diff options
| author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2020-11-15 16:06:10 +0000 |
|---|---|---|
| committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2020-11-17 10:39:32 +0000 |
| commit | 229757be70e7884b1a64972c2bdf9919075401a2 (patch) | |
| tree | f71d3b029d77db7328236ed28cd0541212fc2ed2 /src/runtime/CL/gemm/CLGEMMKernelSelectionBifrost.h | |
| parent | 6c62d7ae1e989ac04b139b45ee61a8a4650fc4fd (diff) | |
| download | ComputeLibrary-229757be70e7884b1a64972c2bdf9919075401a2.tar.gz | |
COMPMID-3975: Update CLGEMM heuristic for Mali-G52 F16
- Update the GEMM heuristic for Mali-G52
- Fix the GEMV heuristic on Mali-G76
Change-Id: I895153d02d09e73c51ecf158e2ae43f81f6d7b05
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4425
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/CL/gemm/CLGEMMKernelSelectionBifrost.h')
| -rw-r--r-- | src/runtime/CL/gemm/CLGEMMKernelSelectionBifrost.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/src/runtime/CL/gemm/CLGEMMKernelSelectionBifrost.h b/src/runtime/CL/gemm/CLGEMMKernelSelectionBifrost.h index fbafc531f5..6831a12aec 100644 --- a/src/runtime/CL/gemm/CLGEMMKernelSelectionBifrost.h +++ b/src/runtime/CL/gemm/CLGEMMKernelSelectionBifrost.h @@ -47,6 +47,7 @@ private: CLGEMMKernelType g52_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b, bool is_rhs_constant); CLGEMMKernelType g76_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b, bool is_rhs_constant); CLGEMMKernelType g76_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b, bool is_rhs_constant); + CLGEMMKernelType g52_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b, bool is_rhs_constant); CLGEMMKernelType g71_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b, bool is_rhs_constant); CLGEMMKernelType default_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b, bool is_rhs_constant); CLGEMMKernelType default_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b, bool is_rhs_constant); |