// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s

// REQUIRES: aarch64-registered-target || arm-registered-target

#include <arm_mve.h>

// CHECK-LABEL: @test_vldrbq_gather_offset_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.v8i16.p0i8.v8i16(i8* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 8, i32 0, i32 0)
// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
//
int16x8_t test_vldrbq_gather_offset_s16(const int8_t *base, uint16x8_t offset)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_s16(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i8.v4i32(i8* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 8, i32 0, i32 0)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
int32x4_t test_vldrbq_gather_offset_s32(const int8_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_s32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vldr.gather.offset.v16i8.p0i8.v16i8(i8* [[BASE:%.*]], <16 x i8> [[OFFSET:%.*]], i32 8, i32 0, i32 0)
// CHECK-NEXT:    ret <16 x i8> [[TMP0]]
//
int8x16_t test_vldrbq_gather_offset_s8(const int8_t *base, uint8x16_t offset)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_s8(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.v8i16.p0i8.v8i16(i8* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 8, i32 0, i32 1)
// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
//
uint16x8_t test_vldrbq_gather_offset_u16(const uint8_t *base, uint16x8_t offset)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_u16(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i8.v4i32(i8* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 8, i32 0, i32 1)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
uint32x4_t test_vldrbq_gather_offset_u32(const uint8_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_u32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vldr.gather.offset.v16i8.p0i8.v16i8(i8* [[BASE:%.*]], <16 x i8> [[OFFSET:%.*]], i32 8, i32 0, i32 1)
// CHECK-NEXT:    ret <16 x i8> [[TMP0]]
//
uint8x16_t test_vldrbq_gather_offset_u8(const uint8_t *base, uint8x16_t offset)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_u8(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_z_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.predicated.v8i16.p0i8.v8i16.v8i1(i8* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 8, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
//
int16x8_t test_vldrbq_gather_offset_z_s16(const int8_t *base, uint16x8_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_z_s16(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_z_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i8.v4i32.v4i1(i8* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 8, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
int32x4_t test_vldrbq_gather_offset_z_s32(const int8_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_z_s32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_z_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vldr.gather.offset.predicated.v16i8.p0i8.v16i8.v16i1(i8* [[BASE:%.*]], <16 x i8> [[OFFSET:%.*]], i32 8, i32 0, i32 0, <16 x i1> [[TMP1]])
// CHECK-NEXT:    ret <16 x i8> [[TMP2]]
//
int8x16_t test_vldrbq_gather_offset_z_s8(const int8_t *base, uint8x16_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_z_s8(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_z_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.predicated.v8i16.p0i8.v8i16.v8i1(i8* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 8, i32 0, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
//
uint16x8_t test_vldrbq_gather_offset_z_u16(const uint8_t *base, uint16x8_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_z_u16(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_z_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i8.v4i32.v4i1(i8* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 8, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
uint32x4_t test_vldrbq_gather_offset_z_u32(const uint8_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_z_u32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrbq_gather_offset_z_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vldr.gather.offset.predicated.v16i8.p0i8.v16i8.v16i1(i8* [[BASE:%.*]], <16 x i8> [[OFFSET:%.*]], i32 8, i32 0, i32 1, <16 x i1> [[TMP1]])
// CHECK-NEXT:    ret <16 x i8> [[TMP2]]
//
uint8x16_t test_vldrbq_gather_offset_z_u8(const uint8_t *base, uint8x16_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrbq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrbq_gather_offset_z_u8(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrdq_gather_base_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.base.v2i64.v2i64(<2 x i64> [[ADDR:%.*]], i32 616)
// CHECK-NEXT:    ret <2 x i64> [[TMP0]]
//
int64x2_t test_vldrdq_gather_base_s64(uint64x2_t addr)
{
    return vldrdq_gather_base_s64(addr, 0x268);
}

// CHECK-LABEL: @test_vldrdq_gather_base_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.base.v2i64.v2i64(<2 x i64> [[ADDR:%.*]], i32 -336)
// CHECK-NEXT:    ret <2 x i64> [[TMP0]]
//
uint64x2_t test_vldrdq_gather_base_u64(uint64x2_t addr)
{
    return vldrdq_gather_base_u64(addr, -0x150);
}

// CHECK-LABEL: @test_vldrdq_gather_base_wb_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call { <2 x i64>, <2 x i64> } @llvm.arm.mve.vldr.gather.base.wb.v2i64.v2i64(<2 x i64> [[TMP0]], i32 576)
// CHECK-NEXT:    [[TMP2:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP1]], 1
// CHECK-NEXT:    store <2 x i64> [[TMP2]], <2 x i64>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP1]], 0
// CHECK-NEXT:    ret <2 x i64> [[TMP3]]
//
int64x2_t test_vldrdq_gather_base_wb_s64(uint64x2_t *addr)
{
    return vldrdq_gather_base_wb_s64(addr, 0x240);
}

// CHECK-LABEL: @test_vldrdq_gather_base_wb_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call { <2 x i64>, <2 x i64> } @llvm.arm.mve.vldr.gather.base.wb.v2i64.v2i64(<2 x i64> [[TMP0]], i32 -328)
// CHECK-NEXT:    [[TMP2:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP1]], 1
// CHECK-NEXT:    store <2 x i64> [[TMP2]], <2 x i64>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP1]], 0
// CHECK-NEXT:    ret <2 x i64> [[TMP3]]
//
uint64x2_t test_vldrdq_gather_base_wb_u64(uint64x2_t *addr)
{
    return vldrdq_gather_base_wb_u64(addr, -0x148);
}

