Fix sycl::queue leak in usm_ndarray get_queue()/get_device() - #3042
Open
vlad-perevezentsev wants to merge 8 commits into
Open
Fix sycl::queue leak in usm_ndarray get_queue()/get_device()#3042vlad-perevezentsev wants to merge 8 commits into
get_queue()/get_device()#3042vlad-perevezentsev wants to merge 8 commits into
Conversation
vlad-perevezentsev
requested review from
antonwolfy and
ndgrigorian
as code owners
August 25, 2026 16:37
Contributor
|
View rendered docs @ https://intelpython.github.io/dpnp/pull/3042/index.html |
Contributor
|
Array API standard conformance tests for dpnp=0.21.0dev6=py314ha0e2e8e_25 ran successfully. |
Collaborator
|
coverage: 78.471% (-0.01%) from 78.483% — fix_queue_leak into master |
antonwolfy
reviewed
Aug 26, 2026
| // UsmNDArray_GetQueueRef_ returns an owning copy (DPCTLQueue_Copy, | ||
| // i.e. `new sycl::queue`); wrap it in a unique_ptr to avoid leaking a | ||
| // queue per call. | ||
| DPCTLSyclQueueRef QRef = api.UsmNDArray_GetQueueRef_(raw_ar); |
Contributor
There was a problem hiding this comment.
QRef might be NULL on OOM inside DPCTLQueue_Copy, while below dereferencing of NULL is UB.
It seems legacy and can be done in the follow-up PR.
Contributor
Author
There was a problem hiding this comment.
A good catch
I will be implemented in the follow-up PR
vlad-perevezentsev
force-pushed
the
fix_queue_leak
branch
from
August 27, 2026 11:01
46ff77a to
41be8eb
Compare
antonwolfy
approved these changes
Aug 27, 2026
antonwolfy
left a comment
antonwolfy
left a comment
Contributor
There was a problem hiding this comment.
Thank you @vlad-perevezentsev, LGTM
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
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.
This PR fixes a memory leak in the C++ accessors
usm_ndarray::get_queue()andget_device()indpnp/include/dpnp4pybind11.hppUsmNDArray_GetQueueRef_(dpnp'susm_ndarray.get_queue_ref()) returns an owning copy of the queue (it callsDPCTLQueue_Copyi.e. newsycl::queue)Both accessors dereferenced this pointer and copied the queue out but never freed the heap copy, leaking one
sycl::queueper call. Under queue churn this keepsqueue_implalive and prevents reuse of the associated Level Zero command lists / event pools.The fix adds
UsmNDArray_RemoveQueueRefC-API todpnp_capi(it bindsDPCTLQueue_Delete);get_queue()/get_device()take ownership of the returned copy withstd::unique_ptr<sycl::queue>whose custom deleter frees it viaUsmNDArray_RemoveQueueRef. This keeps allocation and deallocation on dpctl's side of the ABI.dpctl needs no change because its
Memory_GetQueueRefreturns a borrowed ref, whereas dpnp'sUsmNDArray_GetQueueRefis documented to return a copy so it must be deleted.