diff options
| author | ramelg01 <ramy.elgammal@arm.com> | 2021-11-11 10:05:00 +0000 |
|---|---|---|
| committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2021-11-20 17:38:07 +0000 |
| commit | 9cca592c13f1e688a35698641069bcd37a525f0c (patch) | |
| tree | 8f69b654c5f543d918ec5d61140af30bbadbd390 /src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsKernel.h | |
| parent | e330fb41d85d7058f74902ce1d47b2dc00b10a52 (diff) | |
| download | ComputeLibrary-9cca592c13f1e688a35698641069bcd37a525f0c.tar.gz | |
Improve start-up timer for GeMM (floating-point):
- Pass M,N,K at runtime as kernel parameters
- Add a guard macro to compile only kernel of interest
- Move reshpaing kernels to gemm_utils.cl
- Remove the fallback reshaping kernel with Y-Padding support
Resolves: COMPMID-4888
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Change-Id: Ida3851326f0b77e410633271de9ecca106e37931
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6662
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsKernel.h')
| -rw-r--r-- | src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsKernel.h | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsKernel.h b/src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsKernel.h index a8f0c4c3a0..ec5878d5cc 100644 --- a/src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsKernel.h +++ b/src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsKernel.h @@ -97,6 +97,9 @@ private: bool _add_bias{ false }; bool _export_to_cl_image{ false }; bool _has_pad_y{ false }; + signed int _m{ 1 }; + signed int _n{ 1 }; + signed int _k{ 1 }; unsigned int _num_post_op_args{ 0 }; // (EXPERIMENTAL_POST_OPS) total number of post op arguments }; } // namespace kernels |