forked from OSchip/llvm-project
1326 lines
46 KiB
C
1326 lines
46 KiB
C
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
|
|
// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-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-arm-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
|
|
|
|
#include <arm_mve.h>
|
|
|
|
// CHECK-LABEL: @test_vld1q_f16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast half* [[BASE:%.*]] to <8 x half>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x half>, <8 x half>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret <8 x half> [[TMP1]]
|
|
//
|
|
float16x8_t test_vld1q_f16(const float16_t *base)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q(base);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_f16(base);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_f32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[BASE:%.*]] to <4 x float>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret <4 x float> [[TMP1]]
|
|
//
|
|
float32x4_t test_vld1q_f32(const float32_t *base)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q(base);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_f32(base);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_s8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP1]]
|
|
//
|
|
int8x16_t test_vld1q_s8(const int8_t *base)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q(base);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_s8(base);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP1]]
|
|
//
|
|
int16x8_t test_vld1q_s16(const int16_t *base)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q(base);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_s16(base);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP1]]
|
|
//
|
|
int32x4_t test_vld1q_s32(const int32_t *base)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q(base);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_s32(base);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP1]]
|
|
//
|
|
uint8x16_t test_vld1q_u8(const uint8_t *base)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q(base);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_u8(base);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP1]]
|
|
//
|
|
uint16x8_t test_vld1q_u16(const uint16_t *base)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q(base);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_u16(base);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP1]]
|
|
//
|
|
uint32x4_t test_vld1q_u32(const uint32_t *base)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q(base);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_u32(base);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_z_f16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast half* [[BASE:%.*]] to <8 x half>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>* [[TMP0]], i32 2, <8 x i1> [[TMP2]], <8 x half> zeroinitializer)
|
|
// CHECK-NEXT: ret <8 x half> [[TMP3]]
|
|
//
|
|
float16x8_t test_vld1q_z_f16(const float16_t *base, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q_z(base, p);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_z_f16(base, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_z_f32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[BASE:%.*]] to <4 x float>*
|
|
// 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> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* [[TMP0]], i32 4, <4 x i1> [[TMP2]], <4 x float> zeroinitializer)
|
|
// CHECK-NEXT: ret <4 x float> [[TMP3]]
|
|
//
|
|
float32x4_t test_vld1q_z_f32(const float32_t *base, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q_z(base, p);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_z_f32(base, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_z_s8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP0]], i32 1, <16 x i1> [[TMP2]], <16 x i8> zeroinitializer)
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP3]]
|
|
//
|
|
int8x16_t test_vld1q_z_s8(const int8_t *base, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q_z(base, p);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_z_s8(base, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_z_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP0]], i32 2, <8 x i1> [[TMP2]], <8 x i16> zeroinitializer)
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP3]]
|
|
//
|
|
int16x8_t test_vld1q_z_s16(const int16_t *base, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q_z(base, p);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_z_s16(base, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_z_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// 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.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]], <4 x i32> zeroinitializer)
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP3]]
|
|
//
|
|
int32x4_t test_vld1q_z_s32(const int32_t *base, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q_z(base, p);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_z_s32(base, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_z_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP0]], i32 1, <16 x i1> [[TMP2]], <16 x i8> zeroinitializer)
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP3]]
|
|
//
|
|
uint8x16_t test_vld1q_z_u8(const uint8_t *base, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q_z(base, p);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_z_u8(base, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_z_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP0]], i32 2, <8 x i1> [[TMP2]], <8 x i16> zeroinitializer)
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP3]]
|
|
//
|
|
uint16x8_t test_vld1q_z_u16(const uint16_t *base, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q_z(base, p);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_z_u16(base, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vld1q_z_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// 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.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]], <4 x i32> zeroinitializer)
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP3]]
|
|
//
|
|
uint32x4_t test_vld1q_z_u32(const uint32_t *base, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
return vld1q_z(base, p);
|
|
#else /* POLYMORPHIC */
|
|
return vld1q_z_u32(base, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_s8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP1]]
