diff options
author | Pablo Tello <pablo.tello@arm.com> | 2017-09-21 13:59:14 +0100 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:35:24 +0000 |
commit | c09314a288dc2aa7ef75a09a8ff5dede3f80974a (patch) | |
tree | 91da477f067edc804fc06b03ad4ed84bc4a43e96 /src/core/NEON/kernels/arm32/NEGEMMAArch32Kernel.cpp | |
parent | 3447a598086d8f3a2df2f891c9adeda8ce36a8ab (diff) | |
download | ComputeLibrary-c09314a288dc2aa7ef75a09a8ff5dede3f80974a.tar.gz |
COMPMID-544: NEDirectConvolutionKernel optimization.
The optimization works on tensors with width <= 8 and height <= 8.
The new code is 0.5 faster than the old one as it uses fewer instrunctions to compute the same result.
Change-Id: I408d6c73ebd3d266bdaaf92fcb6bcdd58f239977
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/88642
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm32/NEGEMMAArch32Kernel.cpp')
0 files changed, 0 insertions, 0 deletions