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.
Cheyenne and Casper both now have new versions of Intel, GCC, and NVIDIA's HPC SDK as part of our yearly compiler refresh. Intel redesigned its Parallel Studio into Intel OneAPI, which provides the traditional compilers as well as a new suite based on LLVM. Both the new and traditional compilers are made available by loading the intel/2021.2 module; default build flags (e.g., CC, FC) use the tr...
No downtime scheduled for Cheyenne, Casper, Campaign Store, JupyterHub, HPSS, GLADE, Quasar, or Stratus.
The CISL Consulting Services Group will present an online tutorial at 10 a.m. MDT on Monday, May 24, for new users of NCAR’s Cheyenne high-performance computing (HPC) system and storage resources. The 60-minute tutorial – presented by CSG’s Mick Coady – will cover basic usage and typical user workflows and include time for users to ask questions. Participants are assumed to have a basic underst...
All HPC compute and data storage systems hosted at the NCAR-Wyoming Supercomputing Center will be unavailable during part or all of a planned maintenance downtime beginning Monday, July 26, to allow CISL staff and contractors to perform critical updates to the facility’s power infrastructure in preparation for the arrival of the new Derecho system. The Casper cluster, GLADE file systems, Campai...
No downtime scheduled for Cheyenne, Casper, GLADE, JupyterHub, Quasar, Stratus, or HPSS
A. The Casper cluster’s high-throughput computing (HTC) nodes. Why? Take a look at the specs. You’ll see that 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 example sc...