|
|
//
|
|
int8x16_t test_vldrbq_s8(const int8_t *base)
|
|
{
|
|
return vldrbq_s8(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <8 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: [[TMP2:%.*]] = sext <8 x i8> [[TMP1]] to <8 x i16>
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
|
|
//
|
|
int16x8_t test_vldrbq_s16(const int8_t *base)
|
|
{
|
|
return vldrbq_s16(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <4 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i8>, <4 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: [[TMP2:%.*]] = sext <4 x i8> [[TMP1]] to <4 x i32>
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
|
|
//
|
|
int32x4_t test_vldrbq_s32(const int8_t *base)
|
|
{
|
|
return vldrbq_s32(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP1]]
|
|
//
|
|
uint8x16_t test_vldrbq_u8(const uint8_t *base)
|
|
{
|
|
return vldrbq_u8(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <8 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext <8 x i8> [[TMP1]] to <8 x i16>
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
|
|
//
|
|
uint16x8_t test_vldrbq_u16(const uint8_t *base)
|
|
{
|
|
return vldrbq_u16(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <4 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i8>, <4 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext <4 x i8> [[TMP1]] to <4 x i32>
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
|
|
//
|
|
uint32x4_t test_vldrbq_u32(const uint8_t *base)
|
|
{
|
|
return vldrbq_u32(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_z_s8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP0]], i32 1, <16 x i1> [[TMP2]], <16 x i8> zeroinitializer)
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP3]]
|
|
//
|
|
int8x16_t test_vldrbq_z_s8(const int8_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrbq_z_s8(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_z_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <8 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* [[TMP0]], i32 1, <8 x i1> [[TMP2]], <8 x i8> zeroinitializer)
|
|
// CHECK-NEXT: [[TMP4:%.*]] = sext <8 x i8> [[TMP3]] to <8 x i16>
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP4]]
|
|
//
|
|
int16x8_t test_vldrbq_z_s16(const int8_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrbq_z_s16(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_z_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <4 x i8>*
|
|
// 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 i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* [[TMP0]], i32 1, <4 x i1> [[TMP2]], <4 x i8> zeroinitializer)
|
|
// CHECK-NEXT: [[TMP4:%.*]] = sext <4 x i8> [[TMP3]] to <4 x i32>
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP4]]
|
|
//
|
|
int32x4_t test_vldrbq_z_s32(const int8_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrbq_z_s32(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_z_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* [[TMP0]], i32 1, <16 x i1> [[TMP2]], <16 x i8> zeroinitializer)
|
|
// CHECK-NEXT: ret <16 x i8> [[TMP3]]
|
|
//
|
|
uint8x16_t test_vldrbq_z_u8(const uint8_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrbq_z_u8(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_z_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <8 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* [[TMP0]], i32 1, <8 x i1> [[TMP2]], <8 x i8> zeroinitializer)
|
|
// CHECK-NEXT: [[TMP4:%.*]] = zext <8 x i8> [[TMP3]] to <8 x i16>
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP4]]
|
|
//
|
|
uint16x8_t test_vldrbq_z_u16(const uint8_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrbq_z_u16(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrbq_z_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <4 x i8>*
|
|
// 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 i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* [[TMP0]], i32 1, <4 x i1> [[TMP2]], <4 x i8> zeroinitializer)
|
|
// CHECK-NEXT: [[TMP4:%.*]] = zext <4 x i8> [[TMP3]] to <4 x i32>
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP4]]
|
|
//
|
|
uint32x4_t test_vldrbq_z_u32(const uint8_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrbq_z_u32(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_f16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast half* [[BASE:%.*]] to <8 x half>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x half>, <8 x half>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret <8 x half> [[TMP1]]
|
|
//
|
|
float16x8_t test_vldrhq_f16(const float16_t *base)
|
|
{
|
|
return vldrhq_f16(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP1]]
|
|
//
|
|
int16x8_t test_vldrhq_s16(const int16_t *base)
|
|
{
|
|
return vldrhq_s16(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <4 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: [[TMP2:%.*]] = sext <4 x i16> [[TMP1]] to <4 x i32>
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
|
|
//
|
|
int32x4_t test_vldrhq_s32(const int16_t *base)
|
|
{
|
|
return vldrhq_s32(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP1]]
|
|
//
|
|
uint16x8_t test_vldrhq_u16(const uint16_t *base)
|
|
{
|
|
return vldrhq_u16(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <4 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i16>, <4 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext <4 x i16> [[TMP1]] to <4 x i32>
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
|
|
//
|
|
uint32x4_t test_vldrhq_u32(const uint16_t *base)
|
|
{
|
|
return vldrhq_u32(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_z_f16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast half* [[BASE:%.*]] to <8 x half>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>* [[TMP0]], i32 2, <8 x i1> [[TMP2]], <8 x half> zeroinitializer)
|
|
// CHECK-NEXT: ret <8 x half> [[TMP3]]
|
|
//
|
|
float16x8_t test_vldrhq_z_f16(const float16_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrhq_z_f16(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_z_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP0]], i32 2, <8 x i1> [[TMP2]], <8 x i16> zeroinitializer)
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP3]]
|
|
//
|
|
int16x8_t test_vldrhq_z_s16(const int16_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrhq_z_s16(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_z_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <4 x i16>*
|
|
