[UR] Use templates rather than virtual for stream_queue_t #17858
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
RossBrunton
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
RossBrunton
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
RossBrunton
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
|
@npmiller Can I get your thoughts on this since you added this handler? We want to make it so that the first field of a struct is a pointer to the loader's function table, which doesn't really work with virtual methods. Luckily, I think this solution doesn't add any new overhead. |
npmiller
reviewed
Apr 4, 2025
|
Looks great overall, thank you! |
In a future change, UR is going to restrict handle types from having vtables. This patch changes the queue base type shared by CUDA and HIP to a template.
RossBrunton
force-pushed
the
ross/hipcudanovirtual
branch
from
07f51dc to
f1d6255
Compare
RossBrunton
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
npmiller
approved these changes
Apr 4, 2025
RossBrunton
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
RossBrunton
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
|
@intel/llvm-gatekeepers This should be ready to merge. It looks like there's an issue with the gen12 job, it got stuck in the job setup so I cancelled it. But this patch only touches code used for CUDA and HIP, and these jobs passed, so I think it should be fine to merge. |
|
@intel/llvm-gatekeepers this is ready to merge Looks like the gen12 node was fixed 🎉 |
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Outdated suggestions cannot be applied.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.
In a future change, UR is going to restrict handle types from having
vtables. This patch changes the queue base type shared by CUDA and HIP
to a template where each backend specialises its own backend-specific
queue type.