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.
All Cheyenne and Casper system users are invited to the NCAR HPC User Group (NHUG) monthly meeting from 9 to 10 a.m. MST on Tuesday, February 7. CISL staff will discuss the status of the Derecho system and upcoming changes to CPU and GPU allocation accounting, and also highlight some upcoming events. To contribute to the agenda or submit questions for the next meeting, please visit Slido, where...
New documentation about using the Derecho system and other NCAR high-performance computing resources is now available on the Advanced Research Computing portal in Getting started with NCAR systems. The documentation includes information on compiling code, submitting jobs, and performing other common tasks on all NCAR resources unless otherwise noted. Additional Derecho-specific documentation is...
The UCAR Software Engineering Assembly has extended the deadline for accepting abstract submissions for the 2023 Improving Scientific Software Conference. The new deadline for submitting your abstract is Tuesday, February 14. The conference, which is scheduled for April 17 to 21, will focus on the theme of the scientific software lifecycle, from designing and building the software itself to man...
All the hardware for the new Derecho system is on site at the NCAR-Wyoming Supercomputing Center and HPE engineers are installing the base system software needed to boot the system. This installation is going slower than expected, but they are making progress. The next phase of the project will be the hardware check-out when HPE runs software on the system to determine if any hardware has faile...
None planned for Cheyenne, Casper, GLADE, Campaign Storage, Quasar, Stratus, or JupyterHub.
CISL will begin accounting for the use of GPU resources on the Casper cluster and is also revising the charging algorithm for jobs on shared CPU nodes on both Casper and Cheyenne beginning Monday, February 13. Projects that have used Casper GPU resources in the past year have all now received an initial GPU-hours allocation based on that previous use. Charges will be based on a job’s walltime. ...