diff options
author | Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com> | 2023-09-27 17:46:17 +0100 |
---|---|---|
committer | felixjohnny.thomasmathibalan <felixjohnny.thomasmathibalan@arm.com> | 2023-09-28 12:08:05 +0000 |
commit | afd38f0c617d6f89b2b4532c6c44f116617e2b6f (patch) | |
tree | 03bc7d5a762099989b16a656fa8d397b490ed70e /src/gpu/cl/kernels/ClGemmLowpOffsetContributionOutputStageKernel.h | |
parent | bdcb4c148ee2fdeaaddf4cf1e57bbb0de02bb894 (diff) | |
download | ComputeLibrary-afd38f0c617d6f89b2b4532c6c44f116617e2b6f.tar.gz |
Apply clang-format on repository
Code is formatted as per a revised clang format configuration
file(not part of this delivery). Version 14.0.6 is used.
Exclusion List:
- files with .cl extension
- files that are not strictly C/C++ (e.g. Android.bp, Sconscript ...)
And the following directories
- compute_kernel_writer/validation/
- tests/
- include/
- src/core/NEON/kernels/convolution/
- src/core/NEON/kernels/arm_gemm/
- src/core/NEON/kernels/arm_conv/
- data/
There will be a follow up for formatting of .cl files and the
files under tests/ and compute_kernel_writer/validation/.
Signed-off-by: Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>
Change-Id: Ib7eb1fcf4e7537b9feaefcfc15098a804a3fde0a
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10391
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Diffstat (limited to 'src/gpu/cl/kernels/ClGemmLowpOffsetContributionOutputStageKernel.h')
-rw-r--r-- | src/gpu/cl/kernels/ClGemmLowpOffsetContributionOutputStageKernel.h | 29 |
1 files changed, 23 insertions, 6 deletions
diff --git a/src/gpu/cl/kernels/ClGemmLowpOffsetContributionOutputStageKernel.h b/src/gpu/cl/kernels/ClGemmLowpOffsetContributionOutputStageKernel.h index cee04473c4..97ee9bc97f 100644 --- a/src/gpu/cl/kernels/ClGemmLowpOffsetContributionOutputStageKernel.h +++ b/src/gpu/cl/kernels/ClGemmLowpOffsetContributionOutputStageKernel.h @@ -66,23 +66,40 @@ public: * @param[in] output_shifts Output shifts tensor. In case of per-channel quantization, the number of multipliers must be equal to the number of filters (OFM). * Supported data types: S32 */ - void configure(const CLCompileContext &compile_context, const ITensorInfo *mm_result, const ITensorInfo *vector_sum_col, const ITensorInfo *vector_sum_row, const ITensorInfo *bias, ITensorInfo *dst, - int32_t k, int32_t a_offset, int32_t b_offset, const GEMMLowpOutputStageInfo &output_stage, - const ITensorInfo *output_multipliers, const ITensorInfo *output_shifts); + void configure(const CLCompileContext &compile_context, + const ITensorInfo *mm_result, + const ITensorInfo *vector_sum_col, + const ITensorInfo *vector_sum_row, + const ITensorInfo *bias, + ITensorInfo *dst, + int32_t k, + int32_t a_offset, + int32_t b_offset, + const GEMMLowpOutputStageInfo &output_stage, + const ITensorInfo *output_multipliers, + const ITensorInfo *output_shifts); /** Static function to check if given info will lead to a valid configuration * * Similar to @ref ClGemmLowpOffsetContributionOutputStageKernel::configure() * * @return a status */ - static Status validate(const ITensorInfo *mm_result, const ITensorInfo *vector_sum_col, const ITensorInfo *vector_sum_row, const ITensorInfo *bias, const ITensorInfo *dst, int32_t a_offset, - int32_t b_offset, const GEMMLowpOutputStageInfo &output_stage, const ITensorInfo *output_multipliers, const ITensorInfo *output_shifts); + static Status validate(const ITensorInfo *mm_result, + const ITensorInfo *vector_sum_col, + const ITensorInfo *vector_sum_row, + const ITensorInfo *bias, + const ITensorInfo *dst, + int32_t a_offset, + int32_t b_offset, + const GEMMLowpOutputStageInfo &output_stage, + const ITensorInfo *output_multipliers, + const ITensorInfo *output_shifts); // Inherited methods overridden: void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override; private: - bool _is_quantized_per_channel{ false }; + bool _is_quantized_per_channel{false}; }; } // namespace kernels } // namespace opencl |