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 software releases have been installed on Cheyenne and Casper, including the following compilers and tools, listed with associated modules: • Arm Forge – arm-forge/22.0.2 • GCC – gnu/12.1.0 • NVIDIA HPC SDK – nvhpc/22.05 • Open MPI – openmpi/4.1.4 Standard libraries like netCDF, pnetCDF, FFTW, and PIO have been compiled with the new compiler and MPI versions. For GPU users, the new nvhpc mo...
Update: PBS was returned to service before 9:30 a.m. MDT. The PBS scheduling system for submitting Cheyenne jobs halted at approximately 7 a.m. MDT today. System engineers are troubleshooting the issue. As of 9 a.m. MDT, no estimate is available for when the system might be returned to service. Updates will be sent via our Notifier system when more information is available and when system fun...
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. See Starting ...
None planned for Cheyenne, Casper, GLADE, Campaign Storage, Quasar, Stratus, or JupyterHub.
New versions of the MATLAB (R2022a), R (4.1.2) and Julia (1.7.1) compute kernels are now accessible on NCAR’s JupyterHub service. These match the current defaults found in our Cheyenne and Casper module environments and, in the case of R, the kernel will provide the same library of installed packages. Older versions of these kernels are deprecated and will be removed at a future date (to be ann...
Registration is open for another session in a series of workshops and tutorials on GPU computing. “IDEs, Debugging, and Optimization Tools for GPU Computing” will be on Thursday, June 2, at 10 a.m. MDT. Please use this form to register by 7 a.m. MDT on May 31 if you plan to attend and have not already registered for the series. The series of one-hour sessions is for scientists, software engine...