[LLVMCPU] infer inner-tile alignment hints for mixed scalability - #24857
Open
egebeysel wants to merge 1 commit into
Open
[LLVMCPU] infer inner-tile alignment hints for mixed scalability#24857egebeysel wants to merge 1 commit into
egebeysel wants to merge 1 commit into
Conversation
egebeysel
requested review from
AGindinson,
banach-space and
phemashekar
and removed request for
AGindinson and
hanhanW
August 26, 2026 15:04
An inner-tile alignment hint was only captured when the pack/unpack inner tile itself was scalable, on the assumption that a static inner tile is resolved by static shape inference downstream. That only holds when the loop tile is static too. A static inner tile under a scalable loop tile also needs a hint. Signed-off-by: Ege Beysel <beyselege@gmail.com>
egebeysel
force-pushed
the
egb.infer-inner-tile-alignment-mixed-scalability
branch
from
August 27, 2026 11:39
edbcff1 to
23d0bc4
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
An inner-tile alignment hint was only captured when the pack/unpack inner tile itself was scalable, on the assumption that a static inner tile is resolved by static shape inference downstream. That only holds when the loop tile is static too. A static inner tile under a scalable loop tile also needs a hint.
Assisted-by: Claude Code