CISL Daily Bulletin

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.

New tutorial online: Job Scheduling with PBS Pro

November 15, 2021 Updated: November 16, 2021

Video and slides for the “Job Scheduling with PBS Pro" tutorial are now available here in the CISL training library. CISL's Consulting Services Group presented this tutorial on November 9, 2021, to introduce new Cheyenne and Casper users to the PBS Pro job scheduler and to update experienced users on recent upgrades. Topics covered include: • Starting batch and interactive jobs on Cheyenne and ...

No systems downtime for November 15-19

November 15, 2021

None planned for Cheyenne, Casper, Glade, Campaign Storage, Quasar, Stratus, or JupyterHub.

Consulting Services Group attending SC21 November 14-19

November 12, 2021

CISL’s Consulting Services Group staff will be attending SC21 from Sunday through Friday, November 14-19, so response times for some support tickets submitted through the NCAR Research Computing help desk may be longer than usual during the week. We appreciate your patience and understanding during this important event.

Study seeks input from scientists, cyberinfrastructure users

November 9, 2021

Researchers and users of NCAR’s research computing environment are invited to participate in a survey study being conducted by Kerk Kee at Texas Tech University. The study is funded by the National Science Foundation (grants #1939067 & #1453864) to identify the organizational capacity necessary to enable cyberinfrastructure (CI) adoption and spread in the scientific community. The study is seek...

No systems downtime for November 8-12

November 5, 2021

None planned for Cheyenne, Casper, Glade, Campaign Storage, Quasar, Stratus, or JupyterHub.

Where to run small jobs that use only CPUs?

November 5, 2021

CISL recommends running small jobs that use only CPUs on the Casper cluster’s high-throughput computing (HTC) nodes. Casper has 64 HTC nodes specifically for running small batch jobs. It also has: More shared resources than the Cheyenne share queue • A far higher concurrent-use limit for CPU cores than Cheyenne: 468 vs. 36. • More available memory, plus NVMe swap for overflow. Here’s an examp...