Fix convolution with bias segmentation fault issue

Indirect hybrid kernels read the full width of the bias. So we need to detect the case where we are writing a partial block and pad the bias for that block.

Resolves: COMPMID-4321

Signed-off-by: Sheri Zhang <sheri.zhang@arm.com>
Change-Id: Ib8d8637724e34d1eae6cc22223df8d81a6d0ded6
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5380
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>

0 files changed, 0 insertions, 0 deletions