Bad node on OneAPI devcloud

[Elliott]

Hi,

I'm seeing what I suspect to be a bad node on Intel OneAPI devcloud. The bad node is s001-n166. Whenever I run my program on this node, the program freezes and the whole node locks down. I cannot kill the job with Ctrl-C or stop it with Ctrl-Z. I have to run qdel from another SSH session to kill the job.

This happens only on node s001-n166. On other nodes (e.g., s001-n201), the program runs fine.

Just thought you might want to know.

[Hemanth_K_Intel]

Hi,

Thanks for letting us know. We'll check, rectify it and let you know of the cause/fix

Best

Hemanth

DevCloud Team

[ArunJ_Intel]

HI Elliot,

We have updated and rebooted the node. Now the GPU code runs fine on the node.

Could you verify from your end and let us know if you are able to run your code or if there are any issues.

Thanks

Arun

[ArunJ_Intel]

Hi Elliot,

Hope you are able to use the node without any issues. Please let us know if the issue does persist.

Arun

[ArunJ_Intel]

Hi Elliot,

As we have not heard back from you for sometime we are assuming your issue is resolved we wont be monitoring this issue further. Please feel free to raise a new thread for further issues.

Thanks

Arun Jose