Add bounds checking to implicit GEMM to allow arbitrary input shapes #2354
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Pull Request Template
Checklist
run-checks all
script has been executed.Changes
Implicit GEMM was previously only padded on the input channel, now all 3 dimensions get implicitly padded to allow arbitrary sized inputs. The performance of the padded convolutions is slightly slower than the next matching size, but still faster than other convolution strategies.
Testing
All tests pass with implicit GEMM except the ones with groups.