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.

GPU workshop video and slides published

February 7, 2022

Slides and a video recording of the February 3 tutorial “Introduction to Parallel Programming" are now available on this CISL web page, which also describes the topics covered. The series was launched recently to help the NCAR and university research communities prepare to use the extensive GPU-computing capabilities of the new Derecho system. Next in the series is “Why Use GPU Accelerators?” o...

No system downtimes for week of February 7 - 11

February 7, 2022

None planned for Cheyenne, Casper, Glade, Campaign Storage, Quasar, Stratus, or JupyterHub.

Software packages updated on Cheyenne and Casper systems

February 3, 2022

CISL has installed new versions of some commonly used software packages on Cheyenne and Casper. The latest versions of the Intel oneAPI (2022.1) and NVIDIA HPC SDK (22.1) compiler and development suites have been installed on both systems. The Intel oneAPI toolkit includes the traditional and oneAPI compilers, tools like Vtune, and libraries like Intel MPI and MKL. These toolchains will be feat...

GPU tutorial: Why Use GPU Accelerators?

February 3, 2022

The second in a series of CISL workshops and tutorials on GPU computing is “Why Use GPU Accelerators” on Thursday, February 17, at 10 a.m. MST. The series of one-hour sessions is for scientists, software engineers, and students in the Earth system sciences to help them prepare to use the extensive GPU-computing capabilities of the new Derecho system. The training is intended for both new and mo...

Where to run small, CPU-only jobs?

February 1, 2022

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 C...

System downtimes for week of January 31-Feburary 4

January 28, 2022 Updated: January 31, 2022

Downtime is scheduled for Quasar Wednesday, 2/2 from 8:00 am to 12:00 pm MT. None planned for Cheyenne, Casper, Glade, Campaign Storage, Stratus, or JupyterHub.