[Codegen][GPU] Add pass for fallback distribution #18726
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
qedawkins
force-pushed
the
fallback_dist
branch
from
fd28be4 to
3fa4811
Compare
qedawkins
requested review from
MaheshRavishankar,
kuhar,
Groverkss and
antiagainst
as code owners
MaheshRavishankar
approved these changes
Oct 13, 2024
If any operation fails to tile or fuse in earlier pipeline stages we need to have a fallback distribution step. This adds a pass for fallback distribution that looks for all tilable ops not inside `scf.forall` regions mapped to threads and greedily tiles + fuses starting from the base of the dispatch.
qedawkins
force-pushed
the
fallback_dist
branch
from
3fa4811 to
dda34d1
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
If any operation fails to tile or fuse in earlier pipeline stages we need to have a fallback distribution step. This adds a pass for fallback distribution that looks for all tilable ops not inside
scf.forallregions mapped to threads and greedily tiles + fuses starting from the base of the dispatch.