Skip to content
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

Fixed bug with the new SpGEMM fallback #177

Merged
merged 1 commit into from
May 23, 2022

Conversation

mattmartineau
Copy link
Collaborator

The singleton cuSPARSE handle was incorrectly destroyed which leads to handle errors in subsequent cuSPARSE calls if the fallback is encountered.

@mattmartineau mattmartineau requested a review from marsaev May 23, 2022 07:01
@mattmartineau mattmartineau self-assigned this May 23, 2022
@piyueh
Copy link

piyueh commented May 23, 2022

Is this related to #148?

@mattmartineau
Copy link
Collaborator Author

I believe so - hopefully it should fix that issue.

@mattmartineau mattmartineau linked an issue May 23, 2022 that may be closed by this pull request
@marsaev
Copy link
Collaborator

marsaev commented May 23, 2022

Good find! LGTM, feel free to merge.

@mattmartineau
Copy link
Collaborator Author

Thanks

@mattmartineau mattmartineau merged commit 5db99a0 into NVIDIA:main May 23, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

cusparseSpMV_bufferSize() bad initialization or already destroyed
3 participants