// 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 i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* [[TMP0]], i32 2, <4 x i1> [[TMP2]], <4 x i16> zeroinitializer)
|
|
// CHECK-NEXT: [[TMP4:%.*]] = sext <4 x i16> [[TMP3]] to <4 x i32>
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP4]]
|
|
//
|
|
int32x4_t test_vldrhq_z_s32(const int16_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrhq_z_s32(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_z_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* [[TMP0]], i32 2, <8 x i1> [[TMP2]], <8 x i16> zeroinitializer)
|
|
// CHECK-NEXT: ret <8 x i16> [[TMP3]]
|
|
//
|
|
uint16x8_t test_vldrhq_z_u16(const uint16_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrhq_z_u16(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrhq_z_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <4 x i16>*
|
|
// 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 i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* [[TMP0]], i32 2, <4 x i1> [[TMP2]], <4 x i16> zeroinitializer)
|
|
// CHECK-NEXT: [[TMP4:%.*]] = zext <4 x i16> [[TMP3]] to <4 x i32>
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP4]]
|
|
//
|
|
uint32x4_t test_vldrhq_z_u32(const uint16_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrhq_z_u32(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrwq_f32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[BASE:%.*]] to <4 x float>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret <4 x float> [[TMP1]]
|
|
//
|
|
float32x4_t test_vldrwq_f32(const float32_t *base)
|
|
{
|
|
return vldrwq_f32(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrwq_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP1]]
|
|
//
|
|
int32x4_t test_vldrwq_s32(const int32_t *base)
|
|
{
|
|
return vldrwq_s32(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrwq_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP1]]
|
|
//
|
|
uint32x4_t test_vldrwq_u32(const uint32_t *base)
|
|
{
|
|
return vldrwq_u32(base);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrwq_z_f32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[BASE:%.*]] to <4 x float>*
|
|
// 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> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* [[TMP0]], i32 4, <4 x i1> [[TMP2]], <4 x float> zeroinitializer)
|
|
// CHECK-NEXT: ret <4 x float> [[TMP3]]
|
|
//
|
|
float32x4_t test_vldrwq_z_f32(const float32_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrwq_z_f32(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrwq_z_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// 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.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]], <4 x i32> zeroinitializer)
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP3]]
|
|
//
|
|
int32x4_t test_vldrwq_z_s32(const int32_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrwq_z_s32(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vldrwq_z_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// 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.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]], <4 x i32> zeroinitializer)
|
|
// CHECK-NEXT: ret <4 x i32> [[TMP3]]
|
|
//
|
|
uint32x4_t test_vldrwq_z_u32(const uint32_t *base, mve_pred16_t p)
|
|
{
|
|
return vldrwq_z_u32(base, p);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_f16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast half* [[BASE:%.*]] to <8 x half>*
|
|
// CHECK-NEXT: store <8 x half> [[VALUE:%.*]], <8 x half>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_f16(float16_t *base, float16x8_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_f16(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_f32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[BASE:%.*]] to <4 x float>*
|
|
// CHECK-NEXT: store <4 x float> [[VALUE:%.*]], <4 x float>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_f32(float32_t *base, float32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_f32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_s8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: store <16 x i8> [[VALUE:%.*]], <16 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_s8(int8_t *base, int8x16_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_s8(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: store <8 x i16> [[VALUE:%.*]], <8 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_s16(int16_t *base, int16x8_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_s16(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// CHECK-NEXT: store <4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_s32(int32_t *base, int32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_s32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: store <16 x i8> [[VALUE:%.*]], <16 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_u8(uint8_t *base, uint8x16_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_u8(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: store <8 x i16> [[VALUE:%.*]], <8 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_u16(uint16_t *base, uint16x8_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_u16(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// CHECK-NEXT: store <4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_u32(uint32_t *base, uint32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_u32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_p_f16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast half* [[BASE:%.*]] to <8 x half>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> [[VALUE:%.*]], <8 x half>* [[TMP0]], i32 2, <8 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_p_f16(float16_t *base, float16x8_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_p_f16(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_p_f32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[BASE:%.*]] to <4 x float>*
|
|
