projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 4cace32) | patch
IVGCVSW-4148 Report quant multiplier > 1 as unsupported for ACL
authorJames Conroy <james.conroy@arm.com>
Tue, 19 Nov 2019 15:28:58 +0000 (15:28 +0000)
committerJames Conroy <james.conroy@arm.com>
Thu, 21 Nov 2019 16:40:56 +0000 (16:40 +0000)
commitb86a382417017a4b31bee38eb8291233758ea7d1
treef446b2925ffa823c3bd78078e680dca038538549tree | snapshot
parent4cace320a75de835c08a87bb8aa3cfd0cd18ddfdcommit | diff
IVGCVSW-4148 Report quant multiplier > 1 as unsupported for ACL

* This is a temporary measure that needs to be
  removed when quantization multiplier > 1.0f
  support has been added for NEON and CL.
* Layers affected: convolution, depthwise convolution,
  dilated depthwise convolution and transpose
  convolution.

Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Ief1aec2ff0eedf8250f6a8675288e1c343dcfce4
src/backends/cl/ClLayerSupport.cpp diff | blob | history
src/backends/neon/NeonLayerSupport.cpp diff | blob | history
Domain: Machine Learning / ML Framework;