// CHECK-LABEL: @test_vldrdq_gather_base_wb_z_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call { <2 x i64>, <2 x i64> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v2i64.v2i64.v4i1(<2 x i64> [[TMP0]], i32 664, <4 x i1> [[TMP2]])
// CHECK-NEXT:    [[TMP4:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP3]], 1
// CHECK-NEXT:    store <2 x i64> [[TMP4]], <2 x i64>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP3]], 0
// CHECK-NEXT:    ret <2 x i64> [[TMP5]]
//
int64x2_t test_vldrdq_gather_base_wb_z_s64(uint64x2_t *addr, mve_pred16_t p)
{
    return vldrdq_gather_base_wb_z_s64(addr, 0x298, p);
}

// CHECK-LABEL: @test_vldrdq_gather_base_wb_z_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call { <2 x i64>, <2 x i64> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v2i64.v2i64.v4i1(<2 x i64> [[TMP0]], i32 656, <4 x i1> [[TMP2]])
// CHECK-NEXT:    [[TMP4:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP3]], 1
// CHECK-NEXT:    store <2 x i64> [[TMP4]], <2 x i64>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP3]], 0
// CHECK-NEXT:    ret <2 x i64> [[TMP5]]
//
uint64x2_t test_vldrdq_gather_base_wb_z_u64(uint64x2_t *addr, mve_pred16_t p)
{
    return vldrdq_gather_base_wb_z_u64(addr, 0x290, p);
}

// CHECK-LABEL: @test_vldrdq_gather_base_z_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.base.predicated.v2i64.v2i64.v4i1(<2 x i64> [[ADDR:%.*]], i32 888, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <2 x i64> [[TMP2]]
//
int64x2_t test_vldrdq_gather_base_z_s64(uint64x2_t addr, mve_pred16_t p)
{
    return vldrdq_gather_base_z_s64(addr, 0x378, p);
}

// CHECK-LABEL: @test_vldrdq_gather_base_z_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.base.predicated.v2i64.v2i64.v4i1(<2 x i64> [[ADDR:%.*]], i32 -1000, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <2 x i64> [[TMP2]]
//
uint64x2_t test_vldrdq_gather_base_z_u64(uint64x2_t addr, mve_pred16_t p)
{
    return vldrdq_gather_base_z_u64(addr, -0x3e8, p);
}

