]], <vscale x 2 x i64> zeroinitializer)
// CHECK-NEXT:    [[TMP12:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP11]])
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP12]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_b32bbbb(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[FROMBOOL:%.*]] = zext i1 [[X0:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL1:%.*]] = zext i1 [[X1:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL2:%.*]] = zext i1 [[X2:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL3:%.*]] = zext i1 [[X3:%.*]] to i8
// CPP-CHECK-NEXT:    [[TOBOOL:%.*]] = trunc i8 [[FROMBOOL]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL4:%.*]] = trunc i8 [[FROMBOOL1]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL5:%.*]] = trunc i8 [[FROMBOOL2]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL6:%.*]] = trunc i8 [[FROMBOOL3]] to i1
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = zext i1 [[TOBOOL]] to i32
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = zext i1 [[TOBOOL4]] to i32
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = zext i1 [[TOBOOL5]] to i32
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = zext i1 [[TOBOOL6]] to i32
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP0]], i64 0
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x i32> [[TMP4]], i32 [[TMP1]], i64 1
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[TMP2]], i64 2
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> [[TMP6]], i32 [[TMP3]], i64 3
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> [[TMP7]], i64 0)
// CPP-CHECK-NEXT:    [[TMP9:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP8]], i64 0)
// CPP-CHECK-NEXT:    [[TMP10:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
// CPP-CHECK-NEXT:    [[TMP11:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.cmpne.wide.nxv4i32(<vscale x 4 x i1> [[TMP10]], <vscale x 4 x i32> [[TMP9]], <vscale x 2 x i64> zeroinitializer)
// CPP-CHECK-NEXT:    [[TMP12:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> [[TMP11]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP12]]
//
svbool_t test_svdupq_n_b32(bool x0, bool x1, bool x2, bool x3) MODE_ATTR
{
  // <assume other insertelement>
  return SVE_ACLE_FUNC(svdupq,_n,_b32,)(x0, x1, x2, x3);
}

// CHECK-LABEL: @test_svdupq_n_b64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[FROMBOOL:%.*]] = zext i1 [[X0:%.*]] to i8
// CHECK-NEXT:    [[FROMBOOL1:%.*]] = zext i1 [[X1:%.*]] to i8
// CHECK-NEXT:    [[TOBOOL:%.*]] = trunc i8 [[FROMBOOL]] to i1
// CHECK-NEXT:    [[TOBOOL2:%.*]] = trunc i8 [[FROMBOOL1]] to i1
// CHECK-NEXT:    [[TMP0:%.*]] = zext i1 [[TOBOOL]] to i64
// CHECK-NEXT:    [[TMP1:%.*]] = zext i1 [[TOBOOL2]] to i64
// CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x i64> poison, i64 [[TMP0]], i64 0
// CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x i64> [[TMP2]], i64 [[TMP1]], i64 1
// CHECK-NEXT:    [[TMP4:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> [[TMP3]], i64 0)
// CHECK-NEXT:    [[TMP5:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP4]], i64 0)
// CHECK-NEXT:    [[TMP6:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
// CHECK-NEXT:    [[TMP7:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP6]], <vscale x 2 x i64> [[TMP5]], <vscale x 2 x i64> zeroinitializer)
// CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP7]])
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP8]]
//
// CPP-CHECK-LABEL: @_Z17test_svdupq_n_b64bb(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[FROMBOOL:%.*]] = zext i1 [[X0:%.*]] to i8
// CPP-CHECK-NEXT:    [[FROMBOOL1:%.*]] = zext i1 [[X1:%.*]] to i8
// CPP-CHECK-NEXT:    [[TOBOOL:%.*]] = trunc i8 [[FROMBOOL]] to i1
// CPP-CHECK-NEXT:    [[TOBOOL2:%.*]] = trunc i8 [[FROMBOOL1]] to i1
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = zext i1 [[TOBOOL]] to i64
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = zext i1 [[TOBOOL2]] to i64
// CPP-CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x i64> poison, i64 [[TMP0]], i64 0
// CPP-CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x i64> [[TMP2]], i64 [[TMP1]], i64 1
// CPP-CHECK-NEXT:    [[TMP4:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> [[TMP3]], i64 0)
// CPP-CHECK-NEXT:    [[TMP5:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP4]], i64 0)
// CPP-CHECK-NEXT:    [[TMP6:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
// CPP-CHECK-NEXT:    [[TMP7:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.cmpne.nxv2i64(<vscale x 2 x i1> [[TMP6]], <vscale x 2 x i64> [[TMP5]], <vscale x 2 x i64> zeroinitializer)
// CPP-CHECK-NEXT:    [[TMP8:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> [[TMP7]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP8]]
//
svbool_t test_svdupq_n_b64(bool x0, bool x1) MODE_ATTR
{
  return SVE_ACLE_FUNC(svdupq,_n,_b64,)(x0, x1);
}