diff options
author | Teresa Charlin <teresa.charlinreyes@arm.com> | 2024-02-29 14:59:30 +0000 |
---|---|---|
committer | TeresaARM <teresa.charlinreyes@arm.com> | 2024-02-29 15:01:18 +0000 |
commit | 2ab3032ae39d129ef79115cad9084a7074606b59 (patch) | |
tree | 89293008b7a4a7f7331075d918b627367f2207c6 /delegate/opaque/include/armnn_delegate.hpp | |
parent | 282881877522d3e94752dfc0839de9bfa0aa5a81 (diff) | |
download | armnn-2ab3032ae39d129ef79115cad9084a7074606b59.tar.gz |
IVGCVSW-8212 Bug Fix: AddMulAdd optimization missing check on second ADD
* Failures was: MultiplicationQueueDescriptor: Tensors input_0 & input_1 must have the same number of dimensions in order to be broadcasted
* When trying to apply AddMulAdd, Mul dimensions were being collapsed before checking the second ADD.
* If the second ADD determined that fusion cannot happened MUL should have not been collapse.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6dda131c424e1bf7b22fff40c5bef8977f073b24
Diffstat (limited to 'delegate/opaque/include/armnn_delegate.hpp')
0 files changed, 0 insertions, 0 deletions