// CHECK-LABEL: @test_vldrdq_gather_offset_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.offset.v2i64.p0i64.v2i64(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], i32 64, i32 0, i32 0)
// CHECK-NEXT:    ret <2 x i64> [[TMP0]]
//
int64x2_t test_vldrdq_gather_offset_s64(const int64_t *base, uint64x2_t offset)
{
#ifdef POLYMORPHIC
    return vldrdq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrdq_gather_offset_s64(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrdq_gather_offset_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.offset.v2i64.p0i64.v2i64(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], i32 64, i32 0, i32 1)
// CHECK-NEXT:    ret <2 x i64> [[TMP0]]
//
uint64x2_t test_vldrdq_gather_offset_u64(const uint64_t *base, uint64x2_t offset)
{
#ifdef POLYMORPHIC
    return vldrdq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrdq_gather_offset_u64(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrdq_gather_offset_z_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.offset.predicated.v2i64.p0i64.v2i64.v4i1(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], i32 64, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <2 x i64> [[TMP2]]
//
int64x2_t test_vldrdq_gather_offset_z_s64(const int64_t *base, uint64x2_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrdq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrdq_gather_offset_z_s64(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrdq_gather_offset_z_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.offset.predicated.v2i64.p0i64.v2i64.v4i1(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], i32 64, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <2 x i64> [[TMP2]]
//
uint64x2_t test_vldrdq_gather_offset_z_u64(const uint64_t *base, uint64x2_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrdq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrdq_gather_offset_z_u64(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrdq_gather_shifted_offset_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.offset.v2i64.p0i64.v2i64(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], i32 64, i32 3, i32 0)
// CHECK-NEXT:    ret <2 x i64> [[TMP0]]
//
int64x2_t test_vldrdq_gather_shifted_offset_s64(const int64_t *base, uint64x2_t offset)
{
#ifdef POLYMORPHIC
    return vldrdq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrdq_gather_shifted_offset_s64(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrdq_gather_shifted_offset_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.offset.v2i64.p0i64.v2i64(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], i32 64, i32 3, i32 1)
// CHECK-NEXT:    ret <2 x i64> [[TMP0]]
//
uint64x2_t test_vldrdq_gather_shifted_offset_u64(const uint64_t *base, uint64x2_t offset)
{
#ifdef POLYMORPHIC
    return vldrdq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrdq_gather_shifted_offset_u64(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrdq_gather_shifted_offset_z_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.offset.predicated.v2i64.p0i64.v2i64.v4i1(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], i32 64, i32 3, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <2 x i64> [[TMP2]]
//
int64x2_t test_vldrdq_gather_shifted_offset_z_s64(const int64_t *base, uint64x2_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrdq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrdq_gather_shifted_offset_z_s64(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrdq_gather_shifted_offset_z_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <2 x i64> @llvm.arm.mve.vldr.gather.offset.predicated.v2i64.p0i64.v2i64.v4i1(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], i32 64, i32 3, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <2 x i64> [[TMP2]]
//
uint64x2_t test_vldrdq_gather_shifted_offset_z_u64(const uint64_t *base, uint64x2_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrdq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrdq_gather_shifted_offset_z_u64(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x half> @llvm.arm.mve.vldr.gather.offset.v8f16.p0f16.v8i16(half* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 0, i32 0)
// CHECK-NEXT:    ret <8 x half> [[TMP0]]
//
float16x8_t test_vldrhq_gather_offset_f16(const float16_t *base, uint16x8_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_f16(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.v8i16.p0i16.v8i16(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 0, i32 0)
// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
//
int16x8_t test_vldrhq_gather_offset_s16(const int16_t *base, uint16x8_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_s16(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i16.v4i32(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 16, i32 0, i32 0)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
int32x4_t test_vldrhq_gather_offset_s32(const int16_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_s32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.v8i16.p0i16.v8i16(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 0, i32 1)
// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
//
uint16x8_t test_vldrhq_gather_offset_u16(const uint16_t *base, uint16x8_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_u16(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i16.v4i32(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 16, i32 0, i32 1)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
uint32x4_t test_vldrhq_gather_offset_u32(const uint16_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_u32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_z_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x half> @llvm.arm.mve.vldr.gather.offset.predicated.v8f16.p0f16.v8i16.v8i1(half* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret <8 x half> [[TMP2]]
//
float16x8_t test_vldrhq_gather_offset_z_f16(const float16_t *base, uint16x8_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_z_f16(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_z_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.predicated.v8i16.p0i16.v8i16.v8i1(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
//
int16x8_t test_vldrhq_gather_offset_z_s16(const int16_t *base, uint16x8_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_z_s16(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_z_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i16.v4i32.v4i1(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 16, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
int32x4_t test_vldrhq_gather_offset_z_s32(const int16_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_z_s32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_z_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.predicated.v8i16.p0i16.v8i16.v8i1(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 0, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
//
uint16x8_t test_vldrhq_gather_offset_z_u16(const uint16_t *base, uint16x8_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_z_u16(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_offset_z_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i16.v4i32.v4i1(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 16, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
uint32x4_t test_vldrhq_gather_offset_z_u32(const uint16_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_offset_z_u32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x half> @llvm.arm.mve.vldr.gather.offset.v8f16.p0f16.v8i16(half* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 1, i32 0)
// CHECK-NEXT:    ret <8 x half> [[TMP0]]
//
float16x8_t test_vldrhq_gather_shifted_offset_f16(const float16_t *base, uint16x8_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_f16(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.v8i16.p0i16.v8i16(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 1, i32 0)
// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
//
int16x8_t test_vldrhq_gather_shifted_offset_s16(const int16_t *base, uint16x8_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_s16(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i16.v4i32(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 16, i32 1, i32 0)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
int32x4_t test_vldrhq_gather_shifted_offset_s32(const int16_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_s32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.v8i16.p0i16.v8i16(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 1, i32 1)
// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
//
uint16x8_t test_vldrhq_gather_shifted_offset_u16(const uint16_t *base, uint16x8_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_u16(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i16.v4i32(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 16, i32 1, i32 1)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
uint32x4_t test_vldrhq_gather_shifted_offset_u32(const uint16_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_u32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_z_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x half> @llvm.arm.mve.vldr.gather.offset.predicated.v8f16.p0f16.v8i16.v8i1(half* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 1, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret <8 x half> [[TMP2]]
//
float16x8_t test_vldrhq_gather_shifted_offset_z_f16(const float16_t *base, uint16x8_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_z_f16(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_z_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.predicated.v8i16.p0i16.v8i16.v8i1(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 1, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
//
int16x8_t test_vldrhq_gather_shifted_offset_z_s16(const int16_t *base, uint16x8_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_z_s16(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_z_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i16.v4i32.v4i1(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 16, i32 1, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
int32x4_t test_vldrhq_gather_shifted_offset_z_s32(const int16_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_z_s32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_z_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vldr.gather.offset.predicated.v8i16.p0i16.v8i16.v8i1(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], i32 16, i32 1, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret <8 x i16> [[TMP2]]
//
uint16x8_t test_vldrhq_gather_shifted_offset_z_u16(const uint16_t *base, uint16x8_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_z_u16(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrhq_gather_shifted_offset_z_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i16.v4i32.v4i1(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 16, i32 1, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
uint32x4_t test_vldrhq_gather_shifted_offset_z_u32(const uint16_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrhq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrhq_gather_shifted_offset_z_u32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_base_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x float> @llvm.arm.mve.vldr.gather.base.v4f32.v4i32(<4 x i32> [[ADDR:%.*]], i32 12)
// CHECK-NEXT:    ret <4 x float> [[TMP0]]
//
float32x4_t test_vldrwq_gather_base_f32(uint32x4_t addr)
{
    return vldrwq_gather_base_f32(addr, 0xc);
}

// CHECK-LABEL: @test_vldrwq_gather_base_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.base.v4i32.v4i32(<4 x i32> [[ADDR:%.*]], i32 400)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
int32x4_t test_vldrwq_gather_base_s32(uint32x4_t addr)
{
    return vldrwq_gather_base_s32(addr, 0x190);
}

// CHECK-LABEL: @test_vldrwq_gather_base_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.base.v4i32.v4i32(<4 x i32> [[ADDR:%.*]], i32 284)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
uint32x4_t test_vldrwq_gather_base_u32(uint32x4_t addr)
{
    return vldrwq_gather_base_u32(addr, 0x11c);
}

