Conv Transpose: migration decent speedup #1541
Merged
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Outdated suggestions cannot be applied.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.
Conv transpose 2d kernel for #1422
It was the last of the kernel i had to migrate, so
Fix #1422
Also I spent a bit more time on this kernel because it was notoriously slow.
I sped it up by a factor that scales (not linearly, maybe square root or something) with the kernel size.
Benchmark for conv transpose is added as well.
For instance on my machine, with 8x8 kernel, time decreased from 524ms to 44ms.