The Daily Bulletin delivers news about CISL’s high-performance computing environment, training opportunities, scheduled maintenance, and other events of interest to the user community. To get the Daily Bulletin by email, use this link to subscribe.
Welcome to the new CISL Daily Bulletin. We hope you like the new look and our new approach to serving our HPC user community. The redesigned newsletter is just the first step. It also connects you to the brand new NCAR Advanced Research Computing (ARC) portal. The ARC portal is where you can read the Daily Bulletin online, check the status of our Cheyenne and Casper clusters, and more. Take a l...
Additional nodes in the Casper cluster are now accessible using the PBS Pro workload manager as the migration from Slurm to PBS continues. In addition to the 64 new high-throughput computing (HTC) nodes announced recently, about half of the cluster’s other nodes have been transitioned as of today. PBS jobs can now run on: • 7 CPU-only nodes • 4 GP100 GPU nodes • 2 4xV100 GPU nodes • 3 8xV100 GP...
The CISL Consulting Services Group will present an online tutorial at 9 a.m. MDT on Tuesday, March 30, to help Casper users transition from the Slurm scheduler to PBS Pro. Users who have experience with PBS on Cheyenne are encouraged to attend as well, as there are a few differences between the PBS deployments on each system. Topics will include: • Batch and interactive scheduling with qsub, qs...
You’ll see a fresh new look soon when you check your Daily Bulletin email, which is the first piece of the brand new portal being developed for our HPC user community. The NCAR Advanced Research Computing portal will be rolled out in just a few days as the new home of the Daily Bulletin, a quick way to check on HPC system status, and a link to the NCAR Research Computing help center. That’s jus...
HPSS will be down March 23 from 7am to 4pm for hardware work on two of the libraries. No downtime scheduled for Cheyenne, Casper, GLADE, Campaign Storage, JupyterHub, Quasar, or Stratus.
Casper users will notice some service changes as the cluster is migrated from Slurm to the PBS job scheduler over the next couple of weeks. The first change involves the vncmgr script, which allows users to start VNC sessions on Casper nodes. This script uses Slurm now, but will be migrated to PBS on Monday, March 29. Changes will be minimal, but custom scheduler options must be specified in PB...