Skip to content

wait() failing for the default stream 0 #3873

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 3 commits into
base: develop
Choose a base branch
from

Conversation

lakhinderwalia
Copy link
Contributor

This PR fixes these two issues when using the default stream on the GPU: i.e. via MIGRAPHX_ENABLE_NULL_STREAM=1:

  1. Trying to verify on a model, (resnet50v2 here) gives this exception: context.hpp:365: get_elapsed_ms: Failed hipEventElapsedTime: device not ready

  2. Trying to run perf on a model with the default stream gives more optimistic results, as the gpu-sync-up is essentially bypassed, incorrectly.

@lakhinderwalia lakhinderwalia requested a review from causten as a code owner March 7, 2025 19:24
@lakhinderwalia lakhinderwalia self-assigned this Mar 7, 2025
@amd-jmacaran
Copy link
Contributor

/AzurePipelines run

Copy link

Azure Pipelines successfully started running 1 pipeline(s).

Copy link

codecov bot commented Mar 8, 2025

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.40%. Comparing base (b235f15) to head (57e384a).

Additional details and impacted files
@@           Coverage Diff            @@
##           develop    #3873   +/-   ##
========================================
  Coverage    92.40%   92.40%           
========================================
  Files          520      520           
  Lines        22485    22485           
========================================
  Hits         20778    20778           
  Misses        1707     1707           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Copy link
Collaborator

@CharlieL7 CharlieL7 left a comment

Choose a reason for hiding this comment

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

LGTM

Copy link
Collaborator

@pfultz2 pfultz2 left a comment

Choose a reason for hiding this comment

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

Since this relies on undocumented behavior, a unit test needs to be added.

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.

5 participants