[AMD] Enable buffer ops for i64 offsets in ConvertToBufferOps#9619
Merged
antiagainst merged 5 commits intotriton-lang:mainfrom Mar 6, 2026
Merged
[AMD] Enable buffer ops for i64 offsets in ConvertToBufferOps#9619antiagainst merged 5 commits intotriton-lang:mainfrom
antiagainst merged 5 commits intotriton-lang:mainfrom
Conversation
Signed-off-by: nithinsubbiah <nithinsubbiah@gmail.com>
nithinsubbiah
requested review from
antiagainst,
ptillet and
zhanglx13
as code owners
yangshuxin
reviewed
Mar 2, 2026
third_party/amd/lib/TritonAMDGPUTransforms/ConvertToBufferOps.cpp
Outdated
Show resolved
Hide resolved
Signed-off-by: nithinsubbiah <nithinsubbiah@gmail.com>
Signed-off-by: nithinsubbiah <nithinsubbiah@gmail.com>
Contributor
|
The latest revision (rev3) LGTM in terms of correctness. Thanks. |
antiagainst
approved these changes
Mar 6, 2026
Contributor
Author
|
oops, thanks for checking |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Previously,
ConvertToBufferOpsunconditionally rejected any load/store with 64-bit offsets. This prevented buffer_load/buffer_store from being used for kernels (e.g. flex attention) that use 64-bit pointer arithmetic. This patch allows 64-bit offsets through when they can be proved safe, truncates them to 32-bit, and uses the faster buffer instructions instead.