// CHECK-LABEL: @test_vldrwq_gather_base_wb_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call { <4 x float>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.v4f32.v4i32(<4 x i32> [[TMP0]], i32 -64)
// CHECK-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x float>, <4 x i32> } [[TMP1]], 1
// CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x float>, <4 x i32> } [[TMP1]], 0
// CHECK-NEXT:    ret <4 x float> [[TMP3]]
//
float32x4_t test_vldrwq_gather_base_wb_f32(uint32x4_t *addr)
{
    return vldrwq_gather_base_wb_f32(addr, -0x40);
}

// CHECK-LABEL: @test_vldrwq_gather_base_wb_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.v4i32.v4i32(<4 x i32> [[TMP0]], i32 80)
// CHECK-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP1]], 1
// CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP1]], 0
// CHECK-NEXT:    ret <4 x i32> [[TMP3]]
//
int32x4_t test_vldrwq_gather_base_wb_s32(uint32x4_t *addr)
{
    return vldrwq_gather_base_wb_s32(addr, 0x50);
}

// CHECK-LABEL: @test_vldrwq_gather_base_wb_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.v4i32.v4i32(<4 x i32> [[TMP0]], i32 480)
// CHECK-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP1]], 1
// CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP1]], 0
// CHECK-NEXT:    ret <4 x i32> [[TMP3]]
//
uint32x4_t test_vldrwq_gather_base_wb_u32(uint32x4_t *addr)
{
    return vldrwq_gather_base_wb_u32(addr, 0x1e0);
}

// CHECK-LABEL: @test_vldrwq_gather_base_wb_z_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call { <4 x float>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v4f32.v4i32.v4i1(<4 x i32> [[TMP0]], i32 -352, <4 x i1> [[TMP2]])
// CHECK-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x float>, <4 x i32> } [[TMP3]], 1
// CHECK-NEXT:    store <4 x i32> [[TMP4]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x float>, <4 x i32> } [[TMP3]], 0
// CHECK-NEXT:    ret <4 x float> [[TMP5]]
//
float32x4_t test_vldrwq_gather_base_wb_z_f32(uint32x4_t *addr, mve_pred16_t p)
{
    return vldrwq_gather_base_wb_z_f32(addr, -0x160, p);
}

// CHECK-LABEL: @test_vldrwq_gather_base_wb_z_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v4i32.v4i32.v4i1(<4 x i32> [[TMP0]], i32 276, <4 x i1> [[TMP2]])
// CHECK-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP3]], 1
// CHECK-NEXT:    store <4 x i32> [[TMP4]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP3]], 0
// CHECK-NEXT:    ret <4 x i32> [[TMP5]]
//
int32x4_t test_vldrwq_gather_base_wb_z_s32(uint32x4_t *addr, mve_pred16_t p)
{
    return vldrwq_gather_base_wb_z_s32(addr, 0x114, p);
}

// CHECK-LABEL: @test_vldrwq_gather_base_wb_z_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call { <4 x i32>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v4i32.v4i32.v4i1(<4 x i32> [[TMP0]], i32 88, <4 x i1> [[TMP2]])
// CHECK-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP3]], 1
// CHECK-NEXT:    store <4 x i32> [[TMP4]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32> } [[TMP3]], 0
// CHECK-NEXT:    ret <4 x i32> [[TMP5]]
//
uint32x4_t test_vldrwq_gather_base_wb_z_u32(uint32x4_t *addr, mve_pred16_t p)
{
    return vldrwq_gather_base_wb_z_u32(addr, 0x58, p);
}

// CHECK-LABEL: @test_vldrwq_gather_base_z_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x float> @llvm.arm.mve.vldr.gather.base.predicated.v4f32.v4i32.v4i1(<4 x i32> [[ADDR:%.*]], i32 300, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x float> [[TMP2]]
//
float32x4_t test_vldrwq_gather_base_z_f32(uint32x4_t addr, mve_pred16_t p)
{
    return vldrwq_gather_base_z_f32(addr, 0x12c, p);
}

// CHECK-LABEL: @test_vldrwq_gather_base_z_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.base.predicated.v4i32.v4i32.v4i1(<4 x i32> [[ADDR:%.*]], i32 440, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
int32x4_t test_vldrwq_gather_base_z_s32(uint32x4_t addr, mve_pred16_t p)
{
    return vldrwq_gather_base_z_s32(addr, 0x1b8, p);
}

// CHECK-LABEL: @test_vldrwq_gather_base_z_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.base.predicated.v4i32.v4i32.v4i1(<4 x i32> [[ADDR:%.*]], i32 -300, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
uint32x4_t test_vldrwq_gather_base_z_u32(uint32x4_t addr, mve_pred16_t p)
{
    return vldrwq_gather_base_z_u32(addr, -0x12c, p);
}

