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.
A two-hour XSEDE tutorial at 12 p.m. MDT on Wednesday, November 3, will introduce participants to the development platform for NVIDIA A100 and A40 GPUs. Twenty percent of the computing power for Derecho, NCAR’s next supercomputer, will come from NVIDIA A100s. The NVIDIA HPC software development toolkit (SDK) is a suite of tools for programming NVIDIA GPUs for high-performance computing, artifi...
None planned for Cheyenne, Casper, Glade, Campaign Storage, Quasar, Stratus, or JupyterHub.
The previously announced deployment of peer-scheduling capability between Cheyenne and Casper has been delayed. Changes made Wednesday morning to PBS were rolled back after CISL engineers discovered that unforeseen issues related to Cheyenne jobs’ environments were the source of some job failures. A potential solution to the problem is being thoroughly evaluated and tested, and expected to be d...
CISL has implemented its new peer-scheduling capability so users can now submit PBS jobs from Cheyenne to Casper and from Casper to Cheyenne. Users can also now craft job-dependency rules between jobs on both systems. Review this new documentation to learn how to use the new capabilities. Also effective October 20, as announced last month, the Cheyenne system’s default behavior has been modifie...
None planned for Cheyenne, Casper, Glade, HPSS, Campaign Storage, Quasar, Stratus, or JupyterHub.
Recent upgrades to PBS Pro are bringing some changes and new capabilities to the scheduler, most prominently the addition of peer scheduling (coming October 20) between Cheyenne and Casper. Brian Vanderwende of CISL's Consulting Services Group will present a tutorial at 11 a.m. MST on Tuesday, November 9, to introduce new users to the scheduler and to update experienced users on these recent up...