// 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: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> [[VALUE:%.*]], <4 x float>* [[TMP0]], i32 4, <4 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_p_f32(float32_t *base, float32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_p_f32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_p_s8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> [[VALUE:%.*]], <16 x i8>* [[TMP0]], i32 1, <16 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_p_s8(int8_t *base, int8x16_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_p_s8(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_p_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> [[VALUE:%.*]], <8 x i16>* [[TMP0]], i32 2, <8 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_p_s16(int16_t *base, int16x8_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_p_s16(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_p_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// 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: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_p_s32(int32_t *base, int32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_p_s32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_p_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> [[VALUE:%.*]], <16 x i8>* [[TMP0]], i32 1, <16 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_p_u8(uint8_t *base, uint8x16_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_p_u8(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_p_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> [[VALUE:%.*]], <8 x i16>* [[TMP0]], i32 2, <8 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_p_u16(uint16_t *base, uint16x8_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_p_u16(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vst1q_p_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// 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: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vst1q_p_u32(uint32_t *base, uint32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vst1q_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vst1q_p_u32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_s8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: store <16 x i8> [[VALUE:%.*]], <16 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_s8(int8_t *base, int8x16_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_s8(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <8 x i16> [[VALUE:%.*]] to <8 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[BASE:%.*]] to <8 x i8>*
|
|
// CHECK-NEXT: store <8 x i8> [[TMP0]], <8 x i8>* [[TMP1]], align 1
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_s16(int8_t *base, int16x8_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_s16(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[VALUE:%.*]] to <4 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[BASE:%.*]] to <4 x i8>*
|
|
// CHECK-NEXT: store <4 x i8> [[TMP0]], <4 x i8>* [[TMP1]], align 1
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_s32(int8_t *base, int32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_s32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: store <16 x i8> [[VALUE:%.*]], <16 x i8>* [[TMP0]], align 1
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_u8(uint8_t *base, uint8x16_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_u8(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <8 x i16> [[VALUE:%.*]] to <8 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[BASE:%.*]] to <8 x i8>*
|
|
// CHECK-NEXT: store <8 x i8> [[TMP0]], <8 x i8>* [[TMP1]], align 1
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_u16(uint8_t *base, uint16x8_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_u16(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[VALUE:%.*]] to <4 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[BASE:%.*]] to <4 x i8>*
|
|
// CHECK-NEXT: store <4 x i8> [[TMP0]], <4 x i8>* [[TMP1]], align 1
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_u32(uint8_t *base, uint32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_u32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_p_s8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> [[VALUE:%.*]], <16 x i8>* [[TMP0]], i32 1, <16 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_p_s8(int8_t *base, int8x16_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_p_s8(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_p_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <8 x i16> [[VALUE:%.*]] to <8 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[BASE:%.*]] to <8 x i8>*
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP2]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> [[TMP0]], <8 x i8>* [[TMP1]], i32 1, <8 x i1> [[TMP3]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_p_s16(int8_t *base, int16x8_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_p_s16(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_p_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[VALUE:%.*]] to <4 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[BASE:%.*]] to <4 x i8>*
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP2]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v4i8.p0v4i8(<4 x i8> [[TMP0]], <4 x i8>* [[TMP1]], i32 1, <4 x i1> [[TMP3]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_p_s32(int8_t *base, int32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_p_s32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_p_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[BASE:%.*]] to <16 x i8>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> [[VALUE:%.*]], <16 x i8>* [[TMP0]], i32 1, <16 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_p_u8(uint8_t *base, uint8x16_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_p_u8(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_p_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <8 x i16> [[VALUE:%.*]] to <8 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[BASE:%.*]] to <8 x i8>*
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP2]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v8i8.p0v8i8(<8 x i8> [[TMP0]], <8 x i8>* [[TMP1]], i32 1, <8 x i1> [[TMP3]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_p_u16(uint8_t *base, uint16x8_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_p_u16(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrbq_p_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[VALUE:%.*]] to <4 x i8>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i8* [[BASE:%.*]] to <4 x i8>*
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP2]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v4i8.p0v4i8(<4 x i8> [[TMP0]], <4 x i8>* [[TMP1]], i32 1, <4 x i1> [[TMP3]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrbq_p_u32(uint8_t *base, uint32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrbq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrbq_p_u32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_f16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast half* [[BASE:%.*]] to <8 x half>*
