UPDATE: The original announcement had this work scheduled for Thursday, October 22. The downtime has been moved to Friday, October 30 and the text below has been updated to reflect this change.

In order to integrate new hardware into the Cabeus supercomputer, the Grace Hopper nodes will be unavailable Friday, October 30 from 8:00 a.m. to 8:00 p.m. (Pacific). Jobs running on the Grace Hopper nodes will be drained prior to the beginning of the dedicated time, and submitted jobs that are not scheduled to complete before the downtime will not run until after the system returns to users.

The Cabeus Milan/A100 nodes will not be impacted by this work.

See Running Jobs Before Dedicated Time in the Knowledge Base to learn how to manage your jobs to run before dedicated time.

If you have any questions or need assistance please contact the Control Room at (800) 331-8737, (650) 604-4444, or support@nas.nasa.gov.