Repository navigation
Conversation
Treat each block as one cluster when a known earlier target is selected. Bind a device hint only after this fallback is used, so later feature selection cannot silently change its semantics. Keep raw intrinsic and cluster operation target requirements intact. Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cluster hierarchy queries can describe a one-block cluster on targets before SM90. This adds that fallback for the twelve compatibility query leaves, preserving the architecture checks on raw intrinsics and actual cluster operations.
An explicit target takes precedence. When fallback consumes a device hint, that hint pins the artifact target: SM80 queries combined with an SM90-only operation now fail compilation instead of producing an artifact for a different device. An unused hint remains advisory.
Validation: 1,182 importer tests, an actual MIR-to-NVVM-IR regression with exact axis/result mapping, strict clippy and rustdoc. Compile probes cover SM80 CUBIN generation, libdevice target selection, raw intrinsic floors, and rejected hardware-cluster launches. The coordinated Rust hierarchy fixture compiles for SM80 without hardware clusters and passes 293,120 values plus memcheck on SM120. SM80 execution was not tested.