std_detect: Add sme-b16b16 as an explicit aarch64 target feature #1635
Conversation
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
Amanieu
reviewed
Sep 14, 2024
| enable_feature(Feature::sme2p1, self.sme2p1 && sme2); | ||
| enable_feature( | ||
| Feature::sme_b16b16, | ||
| sme2 && self.bf16 && self.sveb16b16 && self.smeb16b16, |
There was a problem hiding this comment.
Is it necessary to check for sveb16b16 here as well? I would expect this to be available for chips that only support SME but not SVE like the latest apple ones.
There was a problem hiding this comment.
Yeah we should check because there's a dependency in the architecture and if you try enabling this in LLVM it'll also enable sve-b16b16.
The check is just being overly cautious because having this one implies having the other one on the architecture level anyway so that part of the check should never fail.
Slightly counterintuitive due to the naming but this is still fine for SME-only devices because sve-b16b16 does not actually depend on sve, in that case it would just only give you the SME instructions.
LLVM 20 split out what used to be called b16b16 and correspond to aarch64 FEAT_SVE_B16B16 into sve-b16b16 and sme-b16b16. Add sme-b16b16 as an explicit feature and update the detection accordingly.
Amanieu
force-pushed
the
detect-b16b16
branch
from
70446a6 to
8e2ac3a
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
LLVM 20 split out what used to be called b16b16 and correspond to aarch64 FEAT_SVE_B16B16 into sve-b16b16 and sme-b16b16.
Add sme-b16b16 as an explicit feature and update the detection accordingly.