diff options
| author | Gian Marco <gianmarco.iodice@arm.com> | 2018-02-01 16:57:48 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:45:42 +0000 |
| commit | c799ed85bcf0b18269e65a64f34382073a68bd93 (patch) | |
| tree | bda7b56321638968a24032ff4e685a2a1d58acd7 /src/runtime/CL/CLTuner.cpp | |
| parent | 604afc059c546b3c060a814f15798019cfb7a3de (diff) | |
| download | ComputeLibrary-c799ed85bcf0b18269e65a64f34382073a68bd93.tar.gz | |
COMPMID-895 - Optimizing CLDepthwiseConvolution3x3Kernel
This patch brings the MACs utilisation up to 25 % when both stride_x and stride_y are equal to 1
Performance reported in the following confluence page:
https://confluence.arm.com/display/MLENG/Depthwise+convolution+3x3+FP32+performance%3A+ACL+18.02
Change-Id: Ida1b64be9a88805902a3d90194559b58eb1224a3
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/119068
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/CL/CLTuner.cpp')
| -rw-r--r-- | src/runtime/CL/CLTuner.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/runtime/CL/CLTuner.cpp b/src/runtime/CL/CLTuner.cpp index 917d56756a..cf5b5bce2d 100644 --- a/src/runtime/CL/CLTuner.cpp +++ b/src/runtime/CL/CLTuner.cpp @@ -204,4 +204,4 @@ cl_int Interceptor::operator()(cl_command_queue command_queue, cl_kernel kernel, _tuner.set_cl_kernel_event(tmp); return retval; -}
\ No newline at end of file +} |