Skip to content

[UR][L0] Add pool statistics #19360

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: sycl
Choose a base branch
from

Conversation

kswiecicki
Copy link
Contributor

@kswiecicki kswiecicki commented Jul 9, 2025

Support pool query via urUSMPoolGetInfoExp for information about reserved or in-use memory and their peak sizes.

Fixes #17772.

@kswiecicki kswiecicki requested review from a team as code owners July 9, 2025 10:33
@kswiecicki kswiecicki requested a review from uditagarwal97 July 9, 2025 10:33
Copy link
Contributor

@pbalcer pbalcer left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

mostly lgtm

Copy link
Contributor

@uditagarwal97 uditagarwal97 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Changes in sycl/test-e2e/AsyncAlloc/device/memory_pool.cpp LGTM.
Can you add "fixes #19360" to the PR description? so that the issue will be closed when this PR gets merged.

@kswiecicki kswiecicki requested a review from a team as a code owner July 11, 2025 09:29
@kswiecicki kswiecicki force-pushed the l0-async-pool-stats branch from 4cc3cee to 6844164 Compare July 11, 2025 09:45
@kswiecicki kswiecicki removed the request for review from a team July 11, 2025 09:48
Support pool query via urUSMPoolGetInfoExp for information about
reserved or in-use memory and their peak sizes.
in sync allocations, when its unsupported by the pool implementation.
This accommodates cases like the UMF proxy pool, which does not support
this functionality.
@kswiecicki
Copy link
Contributor Author

I've marked the urCommandBufferAppendMemBufferWriteRectTestWithParam.Success testcase as a known failure on L0v2 adapter (there's a JIRA ticket for this behavior: NEO-13299).

[ RUN      ] urCommandBufferAppendMemBufferWriteRectTestWithParam.Success/UR_BACKEND_LEVEL_ZERO__Intel_R__oneAPI_Unified_Runtime_over_Level_Zero_V2__Intel_R__Data_Center_GPU_Max_1100_ID0ID______________________write_3D_with_offsets
Segmentation fault from GPU at 0x80abffc01000, ctx_id: 1 (CCS) type: 0 (NotPresent), level: 0 (PTE), access: 0 (Read), banned: 1, aborting.
Segmentation fault from GPU at 0x80abffc01000, ctx_id: 1 (CCS) type: 0 (NotPresent), level: 0 (PTE), access: 0 (Read), banned: 1, aborting.
Abort was called at 288 line in file:
../../neo/shared/source/os_interface/linux/drm_neo.cpp

The urCommandBufferAppendMemBufferWriteRectTestWithParam.Success
testcase is known to fail sporadically on L0 adapter, the same happens
on L0 v2 adapter.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[L0] Update async alloc support to lateset spec changes
4 participants