Chameleon can now be compiled with cuda 12.x
Compare changes
A GitLab upgrade is scheduled for Monday, May 12, 2025. The service will be unavailable for a few minutes in the morning. We'll keep you posted on the progress of the upgrade on the Mattermost channel: https://mattermost.inria.fr/devel/channels/gitlab. We recommend that you do not work on the platform until an announcement indicates that maintenance is complete.
Hello,
This merge request is to fix the issue #117 (closed)
Cuda 12.x does not allow the inclusion of cublas.h and cublas_v2.h. "Disallow including cublas.h and cublas_v2.h in the same translation unit." (https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html#cublas-release-12-0)
Since cublas.h is deprecated since version 4 of cuda, it must now be the minimum version to use and now cublas_v2.h only is used.
Best regards, Nathan Précigout.