Spatial Sharing test update for low variance #8494
Open
Conversation
This file contains 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
Signed-off-by: Akshay Tondak <Akshay.Tondak@amd.com>
aktondak
requested review from
rozumx,
chvamshi-xilinx and
AShivangi
as code owners
|
Can one of the admins verify this patch? |
Signed-off-by: Akshay Tondak <Akshay.Tondak@amd.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Problem solved by the commit
The variance seen in the overhead for spatial-sharing-overhead test was high. This Change solves that.
There is some additional code cleanup which moves 2 APIs out of the TestRunner class for free usage within other code.
The file TestHelper has also been renamed appropriately to be used as a placeholder for future xrt-smi validate APIs.
Bug / issue (if any) fixed, which PR introduced the bug, how it was discovered
https://jira.xilinx.com/browse/CR-1215567
How problem was solved, alternative solutions (if any) and why they were rejected
The problem was solved by running the df-bw DPU instruction instead of the no-op kernel being run previously.
We are now running 8 kernels simultaneously for 10,000 iterations
The overhead now seen in 10 subsequent runs is seen between 900ms - 1100ms (~10% variance).
Risks (if any) associated the changes in the commit
None
What has been tested and how, request additional testing if necessary
Tested on Kracken board. Needs further testing from DSV
Documentation impact (if any)
https://confluence.amd.com/display/AIE/User+Guide%3A+xrt-smi+on+Ryzen+AI will be updated once pulled