diff options
author | Ramy Elgammal <ramy.elgammal@arm.com> | 2023-05-19 14:23:37 +0100 |
---|---|---|
committer | Ramy Elgammal <ramy.elgammal@arm.com> | 2023-06-23 20:06:45 +0000 |
commit | c952596e70f2fe0073029f053e329a4e930ced8c (patch) | |
tree | 1cf9b1c87c2288d6af436b570802d9cc6e8b30b5 /src/gpu/cl/kernels/ClMatMulNativeMMULKernel.h | |
parent | 47a50ef12f513cfa8fde6673b8a61ed0f2d0fbaa (diff) | |
download | ComputeLibrary-c952596e70f2fe0073029f053e329a4e930ced8c.tar.gz |
Implement FP32/FP16 MatMul NT/T kernel using the MMUL extension
Resolves COMPMID-6195
Signed-off-by: ramy.elgammal@arm.com <ramy.elgammal@arm.com>
Change-Id: I8e85fe73308ed84ebb142d6d6d1562b62dddfaa5
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9819
Reviewed-by: SiCong Li <sicong.li@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/gpu/cl/kernels/ClMatMulNativeMMULKernel.h')
-rw-r--r-- | src/gpu/cl/kernels/ClMatMulNativeMMULKernel.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/src/gpu/cl/kernels/ClMatMulNativeMMULKernel.h b/src/gpu/cl/kernels/ClMatMulNativeMMULKernel.h index 26fe08c466..79f675d03b 100644 --- a/src/gpu/cl/kernels/ClMatMulNativeMMULKernel.h +++ b/src/gpu/cl/kernels/ClMatMulNativeMMULKernel.h @@ -86,6 +86,7 @@ public: private: int _m{ 1 }; int _n{ 1 }; + int _k{ 1 }; }; } // namespace kernels } // namespace opencl |