diff options
| author | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-11-13 17:20:45 +0000 |
|---|---|---|
| committer | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-12-07 09:42:47 +0000 |
| commit | 47370943471c98b5ed4c954b350b925d368a810e (patch) | |
| tree | f5fd7d4c4a51b538874632607887b93d8ece3c07 /src/core/NEON/kernels/NEDepthToSpaceLayerKernel.h | |
| parent | 17e116e90e6b962a09c133c646b6ad7884e94693 (diff) | |
| download | ComputeLibrary-47370943471c98b5ed4c954b350b925d368a810e.tar.gz | |
Optimize CPU depth-to-space
Resolves: COMPMID-6622
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: Ibac276618bdda125dcbb9c851c547f12739b15b4
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10749
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/NEDepthToSpaceLayerKernel.h')
| -rw-r--r-- | src/core/NEON/kernels/NEDepthToSpaceLayerKernel.h | 20 |
1 files changed, 12 insertions, 8 deletions
diff --git a/src/core/NEON/kernels/NEDepthToSpaceLayerKernel.h b/src/core/NEON/kernels/NEDepthToSpaceLayerKernel.h index 7e18dd88b8..ca431ec5fe 100644 --- a/src/core/NEON/kernels/NEDepthToSpaceLayerKernel.h +++ b/src/core/NEON/kernels/NEDepthToSpaceLayerKernel.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2019-2020 Arm Limited. + * Copyright (c) 2019-2020, 2023 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -21,8 +21,8 @@ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ -#ifndef ARM_COMPUTE_NEDEPTHTOSPACELAYERKERNEL_H -#define ARM_COMPUTE_NEDEPTHTOSPACELAYERKERNEL_H +#ifndef ACL_SRC_CORE_NEON_KERNELS_NEDEPTHTOSPACELAYERKERNEL_H +#define ACL_SRC_CORE_NEON_KERNELS_NEDEPTHTOSPACELAYERKERNEL_H #include "src/core/NEON/INEKernel.h" @@ -68,14 +68,18 @@ public: */ static Status validate(const ITensorInfo *input, const ITensorInfo *output, int32_t block_shape); + /** Get the dimension the scheduler should use to split. */ + size_t get_split_dimension() const; + // Inherited methods overridden: void run(const Window &window, const ThreadInfo &info) override; private: - const ITensor *_input; /**< Source tensor */ - ITensor *_output; /**< Destination tensor */ - int32_t _block_shape; /**< Block shape */ - DataLayout _data_layout; /**< Data layout of the operation */ + const ITensor *_input; /**< Source tensor */ + ITensor *_output; /**< Destination tensor */ + int32_t _block_shape; /**< Block shape */ + DataLayout _data_layout; /**< Data layout of the operation */ + size_t _split_dimension; /**< The dimension the scheduler should use to split the workload. */ }; } // namespace arm_compute -#endif /* ARM_COMPUTE_NEDEPTHTOSPACELAYERKERNEL_H */ +#endif // ACL_SRC_CORE_NEON_KERNELS_NEDEPTHTOSPACELAYERKERNEL_H |