[CUDA] Implement urKernelSuggestMaxCooperativeGroupCountExp for Cuda #1796
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
Contributor
|
Contributor
Author
@pbalcer Yeah aware, thanks! The root group barrier is currently not supported correctly for cooperative-group kernels in the CUDA backend, so the intel/llvm corresponding PR will be It previously passed because the query was returning a single group and it was calling a work-group level barrier rather than device-wide (cross-work-group). |
GeorgeWeb
force-pushed
the
georgi/ur_kernel_max_active_wgs
branch
3 times, most recently
from
66532d8 to
c612317
Compare
GeorgeWeb
added
the
experimental
This was referenced Jul 5, 2024
GeorgeWeb
force-pushed
the
georgi/ur_kernel_max_active_wgs
branch
from
c612317 to
2359df1
Compare
GeorgeWeb
force-pushed
the
georgi/ur_kernel_max_active_wgs
branch
2 times, most recently
from
ac747c3 to
9dcdc62
Compare
added 2 commits
September 6, 2024 11:11
…ter backend from the sycl runtime This change is required in order to implement per-device semantics for the urKernelSuggestMaxCooperativeGroupCountExp query.
GeorgeWeb
force-pushed
the
georgi/ur_kernel_max_active_wgs
branch
from
9dcdc62 to
45a781f
Compare
Contributor
Author
|
After last rebase, there's a: SYCL :: Regression/device_num.cpp e2e failure that seems unrelated. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.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 commit implements the experimental
urKernelSuggestMaxCooperativeGroupCountExp, for the Cuda adapter, to retrieve the maximum number of cooperative groups that can be launched on the device.Additionally, the changes also cache the result of the
CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNTCuda driver query which is used to calculate the device wide maximum cooperative groups, because the Cuda occupancy query used has per SM (Multiprocessor) semantics.Testing and related changes enabling querying this from SYCL: intel/llvm#14333