[UR][CUDA] Fix device to device copies in...#21277
Draft
kswiecicki wants to merge 1 commit intointel:syclfrom
Draft
[UR][CUDA] Fix device to device copies in...#21277kswiecicki wants to merge 1 commit intointel:syclfrom
kswiecicki wants to merge 1 commit intointel:syclfrom
Conversation
kswiecicki
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
Contributor
Author
|
This is an attempt to fix #19688 issue. It causes a sporadic CI failures, eg. https://github.com/intel/llvm/actions/runs/21866529301/job/63258410809?pr=21251. |
kswiecicki
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
kswiecicki
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
kswiecicki
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
urUSMContextMemcpyExp function. According to the CUDA documentation cuMemcpy doesn't synchronize with the host for device to device copies.
kswiecicki
force-pushed
the
ur-cuda-urUSMContextMemcpyExp-known-failure
branch
from
a8396ce to
f58242e
Compare
kswiecicki
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
pbalcer
reviewed
Feb 16, 2026
| void *pDst, | ||
| const void *pSrc, | ||
| size_t Size) { | ||
| UR_APIEXPORT ur_result_t UR_APICALL urUSMContextMemcpyExp( |
Contributor
There was a problem hiding this comment.
This is not a performance-critical function. Can we just always synchronize at the end? Would make the code simpler.
kswiecicki
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
kswiecicki
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
kswiecicki
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
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
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.
urUSMContextMemcpyExp function. According to the CUDA documentation cuMemcpy doesn't synchronize with the host for device to device copies.