// CHECK-LABEL: @test_vldrwq_gather_offset_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x float> @llvm.arm.mve.vldr.gather.offset.v4f32.p0f32.v4i32(float* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 0, i32 0)
// CHECK-NEXT:    ret <4 x float> [[TMP0]]
//
float32x4_t test_vldrwq_gather_offset_f32(const float32_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrwq_gather_offset_f32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i32.v4i32(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 0, i32 0)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
int32x4_t test_vldrwq_gather_offset_s32(const int32_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrwq_gather_offset_s32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i32.v4i32(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 0, i32 1)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
uint32x4_t test_vldrwq_gather_offset_u32(const uint32_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrwq_gather_offset_u32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_offset_z_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x float> @llvm.arm.mve.vldr.gather.offset.predicated.v4f32.p0f32.v4i32.v4i1(float* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x float> [[TMP2]]
//
float32x4_t test_vldrwq_gather_offset_z_f32(const float32_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrwq_gather_offset_z_f32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_offset_z_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i32.v4i32.v4i1(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
int32x4_t test_vldrwq_gather_offset_z_s32(const int32_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrwq_gather_offset_z_s32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_offset_z_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i32.v4i32.v4i1(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
uint32x4_t test_vldrwq_gather_offset_z_u32(const uint32_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrwq_gather_offset_z_u32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_shifted_offset_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x float> @llvm.arm.mve.vldr.gather.offset.v4f32.p0f32.v4i32(float* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 2, i32 0)
// CHECK-NEXT:    ret <4 x float> [[TMP0]]
//
float32x4_t test_vldrwq_gather_shifted_offset_f32(const float32_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrwq_gather_shifted_offset_f32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_shifted_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i32.v4i32(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 2, i32 0)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
int32x4_t test_vldrwq_gather_shifted_offset_s32(const int32_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrwq_gather_shifted_offset_s32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_shifted_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i32.v4i32(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 2, i32 1)
// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
//
uint32x4_t test_vldrwq_gather_shifted_offset_u32(const uint32_t *base, uint32x4_t offset)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_shifted_offset(base, offset);
#else /* POLYMORPHIC */
    return vldrwq_gather_shifted_offset_u32(base, offset);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_shifted_offset_z_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x float> @llvm.arm.mve.vldr.gather.offset.predicated.v4f32.p0f32.v4i32.v4i1(float* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 2, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x float> [[TMP2]]
//
float32x4_t test_vldrwq_gather_shifted_offset_z_f32(const float32_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrwq_gather_shifted_offset_z_f32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_shifted_offset_z_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i32.v4i32.v4i1(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 2, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
int32x4_t test_vldrwq_gather_shifted_offset_z_s32(const int32_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrwq_gather_shifted_offset_z_s32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vldrwq_gather_shifted_offset_z_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.predicated.v4i32.p0i32.v4i32.v4i1(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], i32 32, i32 2, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret <4 x i32> [[TMP2]]
//
uint32x4_t test_vldrwq_gather_shifted_offset_z_u32(const uint32_t *base, uint32x4_t offset, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    return vldrwq_gather_shifted_offset_z(base, offset, p);
#else /* POLYMORPHIC */
    return vldrwq_gather_shifted_offset_z_u32(base, offset, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_p_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i8.v8i16.v8i16.v8i1(i8* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 8, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_p_s16(int8_t *base, uint16x8_t offset, int16x8_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_p_s16(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_p_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i8.v4i32.v4i32.v4i1(i8* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 8, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_p_s32(int8_t *base, uint32x4_t offset, int32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_p_s32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_p_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i8.v16i8.v16i8.v16i1(i8* [[BASE:%.*]], <16 x i8> [[OFFSET:%.*]], <16 x i8> [[VALUE:%.*]], i32 8, i32 0, <16 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_p_s8(int8_t *base, uint8x16_t offset, int8x16_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_p_s8(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_p_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i8.v8i16.v8i16.v8i1(i8* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 8, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_p_u16(uint8_t *base, uint16x8_t offset, uint16x8_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_p_u16(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_p_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i8.v4i32.v4i32.v4i1(i8* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 8, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_p_u32(uint8_t *base, uint32x4_t offset, uint32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_p_u32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_p_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i8.v16i8.v16i8.v16i1(i8* [[BASE:%.*]], <16 x i8> [[OFFSET:%.*]], <16 x i8> [[VALUE:%.*]], i32 8, i32 0, <16 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_p_u8(uint8_t *base, uint8x16_t offset, uint8x16_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_p_u8(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i8.v8i16.v8i16(i8* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 8, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_s16(int8_t *base, uint16x8_t offset, int16x8_t value)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_s16(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i8.v4i32.v4i32(i8* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 8, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_s32(int8_t *base, uint32x4_t offset, int32x4_t value)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_s32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i8.v16i8.v16i8(i8* [[BASE:%.*]], <16 x i8> [[OFFSET:%.*]], <16 x i8> [[VALUE:%.*]], i32 8, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_s8(int8_t *base, uint8x16_t offset, int8x16_t value)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_s8(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i8.v8i16.v8i16(i8* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 8, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_u16(uint8_t *base, uint16x8_t offset, uint16x8_t value)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_u16(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i8.v4i32.v4i32(i8* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 8, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_u32(uint8_t *base, uint32x4_t offset, uint32x4_t value)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_u32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrbq_scatter_offset_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i8.v16i8.v16i8(i8* [[BASE:%.*]], <16 x i8> [[OFFSET:%.*]], <16 x i8> [[VALUE:%.*]], i32 8, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrbq_scatter_offset_u8(uint8_t *base, uint8x16_t offset, uint8x16_t value)
