diff options
| author | Omar Al Khatib <omar.alkhatib@arm.com> | 2022-12-20 14:36:45 +0000 |
|---|---|---|
| committer | Omar Al Khatib <omar.alkhatib@arm.com> | 2022-12-29 09:14:15 +0000 |
| commit | 939b21ad4b9ed15d43b4ee8b17484e57ed55a01f (patch) | |
| tree | 6c90f78ad73161ffd0f54956a77fa50ef1916819 /src/cpu/kernels/add/generic/neon/impl.h | |
| parent | bb1ab0505452691d0e536921cd4c4e2ce32e40ed (diff) | |
| download | ComputeLibrary-939b21ad4b9ed15d43b4ee8b17484e57ed55a01f.tar.gz | |
Use CPU quantized addition kernel for quantized subtraction
Resolves : [COMPMID-5629]
Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com>
Change-Id: I061ea5bdafa3a01e66ff869d158f26a38d19e125
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8835
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/cpu/kernels/add/generic/neon/impl.h')
| -rw-r--r-- | src/cpu/kernels/add/generic/neon/impl.h | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/src/cpu/kernels/add/generic/neon/impl.h b/src/cpu/kernels/add/generic/neon/impl.h index 91f347ff9c..d544ef5728 100644 --- a/src/cpu/kernels/add/generic/neon/impl.h +++ b/src/cpu/kernels/add/generic/neon/impl.h @@ -35,8 +35,19 @@ void add_same_neon(const ITensor *src0, const ITensor *src1, ITensor *dst, const bool add_q8_neon_fixedpoint_possible(const ITensorInfo *src0, const ITensorInfo *src1, const ITensorInfo *dst); +bool sub_q8_neon_fixedpoint_possible(const ITensorInfo *src0, const ITensorInfo *src1, const ITensorInfo *dst); + +bool add_sub_q8_neon_fixedpoint_possible(const ITensorInfo *src0, const ITensorInfo *src1, const ITensorInfo *dst, bool is_addition); + +void add_sub_qasymm8_neon(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window, bool is_addition); + +void add_sub_qasymm8_signed_neon(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window, bool is_addition); + template <typename ScalarType> void add_q8_neon_fixedpoint(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window); + +template <typename ScalarType> +void add_sub_q8_neon_fixedpoint(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window, bool is_addition); } // namespace cpu } // namespace arm_compute #endif // SRC_CORE_NEON_KERNELS_ADD_IMPL_H
\ No newline at end of file |