[VectorDistribute] LDS promotion with async DMA#24509
Open
sommerlukas wants to merge 2 commits into
Open
Conversation
Signed-off-by: Lukas Sommer <lukas.sommer@amd.com>
Signed-off-by: Lukas Sommer <lukas.sommer@amd.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Extends the
GPUVectorAllocpass to promote operands to LDS using asynchronous DMA operations (e.g., AMD GPU direct-to-LDS).Based on propagation of the
use_global_load_dmapropagation type during analysis, the pass inserts LDS allocation andasync_dmaoperations, if the necessary requirements are met. Otherwise, promotion falls back to load/store via registers.The inserted
async_dmaoperations are lowered and distributed by the pass landed in #24299 further down in the pipeline.This is part of #23782.
Assisted-by: Claude Code and Codex