{
#ifdef POLYMORPHIC
    vstrbq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrbq_scatter_offset_u8(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_base_p_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.predicated.v2i64.v2i64.v4i1(<2 x i64> [[ADDR:%.*]], i32 888, <2 x i64> [[VALUE:%.*]], <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_base_p_s64(uint64x2_t addr, int64x2_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_base_p(addr, 0x378, value, p);
#else /* POLYMORPHIC */
    vstrdq_scatter_base_p_s64(addr, 0x378, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_base_p_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.predicated.v2i64.v2i64.v4i1(<2 x i64> [[ADDR:%.*]], i32 264, <2 x i64> [[VALUE:%.*]], <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_base_p_u64(uint64x2_t addr, uint64x2_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_base_p(addr, 0x108, value, p);
#else /* POLYMORPHIC */
    vstrdq_scatter_base_p_u64(addr, 0x108, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_base_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.v2i64.v2i64(<2 x i64> [[ADDR:%.*]], i32 408, <2 x i64> [[VALUE:%.*]])
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_base_s64(uint64x2_t addr, int64x2_t value)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_base(addr, 0x198, value);
#else /* POLYMORPHIC */
    vstrdq_scatter_base_s64(addr, 0x198, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_base_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.v2i64.v2i64(<2 x i64> [[ADDR:%.*]], i32 -472, <2 x i64> [[VALUE:%.*]])
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_base_u64(uint64x2_t addr, uint64x2_t value)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_base(addr, -0x1d8, value);
#else /* POLYMORPHIC */
    vstrdq_scatter_base_u64(addr, -0x1d8, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_base_wb_p_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call <2 x i64> @llvm.arm.mve.vstr.scatter.base.wb.predicated.v2i64.v2i64.v4i1(<2 x i64> [[TMP0]], i32 248, <2 x i64> [[VALUE:%.*]], <4 x i1> [[TMP2]])
// CHECK-NEXT:    store <2 x i64> [[TMP3]], <2 x i64>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_base_wb_p_s64(uint64x2_t *addr, int64x2_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_base_wb_p(addr, 0xf8, value, p);
#else /* POLYMORPHIC */
    vstrdq_scatter_base_wb_p_s64(addr, 0xf8, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_base_wb_p_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call <2 x i64> @llvm.arm.mve.vstr.scatter.base.wb.predicated.v2i64.v2i64.v4i1(<2 x i64> [[TMP0]], i32 136, <2 x i64> [[VALUE:%.*]], <4 x i1> [[TMP2]])
// CHECK-NEXT:    store <2 x i64> [[TMP3]], <2 x i64>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_base_wb_p_u64(uint64x2_t *addr, uint64x2_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_base_wb_p(addr, 0x88, value, p);
#else /* POLYMORPHIC */
    vstrdq_scatter_base_wb_p_u64(addr, 0x88, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_base_wb_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i64> @llvm.arm.mve.vstr.scatter.base.wb.v2i64.v2i64(<2 x i64> [[TMP0]], i32 208, <2 x i64> [[VALUE:%.*]])
// CHECK-NEXT:    store <2 x i64> [[TMP1]], <2 x i64>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_base_wb_s64(uint64x2_t *addr, int64x2_t value)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_base_wb(addr, 0xd0, value);
#else /* POLYMORPHIC */
    vstrdq_scatter_base_wb_s64(addr, 0xd0, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_base_wb_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call <2 x i64> @llvm.arm.mve.vstr.scatter.base.wb.v2i64.v2i64(<2 x i64> [[TMP0]], i32 -168, <2 x i64> [[VALUE:%.*]])
// CHECK-NEXT:    store <2 x i64> [[TMP1]], <2 x i64>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_base_wb_u64(uint64x2_t *addr, uint64x2_t value)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_base_wb(addr, -0xa8, value);
#else /* POLYMORPHIC */
    vstrdq_scatter_base_wb_u64(addr, -0xa8, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_offset_p_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i64.v2i64.v2i64.v4i1(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], <2 x i64> [[VALUE:%.*]], i32 64, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_offset_p_s64(int64_t *base, uint64x2_t offset, int64x2_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrdq_scatter_offset_p_s64(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_offset_p_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i64.v2i64.v2i64.v4i1(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], <2 x i64> [[VALUE:%.*]], i32 64, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_offset_p_u64(uint64_t *base, uint64x2_t offset, uint64x2_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrdq_scatter_offset_p_u64(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_offset_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i64.v2i64.v2i64(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], <2 x i64> [[VALUE:%.*]], i32 64, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_offset_s64(int64_t *base, uint64x2_t offset, int64x2_t value)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrdq_scatter_offset_s64(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_offset_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i64.v2i64.v2i64(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], <2 x i64> [[VALUE:%.*]], i32 64, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_offset_u64(uint64_t *base, uint64x2_t offset, uint64x2_t value)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrdq_scatter_offset_u64(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_shifted_offset_p_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i64.v2i64.v2i64.v4i1(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], <2 x i64> [[VALUE:%.*]], i32 64, i32 3, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_shifted_offset_p_s64(int64_t *base, uint64x2_t offset, int64x2_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrdq_scatter_shifted_offset_p_s64(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_shifted_offset_p_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i64.v2i64.v2i64.v4i1(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], <2 x i64> [[VALUE:%.*]], i32 64, i32 3, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_shifted_offset_p_u64(uint64_t *base, uint64x2_t offset, uint64x2_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrdq_scatter_shifted_offset_p_u64(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_shifted_offset_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i64.v2i64.v2i64(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], <2 x i64> [[VALUE:%.*]], i32 64, i32 3)
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_shifted_offset_s64(int64_t *base, uint64x2_t offset, int64x2_t value)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrdq_scatter_shifted_offset_s64(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrdq_scatter_shifted_offset_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i64.v2i64.v2i64(i64* [[BASE:%.*]], <2 x i64> [[OFFSET:%.*]], <2 x i64> [[VALUE:%.*]], i32 64, i32 3)
// CHECK-NEXT:    ret void
//
void test_vstrdq_scatter_shifted_offset_u64(uint64_t *base, uint64x2_t offset, uint64x2_t value)
{
#ifdef POLYMORPHIC
