Specialize updates to pipeline states' index - help compiler DCE index - #3473
Open
manishucsd wants to merge 1 commit into
Open
Specialize updates to pipeline states' index - help compiler DCE index #3473manishucsd wants to merge 1 commit into
index - help compiler DCE index #3473manishucsd wants to merge 1 commit into
Conversation
manishucsd
changed the title
index - help compiler DCE index index - help compiler DCE index
Collaborator
|
LGTM; We should now be ready to merge this PR. @IonThruster |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request updates the
PipelineStatestruct insm90_pipeline.hpp(used for sm90+ arches) to improve the handling of pipeline stage advancement, especially for single-stage and multi-iteration scenarios. The main changes clarify and optimize how the pipeline state is updated.Pipeline state advancement improvements:
operator++to handle the single-stage (Stages == 1) case by togglingphase_and incrementingcount_, ensuring correct phase handling forStages == 1and maintaining the previous logic forStages > 0.advance<NumIterations>()method to efficiently advance the pipeline state by a full traversal whenNumIterations == Stages, togglingphase_and updatingcount_.In both changes skip updating index and make it easier for the compiler to DCE index for the pipeline guarding single-staged resource or multi-staged resource with index updates equal to Stages