diff options
author | Ethan Doe <yidoe@amazon.com> | 2023-03-01 23:19:26 +0000 |
---|---|---|
committer | Pablo Marquez Tello <pablo.tello@arm.com> | 2023-03-03 08:22:35 +0000 |
commit | 1fe48cafde21a316011fff32a5b0f98a74fbe2b9 (patch) | |
tree | 57abe64846bd1cea18329c5a56dab2bc210df7d5 /arm_compute/runtime/CL/functions/CLConvolutionLayer.h | |
parent | e2e6d745c940cdfd8c3340fd1227dbef1badfb3c (diff) | |
download | ComputeLibrary-1fe48cafde21a316011fff32a5b0f98a74fbe2b9.tar.gz |
NEGEMMLowpMatrixMultiplyCore should be configured for optimized int8 kernel.
Currently the validation routine incorrectly prevents optimized INT8 Gemm kernel from being used if the input is QASYMM8 and output type is S32.
This change allows QASYMM8 input and S32 output types to leverage optimized kernel.
Signed-off-by: Ethan Doe <yidoe@amazon.com>
Change-Id: I65b060f522795db07d6d4df86fb7c6ddd1c626d4
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9250
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/functions/CLConvolutionLayer.h')
0 files changed, 0 insertions, 0 deletions