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.

Reanalysis combines 80 hindcasts with observations to improve forecast reliability

March 9, 2021

A team of NCAR scientists has released a reanalysis that combines an ensemble of 80 different hindcasts (forecasts made for a time in the past) with real-world observations to better understand phenomena like hurricanes and improve the reliability of forecasts. The resulting reanalysis provides snapshots of the atmosphere four times a day from 2011 through 2019, and a detailed picture of atmosp...

Reminder: HPC systems maintenance downtime March 9-10

March 8, 2021

NCAR’s HPC resources will be unavailable to users March 9-10 to allow CISL staff and HPE engineers to perform compute and networking infrastructure updates and maintenance. Significant updates, as announced previously, include the addition of high-throughput computing (HTC) nodes to the Casper cluster. Related documentation will be available by Thursday. The Cheyenne and Casper clusters, GLADE ...

Systems downtime for week of March 8 - 12

March 8, 2021

Cheyenne, Casper, GLADE, Campaign Storage, JupyterHub, HPSS, Stratus, and Quasar will be down from 06:00 MST on March 9th until 21:00 MST on March 10th in support of network upgrades.

Compiling code update: Transition from PGI to NVIDIA

February 4, 2021 Updated: March 4, 2021

CISL documentation for compiling code to run on the Cheyenne and Casper systems has been updated because of changes to the PGI compiler. It has become the NVIDIA HPC (nvhpc) compiler and all future versions will be released as such. The updated Compiling code documentation advises PGI users to transition to the nvhpc compiler, which has no license limitations, although the PGI compiler remains ...

New documentation for using MATLAB in parallel

February 1, 2021 Updated: March 4, 2021

New CISL documentation is now available to help users leverage MATLAB’s Parallel Computing Toolbox and Parallel Server to speed up their computations on the Cheyenne system. The toolbox enables single-node parallelism, while the server enables parallelism across nodes. Some setup is required to correctly and optimally use these capabilities on Cheyenne. The documentation shows how to configur...

Deadline March 22 for university large-scale allocation requests

February 3, 2021 Updated: March 4, 2021

CISL is now accepting large-scale allocation requests from university-based researchers for the 5.34-petaflops Cheyenne supercomputer and the Casper data analysis and visualization cluster. Those requests are due March 22. Cheyenne will continue in operation through mid-2022. Allocations for NCAR’s recently announced next-generation supercomputer that will become operational early in 2022 will ...