    vstrdq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrdq_scatter_shifted_offset_u64(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0f16.v8i16.v8f16(half* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x half> [[VALUE:%.*]], i32 16, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_f16(float16_t *base, uint16x8_t offset, float16x8_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_f16(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_p_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0f16.v8i16.v8f16.v8i1(half* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x half> [[VALUE:%.*]], i32 16, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_p_f16(float16_t *base, uint16x8_t offset, float16x8_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_p_f16(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_p_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i16.v8i16.v8i16.v8i1(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 16, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_p_s16(int16_t *base, uint16x8_t offset, int16x8_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_p_s16(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_p_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i16.v4i32.v4i32.v4i1(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 16, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_p_s32(int16_t *base, uint32x4_t offset, int32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_p_s32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_p_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i16.v8i16.v8i16.v8i1(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 16, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_p_u16(uint16_t *base, uint16x8_t offset, uint16x8_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_p_u16(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_p_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i16.v4i32.v4i32.v4i1(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 16, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_p_u32(uint16_t *base, uint32x4_t offset, uint32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_p_u32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i16.v8i16.v8i16(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 16, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_s16(int16_t *base, uint16x8_t offset, int16x8_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_s16(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i16.v4i32.v4i32(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 16, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_s32(int16_t *base, uint32x4_t offset, int32x4_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_s32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i16.v8i16.v8i16(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 16, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_u16(uint16_t *base, uint16x8_t offset, uint16x8_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_u16(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i16.v4i32.v4i32(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 16, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_offset_u32(uint16_t *base, uint32x4_t offset, uint32x4_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_offset_u32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0f16.v8i16.v8f16(half* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x half> [[VALUE:%.*]], i32 16, i32 1)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_f16(float16_t *base, uint16x8_t offset, float16x8_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_f16(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_p_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0f16.v8i16.v8f16.v8i1(half* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x half> [[VALUE:%.*]], i32 16, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_p_f16(float16_t *base, uint16x8_t offset, float16x8_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_p_f16(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_p_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i16.v8i16.v8i16.v8i1(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 16, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_p_s16(int16_t *base, uint16x8_t offset, int16x8_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_p_s16(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_p_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i16.v4i32.v4i32.v4i1(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 16, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_p_s32(int16_t *base, uint32x4_t offset, int32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_p_s32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_p_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i16.v8i16.v8i16.v8i1(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 16, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_p_u16(uint16_t *base, uint16x8_t offset, uint16x8_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_p_u16(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_p_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i16.v4i32.v4i32.v4i1(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 16, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_p_u32(uint16_t *base, uint32x4_t offset, uint32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_p_u32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i16.v8i16.v8i16(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 16, i32 1)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_s16(int16_t *base, uint16x8_t offset, int16x8_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_s16(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i16.v4i32.v4i32(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 16, i32 1)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_s32(int16_t *base, uint32x4_t offset, int32x4_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_s32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i16.v8i16.v8i16(i16* [[BASE:%.*]], <8 x i16> [[OFFSET:%.*]], <8 x i16> [[VALUE:%.*]], i32 16, i32 1)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_u16(uint16_t *base, uint16x8_t offset, uint16x8_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_u16(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrhq_scatter_shifted_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i16.v4i32.v4i32(i16* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 16, i32 1)
// CHECK-NEXT:    ret void
//
void test_vstrhq_scatter_shifted_offset_u32(uint16_t *base, uint32x4_t offset, uint32x4_t value)
{
#ifdef POLYMORPHIC
    vstrhq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrhq_scatter_shifted_offset_u32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.v4i32.v4f32(<4 x i32> [[ADDR:%.*]], i32 380, <4 x float> [[VALUE:%.*]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_f32(uint32x4_t addr, float32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base(addr, 0x17c, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_f32(addr, 0x17c, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_p_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.predicated.v4i32.v4f32.v4i1(<4 x i32> [[ADDR:%.*]], i32 -400, <4 x float> [[VALUE:%.*]], <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_p_f32(uint32x4_t addr, float32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_p(addr, -0x190, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_p_f32(addr, -0x190, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_p_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.predicated.v4i32.v4i32.v4i1(<4 x i32> [[ADDR:%.*]], i32 48, <4 x i32> [[VALUE:%.*]], <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_p_s32(uint32x4_t addr, int32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_p(addr, 0x30, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_p_s32(addr, 0x30, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_p_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.predicated.v4i32.v4i32.v4i1(<4 x i32> [[ADDR:%.*]], i32 -376, <4 x i32> [[VALUE:%.*]], <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_p_u32(uint32x4_t addr, uint32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_p(addr, -0x178, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_p_u32(addr, -0x178, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.v4i32.v4i32(<4 x i32> [[ADDR:%.*]], i32 156, <4 x i32> [[VALUE:%.*]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_s32(uint32x4_t addr, int32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base(addr, 0x9c, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_s32(addr, 0x9c, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.base.v4i32.v4i32(<4 x i32> [[ADDR:%.*]], i32 212, <4 x i32> [[VALUE:%.*]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_u32(uint32x4_t addr, uint32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base(addr, 0xd4, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_u32(addr, 0xd4, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_wb_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i32> @llvm.arm.mve.vstr.scatter.base.wb.v4i32.v4f32(<4 x i32> [[TMP0]], i32 -412, <4 x float> [[VALUE:%.*]])
