diff options
author | SiCong Li <sicong.li@arm.com> | 2023-05-19 14:23:37 +0100 |
---|---|---|
committer | SiCong Li <sicong.li@arm.com> | 2023-06-19 15:52:40 +0000 |
commit | a8d80583c3b3faa338127ddb9019b6d1085a69ae (patch) | |
tree | 91bcfbf974fdac82b68030ce65e1f9b59fb60877 /src/gpu/cl/ClKernelLibrary.cpp | |
parent | 94abde4f4e98f6f1adb5c46b194527f34a8ea07d (diff) | |
download | ComputeLibrary-a8d80583c3b3faa338127ddb9019b6d1085a69ae.tar.gz |
Implement FP32/FP16 MatMul NT/NT kernel using the MMUL extension
Resolves COMPMID-6194
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: Ie45e2aa9533948b2e5235563cef1d3834494eccf
Signed-off-by: SiCong Li <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9739
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/gpu/cl/ClKernelLibrary.cpp')
-rw-r--r-- | src/gpu/cl/ClKernelLibrary.cpp | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/src/gpu/cl/ClKernelLibrary.cpp b/src/gpu/cl/ClKernelLibrary.cpp index a9080049b5..408f1f7a21 100644 --- a/src/gpu/cl/ClKernelLibrary.cpp +++ b/src/gpu/cl/ClKernelLibrary.cpp @@ -319,6 +319,7 @@ const std::map<std::string, std::string> ClKernelLibrary::_kernel_program_map = { "l2_normalize_x", "common/l2_normalize.cl" }, { "l2_normalize_y", "common/l2_normalize.cl" }, { "l2_normalize_z", "common/l2_normalize.cl" }, + { "mat_mul_native_mmul_nt_nt", "common/mat_mul_mmul.cl" }, { "mat_mul_native_nt_nt", "common/mat_mul.cl" }, { "mat_mul_native_nt_t", "common/mat_mul.cl" }, { "mat_mul_native_t_nt", "common/mat_mul.cl" }, @@ -799,6 +800,10 @@ const std::map<std::string, std::string> ClKernelLibrary::_program_source_map = #include "./cl_kernels/common/mat_mul.clembed" }, { + "common/mat_mul_mmul.cl", +#include "./cl_kernels/common/mat_mul_mmul.clembed" + }, + { "common/mat_mul_quantized.cl", #include "./cl_kernels/common/mat_mul_quantized.clembed" }, |