diff options
| author | Manuel Bottini <manuel.bottini@arm.com> | 2019-11-13 17:24:43 +0000 |
|---|---|---|
| committer | SiCong Li <sicong.li@arm.com> | 2019-11-21 13:21:33 +0000 |
| commit | 3e84bb662f9c6c3f77837640b44c41b7e3403ed4 (patch) | |
| tree | 7096e2a6506baf62ddea78556413fa193ebec76f /arm_compute/core/NEON/wrapper/intrinsics/add.h | |
| parent | 5f7dda6f415f8f065f86b9f52ee6c5c85bbaa5e4 (diff) | |
| download | ComputeLibrary-3e84bb662f9c6c3f77837640b44c41b7e3403ed4.tar.gz | |
COMPMID-2920: NEInstanceNormalization fails on NHWC validations
Improved TensorInfo to accept DataLayout, useful to test the validate functions
Removing nighlies tests
Moving all vpadds instructions in add.h
Change-Id: I96290a6f26272eae865dba48bbc3c6aee4bc0214
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2287
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/wrapper/intrinsics/add.h')
| -rw-r--r-- | arm_compute/core/NEON/wrapper/intrinsics/add.h | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/arm_compute/core/NEON/wrapper/intrinsics/add.h b/arm_compute/core/NEON/wrapper/intrinsics/add.h index 1839170485..f0823463af 100644 --- a/arm_compute/core/NEON/wrapper/intrinsics/add.h +++ b/arm_compute/core/NEON/wrapper/intrinsics/add.h @@ -176,6 +176,26 @@ VPADDL_IMPL(int32x4_t, int16x8_t, vpaddlq, s16) VPADDL_IMPL(uint64x2_t, uint32x4_t, vpaddlq, u32) VPADDL_IMPL(int64x2_t, int32x4_t, vpaddlq, s32) #undef VPADDL_IMPL + +// VPADD: Add pairwise +#define VPADD_IMPL(stype, vtype, prefix, postfix) \ + inline vtype vpadd(const vtype &a, const vtype &b) \ + { \ + return prefix##_##postfix(a, b); \ + } + +VPADD_IMPL(uint8x8_t, uint8x8_t, vpadd, u8) +VPADD_IMPL(int8x8_t, int8x8_t, vpadd, s8) +VPADD_IMPL(uint16x4_t, uint16x4_t, vpadd, u16) +VPADD_IMPL(int16x4_t, int16x4_t, vpadd, s16) +VPADD_IMPL(uint32x2_t, uint32x2_t, vpadd, u32) +VPADD_IMPL(int32x2_t, int32x2_t, vpadd, s32) +VPADD_IMPL(float32x2_t, float32x2_t, vpadd, f32) +#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC +VPADD_IMPL(float16x4_t, float16x4_t, vpadd, f16) +#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC + +#undef VPADD_IMPL } // namespace wrapper } // namespace arm_compute #endif /* __ARM_COMPUTE_WRAPPER_ADD_H__ */ |