// CHECK-NEXT:    store <4 x i32> [[TMP1]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_wb_f32(uint32x4_t *addr, float32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_wb(addr, -0x19c, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_wb_f32(addr, -0x19c, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_wb_p_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call <4 x i32> @llvm.arm.mve.vstr.scatter.base.wb.predicated.v4i32.v4f32.v4i1(<4 x i32> [[TMP0]], i32 236, <4 x float> [[VALUE:%.*]], <4 x i1> [[TMP2]])
// CHECK-NEXT:    store <4 x i32> [[TMP3]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_wb_p_f32(uint32x4_t *addr, float32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_wb_p(addr, 0xec, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_wb_p_f32(addr, 0xec, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_wb_p_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call <4 x i32> @llvm.arm.mve.vstr.scatter.base.wb.predicated.v4i32.v4i32.v4i1(<4 x i32> [[TMP0]], i32 328, <4 x i32> [[VALUE:%.*]], <4 x i1> [[TMP2]])
// CHECK-NEXT:    store <4 x i32> [[TMP3]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_wb_p_s32(uint32x4_t *addr, int32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_wb_p(addr, 0x148, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_wb_p_s32(addr, 0x148, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_wb_p_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
// CHECK-NEXT:    [[TMP3:%.*]] = call <4 x i32> @llvm.arm.mve.vstr.scatter.base.wb.predicated.v4i32.v4i32.v4i1(<4 x i32> [[TMP0]], i32 412, <4 x i32> [[VALUE:%.*]], <4 x i1> [[TMP2]])
// CHECK-NEXT:    store <4 x i32> [[TMP3]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_wb_p_u32(uint32x4_t *addr, uint32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_wb_p(addr, 0x19c, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_wb_p_u32(addr, 0x19c, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_wb_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i32> @llvm.arm.mve.vstr.scatter.base.wb.v4i32.v4i32(<4 x i32> [[TMP0]], i32 -152, <4 x i32> [[VALUE:%.*]])
// CHECK-NEXT:    store <4 x i32> [[TMP1]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_wb_s32(uint32x4_t *addr, int32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_wb(addr, -0x98, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_wb_s32(addr, -0x98, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_base_wb_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i32> @llvm.arm.mve.vstr.scatter.base.wb.v4i32.v4i32(<4 x i32> [[TMP0]], i32 64, <4 x i32> [[VALUE:%.*]])
// CHECK-NEXT:    store <4 x i32> [[TMP1]], <4 x i32>* [[ADDR]], align 8
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_base_wb_u32(uint32x4_t *addr, uint32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_base_wb(addr, 0x40, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_base_wb_u32(addr, 0x40, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_offset_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0f32.v4i32.v4f32(float* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x float> [[VALUE:%.*]], i32 32, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_offset_f32(float32_t *base, uint32x4_t offset, float32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_offset_f32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_offset_p_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0f32.v4i32.v4f32.v4i1(float* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x float> [[VALUE:%.*]], i32 32, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_offset_p_f32(float32_t *base, uint32x4_t offset, float32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_offset_p_f32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_offset_p_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i32.v4i32.v4i32.v4i1(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 32, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_offset_p_s32(int32_t *base, uint32x4_t offset, int32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_offset_p_s32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_offset_p_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i32.v4i32.v4i32.v4i1(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 32, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_offset_p_u32(uint32_t *base, uint32x4_t offset, uint32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_offset_p_u32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i32.v4i32.v4i32(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 32, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_offset_s32(int32_t *base, uint32x4_t offset, int32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_offset_s32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i32.v4i32.v4i32(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 32, i32 0)
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_offset_u32(uint32_t *base, uint32x4_t offset, uint32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_offset_u32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_shifted_offset_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0f32.v4i32.v4f32(float* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x float> [[VALUE:%.*]], i32 32, i32 2)
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_shifted_offset_f32(float32_t *base, uint32x4_t offset, float32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_shifted_offset_f32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_shifted_offset_p_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0f32.v4i32.v4f32.v4i1(float* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x float> [[VALUE:%.*]], i32 32, i32 2, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_shifted_offset_p_f32(float32_t *base, uint32x4_t offset, float32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_shifted_offset_p_f32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_shifted_offset_p_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i32.v4i32.v4i32.v4i1(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 32, i32 2, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_shifted_offset_p_s32(int32_t *base, uint32x4_t offset, int32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_shifted_offset_p_s32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_shifted_offset_p_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.predicated.p0i32.v4i32.v4i32.v4i1(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 32, i32 2, <4 x i1> [[TMP1]])
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_shifted_offset_p_u32(uint32_t *base, uint32x4_t offset, uint32x4_t value, mve_pred16_t p)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_shifted_offset_p(base, offset, value, p);
#else /* POLYMORPHIC */
    vstrwq_scatter_shifted_offset_p_u32(base, offset, value, p);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_shifted_offset_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i32.v4i32.v4i32(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 32, i32 2)
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_shifted_offset_s32(int32_t *base, uint32x4_t offset, int32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_shifted_offset_s32(base, offset, value);
#endif /* POLYMORPHIC */
}

// CHECK-LABEL: @test_vstrwq_scatter_shifted_offset_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    call void @llvm.arm.mve.vstr.scatter.offset.p0i32.v4i32.v4i32(i32* [[BASE:%.*]], <4 x i32> [[OFFSET:%.*]], <4 x i32> [[VALUE:%.*]], i32 32, i32 2)
// CHECK-NEXT:    ret void
//
void test_vstrwq_scatter_shifted_offset_u32(uint32_t *base, uint32x4_t offset, uint32x4_t value)
{
#ifdef POLYMORPHIC
    vstrwq_scatter_shifted_offset(base, offset, value);
#else /* POLYMORPHIC */
    vstrwq_scatter_shifted_offset_u32(base, offset, value);
#endif /* POLYMORPHIC */
}