diff options
author | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-12-18 15:09:00 +0000 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-12-20 11:09:13 +0000 |
commit | 64e738f32187e8a4ea2624d15b48ed79b34cc824 (patch) | |
tree | c9ecbf8f7f20ff0cb919a1cea95726a903d81a03 /arm_compute/runtime/ITensorAllocator.h | |
parent | c3a74200a66ea5fb718b8406bed2043bc097930e (diff) | |
download | ComputeLibrary-64e738f32187e8a4ea2624d15b48ed79b34cc824.tar.gz |
COMPMID-2819: Restrict cases where optimized NEPadLayer runs.
Restricts the optimized path for NEPadLayer on int8 inputs to run only
when both input and output do not have any virtual padding, to honor all
the kernels assumptions.
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I4debf872b5534d8dcec6d34e1c6114e58ce9dbb2
Reviewed-on: https://review.mlplatform.org/c/2494
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Diffstat (limited to 'arm_compute/runtime/ITensorAllocator.h')
0 files changed, 0 insertions, 0 deletions