diff options
author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2021-01-22 09:47:04 +0000 |
---|---|---|
committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2021-06-18 10:33:48 +0000 |
commit | d02d5edfa15ba6c04a9986a8a362a945cb38ac31 (patch) | |
tree | ced4f49691d6c7038e347a8709b315bff59c64cf /src/core/NEON/kernels/arm_gemm/utils.hpp | |
parent | b014c27ba6db9840e4a72519760d51a87a2af7e7 (diff) | |
download | ComputeLibrary-d02d5edfa15ba6c04a9986a8a362a945cb38ac31.tar.gz |
Integrate improved CPU depthwise convolution kernels
* Replace assembly kernels for depthwise convolution with more optimized
ones.
* Add int8 assembly kernels.
* Fix implicit padding on optimized kernels
Resolves: COMPMID-3867, COMPMID-4361
Change-Id: I0b0867e05f61be4f368f62190d55e14d0ab3ebf2
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5622
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/utils.hpp')
-rw-r--r-- | src/core/NEON/kernels/arm_gemm/utils.hpp | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/utils.hpp b/src/core/NEON/kernels/arm_gemm/utils.hpp index 6d483a3b9d..1269ef62a6 100644 --- a/src/core/NEON/kernels/arm_gemm/utils.hpp +++ b/src/core/NEON/kernels/arm_gemm/utils.hpp @@ -175,6 +175,18 @@ inline unsigned long get_vector_length() { #endif } +template <typename T> +inline unsigned long get_vector_length(VLType vl_type) { + switch (vl_type) { +#ifdef __ARM_FEATURE_SVE + case VLType::SVE: + return get_vector_length_sz<sizeof(T)>(); +#endif + default: + return 16 / sizeof(T); + } +} + } // utils namespace } // arm_gemm namespace |