Repository navigation
CUDA: Skip IPC tests on ARM - #7189
Merged
Merged
Conversation
These are unsupported on Tegra platforms (such as Jetson). There are some CUDA ARM systems that support IPC, but for now we will count these as not supported by Numba, and skip the tests regardless. In the longer term (when we get to test Numba on CUDA ARM systems that support IPC) this should be re-visited, either by finding a more precise check for skipping the tests than just "Is the CPU architecture ARM?", or by moving the IPC implementation to use `cuMemCreate()` and obtaining shareable memory handles, which will be supported on Tegra. Fixes numba#7178.
Member
Author
|
/azp run |
Contributor
|
Azure Pipelines successfully started running 1 pipeline(s). |
stuartarchibald
approved these changes
Jul 7, 2021
stuartarchibald
left a comment
stuartarchibald
left a comment
Contributor
There was a problem hiding this comment.
Thanks for the patch, looks good on inspection.
stuartarchibald
added
4 - Waiting on CI
Contributor
|
NOTE: Need to find a way to test this manually, the build farm doesn't cover ARM+CUDA. |
Member
|
BFID |
sklam
added
Pending BuildFarm
Member
|
BF passed, but i think we still need a Jetson test(?) |
Member
|
Confirmed on a jetson nano |
sklam
added
5 - Ready to merge
sklam
added a commit
to sklam/numba
that referenced
this pull request
Aug 4, 2021
CUDA: Skip IPC tests on ARM
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
These are unsupported on Tegra platforms (such as Jetson). There are some CUDA ARM systems that support IPC, but for now we will count these as not supported by Numba, and skip the tests regardless.
In the longer term (when we get to test Numba on CUDA ARM systems that support IPC) this should be re-visited, either by finding a more precise check for skipping the tests than just "Is the CPU architecture ARM?", or by moving the IPC implementation to use
cuMemCreate()and obtaining shareable memory handles, which will be supported on Tegra.Fixes #7178.
(cc @jeffhammond)