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/ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel.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/ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel.h')
-rw-r--r-- | src/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel.h | 40 |
1 files changed, 27 insertions, 13 deletions
diff --git a/src/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel.h b/src/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel.h index a77604db7c..1d4696b089 100644 --- a/src/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel.h +++ b/src/gpu/cl/kernels/ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel.h @@ -25,6 +25,7 @@ #define ARM_COMPUTE_CL_GEMMLOWP_MATRIXMULTIPLY_RESHAPED_ONLY_RHS_KERNEL_H #include "arm_compute/core/KernelDescriptors.h" + #include "src/core/common/Macros.h" #include "src/gpu/cl/ClCompileContext.h" #include "src/gpu/cl/IClKernel.h" @@ -70,31 +71,44 @@ public: * @param[in] output_shifts (Optional) 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 *src0, const ITensorInfo *src1, ITensorInfo *dst, const GEMMKernelInfo &gemm_info, - ITensorInfo *vector_sum_col = nullptr, const ITensorInfo *vector_sum_row = nullptr, ITensorInfo *bias = nullptr, - ITensorInfo *output_multipliers = nullptr, ITensorInfo *output_shifts = nullptr); + void configure(const CLCompileContext &compile_context, + const ITensorInfo *src0, + const ITensorInfo *src1, + ITensorInfo *dst, + const GEMMKernelInfo &gemm_info, + ITensorInfo *vector_sum_col = nullptr, + const ITensorInfo *vector_sum_row = nullptr, + ITensorInfo *bias = nullptr, + ITensorInfo *output_multipliers = nullptr, + ITensorInfo *output_shifts = nullptr); /** Static function to check if given info will lead to a valid configuration * * Similar to @ref ClGemmLowpMatrixMultiplyReshapedOnlyRhsKernel::configure() * * @return a status */ - static Status validate(const ITensorInfo *src0, const ITensorInfo *src1, const ITensorInfo *dst, const GEMMKernelInfo &gemm_info, - const ITensorInfo *vector_sum_col = nullptr, const ITensorInfo *vector_sum_row = nullptr, const ITensorInfo *bias = nullptr, - const ITensorInfo *output_multipliers = nullptr, const ITensorInfo *output_shifts = nullptr); + static Status validate(const ITensorInfo *src0, + const ITensorInfo *src1, + const ITensorInfo *dst, + const GEMMKernelInfo &gemm_info, + const ITensorInfo *vector_sum_col = nullptr, + const ITensorInfo *vector_sum_row = nullptr, + const ITensorInfo *bias = nullptr, + const ITensorInfo *output_multipliers = nullptr, + const ITensorInfo *output_shifts = nullptr); // Inherited methods overridden: void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override; private: - bool _slide_matrix_b{ true }; - bool _reinterpret_input_as_3d{ false }; - bool _reinterpret_output_as_3d{ false }; - bool _use_dummy_work_items{ false }; - bool _is_quantized_per_channel{ false }; - bool _fuse_output_stage{ false }; + bool _slide_matrix_b{true}; + bool _reinterpret_input_as_3d{false}; + bool _reinterpret_output_as_3d{false}; + bool _use_dummy_work_items{false}; + bool _is_quantized_per_channel{false}; + bool _fuse_output_stage{false}; }; } // namespace kernels } // namespace opencl } // namespace arm_compute -#endif /* ARM_COMPUTE_CL_GEMMLOWP_MATRIXMULTIPLY_RESHAPED_ONLY_RHS_KERNEL_H */
\ No newline at end of file +#endif /* ARM_COMPUTE_CL_GEMMLOWP_MATRIXMULTIPLY_RESHAPED_ONLY_RHS_KERNEL_H */ |