diff options
author | Sheri Zhang <sheri.zhang@arm.com> | 2021-04-14 14:16:04 +0100 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-04-14 14:48:48 +0000 |
commit | e5e61bdffd389fc2ce46d4623a98096c963ac6fb (patch) | |
tree | a016843a745112cd7a573f7fb02387129be2c24f /src/core/CL/kernels/CLL2NormalizeLayerKernel.cpp | |
parent | 035004e65dbffb6534ad4183cf8f95da0544fd28 (diff) | |
download | ComputeLibrary-e5e61bdffd389fc2ce46d4623a98096c963ac6fb.tar.gz |
Fix NeDepthwiseConvolution bad_alloc issue
The memory allocation of the failed tests's tensors are huge, all the virtual memories are used up. And then when assign the output to _reference, a copy constructor is called and allocate more memory and caused the crash.
Delete one of the tensor shape and adjust one.
Resolve: COMPMID-4366
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com>
Change-Id: I91a816384ec358481018a724a7b0cd59730698fc
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5426
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL/kernels/CLL2NormalizeLayerKernel.cpp')
0 files changed, 0 insertions, 0 deletions