diff options
| author | Aleksandr Nikolaev <aleksandr.nikolaev@arm.com> | 2020-07-07 19:50:21 +0100 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-07-24 20:40:03 +0000 |
| commit | 6c6619b5ea0688d0e1db4497b4e3bff31ed34677 (patch) | |
| tree | 025857fb526fe64cea3d98fd3640a45a6c709b6b /arm_compute/runtime/CL/functions/CLRNNLayer.h | |
| parent | 09cad7253cc75f67bf428ceef196cfbec7f8c357 (diff) | |
| download | ComputeLibrary-6c6619b5ea0688d0e1db4497b4e3bff31ed34677.tar.gz | |
[ONCPUML-120]: Tweak of the launch heuristics for hybrid_u8u32_dot_16x4 kernel
Hybrid kernel turns to be faster for qasymm8 than quantized_wrapper with interleaved.
Signed-off-by: Aleksandr Nikolaev <aleksandr.nikolaev@arm.com>
Change-Id: I200646aee6cdcabfe125b746c7d87bfa7d06e0fc
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3585
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/functions/CLRNNLayer.h')
0 files changed, 0 insertions, 0 deletions