You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When running tau version 2.31 compiled with gcc 8.5.0 running on Rocky 8 the tau_cupti_avail command lists the expected counter when run on a compute node with a V100 GPU. On the same cluster with an identical compute node setup but with an A100 card the list of available metrics is empty.
Any advice you could provide would be much appreciated.
All the best,
Matthew
The text was updated successfully, but these errors were encountered:
On Nov 30, 2022, at 6:38 PM, G. Matthew Fricke ***@***.***> wrote:
Hello,
When running tau version 2.31 compiled with gcc 8.5.0 running on Rocky 8 the tau_cupti_avail command lists the expected counter when run on a compute node with a V100 GPU. On the same cluster with an identical compute node setup but with an A100 card the list of available metrics is empty.
Any advice you could provide would be much appreciated.
All the best,
Matthew
—
Reply to this email directly, view it on GitHub <#8>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAUHIONHYW5KMRD6YUXLNLLWLAFRNANCNFSM6AAAAAASQI5TF4>.
You are receiving this because you are subscribed to this thread.
Hello,
When running tau version 2.31 compiled with gcc 8.5.0 running on Rocky 8 the tau_cupti_avail command lists the expected counter when run on a compute node with a V100 GPU. On the same cluster with an identical compute node setup but with an A100 card the list of available metrics is empty.
Any advice you could provide would be much appreciated.
All the best,
Matthew
The text was updated successfully, but these errors were encountered: