[TOPI x86] Adding unroll_kw config option for depthwise conv2d. #5197
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Outdated suggestions cannot be applied.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.
@yzhliu @kevinthesun
unroll_kw is used for normal conv2d schedules as well. In the case of depthwise conv2d, the input pixels are actually vectorized (not broadcasted as in the case with normal conv2d). This potentially can create opportunities for reusing the data vector across two output pixels. Therefore, adding unroll_kw config option.
In any case, this does not bring perf degradation. It makes search space larger.
Concern - This might require a minor change in Tophub configuration. I can make that change once this PR is merged (or just before).