|
|
// CHECK-NEXT: store <8 x half> [[VALUE:%.*]], <8 x half>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_f16(float16_t *base, float16x8_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_f16(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: store <8 x i16> [[VALUE:%.*]], <8 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_s16(int16_t *base, int16x8_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_s16(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[VALUE:%.*]] to <4 x i16>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i16* [[BASE:%.*]] to <4 x i16>*
|
|
// CHECK-NEXT: store <4 x i16> [[TMP0]], <4 x i16>* [[TMP1]], align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_s32(int16_t *base, int32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_s32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: store <8 x i16> [[VALUE:%.*]], <8 x i16>* [[TMP0]], align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_u16(uint16_t *base, uint16x8_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_u16(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[VALUE:%.*]] to <4 x i16>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i16* [[BASE:%.*]] to <4 x i16>*
|
|
// CHECK-NEXT: store <4 x i16> [[TMP0]], <4 x i16>* [[TMP1]], align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_u32(uint16_t *base, uint32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_u32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_p_f16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast half* [[BASE:%.*]] to <8 x half>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> [[VALUE:%.*]], <8 x half>* [[TMP0]], i32 2, <8 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_p_f16(float16_t *base, float16x8_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_p_f16(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_p_s16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> [[VALUE:%.*]], <8 x i16>* [[TMP0]], i32 2, <8 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_p_s16(int16_t *base, int16x8_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_p_s16(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_p_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[VALUE:%.*]] to <4 x i16>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i16* [[BASE:%.*]] to <4 x i16>*
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP2]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> [[TMP0]], <4 x i16>* [[TMP1]], i32 2, <4 x i1> [[TMP3]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_p_s32(int16_t *base, int32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_p_s32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_p_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
|
|
// CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP1]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> [[VALUE:%.*]], <8 x i16>* [[TMP0]], i32 2, <8 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_p_u16(uint16_t *base, uint16x8_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_p_u16(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrhq_p_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[VALUE:%.*]] to <4 x i16>
|
|
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i16* [[BASE:%.*]] to <4 x i16>*
|
|
// CHECK-NEXT: [[TMP2:%.*]] = zext i16 [[P:%.*]] to i32
|
|
// CHECK-NEXT: [[TMP3:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP2]])
|
|
// CHECK-NEXT: call void @llvm.masked.store.v4i16.p0v4i16(<4 x i16> [[TMP0]], <4 x i16>* [[TMP1]], i32 2, <4 x i1> [[TMP3]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrhq_p_u32(uint16_t *base, uint32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrhq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrhq_p_u32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrwq_f32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[BASE:%.*]] to <4 x float>*
|
|
// CHECK-NEXT: store <4 x float> [[VALUE:%.*]], <4 x float>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrwq_f32(float32_t *base, float32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrwq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrwq_f32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrwq_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// CHECK-NEXT: store <4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrwq_s32(int32_t *base, int32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrwq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrwq_s32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrwq_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// CHECK-NEXT: store <4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], align 4
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrwq_u32(uint32_t *base, uint32x4_t value)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrwq(base, value);
|
|
#else /* POLYMORPHIC */
|
|
vstrwq_u32(base, value);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrwq_p_f32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[BASE:%.*]] to <4 x float>*
|
|
// 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: call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> [[VALUE:%.*]], <4 x float>* [[TMP0]], i32 4, <4 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrwq_p_f32(float32_t *base, float32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrwq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrwq_p_f32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrwq_p_s32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// 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: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrwq_p_s32(int32_t *base, int32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrwq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrwq_p_s32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vstrwq_p_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
|
|
// 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: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]])
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_vstrwq_p_u32(uint32_t *base, uint32x4_t value, mve_pred16_t p)
|
|
{
|
|
#ifdef POLYMORPHIC
|
|
vstrwq_p(base, value, p);
|
|
#else /* POLYMORPHIC */
|
|
vstrwq_p_u32(base, value, p);
|
|
#endif /* POLYMORPHIC */
|
|
}
|