[DevTSAN] Move AllocInfo into DeviceInfo to support indirect access #19634
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
AllanZyne
reviewed
Jul 30, 2025
zhaomaosu
changed the title
zhaomaosu
had a problem deploying
to
WindowsCILock
GitHub Actions
Failure
AllanZyne
approved these changes
Jul 31, 2025
zhaomaosu
had a problem deploying
to
WindowsCILock
GitHub Actions
Failure
|
Hi @intel/unified-runtime-reviewers, could you please help review this PR? Thanks. |
pbalcer
approved these changes
Aug 4, 2025
|
Hi @intel/llvm-gatekeepers, this PR is ready to be merge. Thanks. |
|
kindly ping @intel/llvm-gatekeepers |
|
@sarnex The post commit testing here failed due to apparently missing Battlemage GPUs. Would you please take a look at those runners? |
|
Taking a look now, thanks for the report |
AlexeySachkov
pushed a commit
to AlexeySachkov/llvm
that referenced
this pull request
Aug 25, 2025
…ntel#19634) If we maintain AllocInfo in ContextInfo, this will cause the pointer which is allocated by another context can't be poisoned.
AlexeySachkov
pushed a commit
to AlexeySachkov/llvm
that referenced
this pull request
Aug 25, 2025
…ntel#19634) If we maintain AllocInfo in ContextInfo, this will cause the pointer which is allocated by another context can't be poisoned.
AlexeySachkov
added a commit
that referenced
this pull request
Sep 1, 2025
This is a combined cherry-pick of: --- [DevSAN] Cache internal queue to avoid repeated create/destroy (#19540) Patch-By: Maosu Zhao <[email protected]> --- [DevTSAN] Move AllocInfo into DeviceInfo to support indirect access (#19634) If we maintain AllocInfo in ContextInfo, this will cause the pointer which is allocated by another context can't be poisoned. Patch-By: Maosu Zhao <[email protected]> --- [DevMSAN] Correctly apply stride for dest/src pointer when do async copy (#19766) Currently, we always define stride in elements when writing to destination pointer. However, according to spirv spec, the stride can only be applied to global ptr. Patch-By: Maosu Zhao <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
If we maintain AllocInfo in ContextInfo, this will cause the pointer which is allocated by another context can't be poisoned.