[MLIR][NVVM] Add mbarrier.try_wait Op #170285
Merged
+258
−0
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
This patch adds an Op for mbarrier.try_wait operation which lowers to the corresponding intrinsics. This Op has support for optional time-limit, state-or-phase as well as relaxed memory semantics, completing the features on this Op up to Blackwell. Unlike the existing `nvvm.mbarrier.try_wait.parity` Op, this Op does not provide a _blocking_ implementation. We intend to add a looping around this at NVGPU in a subsequent PR(and deprecate the inline-asm based Op here). lit tests are added to verify the lowering to the intrinsics. Signed-off-by: Durgadoss R <durgadossr@nvidia.com>
grypp
approved these changes
Dec 3, 2025
kcloudy0717
pushed a commit
to kcloudy0717/llvm-project
that referenced
this pull request
Dec 4, 2025
This patch adds an Op for mbarrier.try_wait operation which lowers to the corresponding intrinsics. This Op has support for an optional time-limit, state-or-phase as well as relaxed memory semantics, completing the features on this Op up to Blackwell. Unlike the existing `nvvm.mbarrier.try_wait.parity` Op, this Op does not provide a _blocking_ implementation. We intend to add looping around this at NVGPU in a subsequent PR (and deprecate the inline-asm based Op here). lit tests are added to verify the lowering to the intrinsics. Signed-off-by: Durgadoss R <durgadossr@nvidia.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
This patch adds an Op for mbarrier.try_wait operation which lowers
to the corresponding intrinsics. This Op has support for an optional
time-limit, state-or-phase as well as relaxed memory semantics,
completing the features on this Op up to Blackwell.
Unlike the existing
nvvm.mbarrier.try_wait.parityOp, this Opdoes not provide a blocking implementation. We intend to
add looping around this at NVGPU in a subsequent PR
(and deprecate the inline-asm based Op here).
lit tests are added to verify the lowering to the intrinsics.