[pallas] size emit_pipeline scratch from reshape-merged block-size products#2769
Open
choijon5 wants to merge 1 commit into
Open
[pallas] size emit_pipeline scratch from reshape-merged block-size products#2769choijon5 wants to merge 1 commit into
choijon5 wants to merge 1 commit into
Conversation
…oducts A reshape([-1, d]) that merges tiled dims gives a leading size that is a sympy product of block-size symbols (u0*u1*u2). _resolve_shape only resolved a single block symbol and fell back to int(s) = the full-extent size hint, over-sizing the loop-carried VMEM scratch for emit_pipeline/fori_loop and crashing at runtime. Resolve compound expressions by substituting each block size. stack-info: PR: #2769, branch: choijon5/stack/93
9d7ae0c to
9a73569
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A reshape([-1, d]) that merges tiled dims gives a leading size that is a sympy
product of block-size symbols (u0u1u2). _resolve_shape only resolved a single
block symbol and fell back to int(s) = the full-extent size hint, over-sizing
the loop-carried VMEM scratch for emit_pipeline/fori_loop and crashing at
runtime. Resolve compound expressions by substituting each block size.