Daily Bulletin Archive

May 26, 2020

MathWorks will present a free program from noon to 1 p.m. MDT on Thursday, May 28, to introduce MATLAB capabilities for exploring parasitology images and identifying and extracting information from images and video. Topics will include feature detection, extraction, and matching, and using built-in apps and visualization tools for deep learning that are not available in open-source frameworks. Using collections of features, the presentation will show how to train a model to recognize objects with user-specified or automatically determined features.

See the MathWorks site for details and registration.

May 21, 2020

Except for the ongoing teamwork, very little remains as it was before mid-March for NCAR staff who keep the mission-critical computing and data-storage systems running at the NCAR-Wyoming Supercomputing Center (NWSC) in Cheyenne.

The photo below shows masked NWSC staff members (from left) Kenny Raff, Jeremy Vaughan and Michael Kercher moving a DDN disc drive rack out of quarantine for installation in the computer room.

Read more in this new CISL article about how the NWSC team has adapted over the past several weeks.

NWSC staff at work

May 20, 2020

The Cheyenne HPC system will be unavailable to users for a week in mid-July to allow CISL staff and external contractors to perform necessary power infrastructure repairs at the NCAR-Wyoming Supercomputing Center (NWSC). The maintenance period will begin Monday, July 13, and the system is expected to be returned to service by Saturday, July 18.

The Casper cluster, GLADE and Campaign Storage file systems, data-access nodes, and HPSS will remain available throughout the week. Watch for more details and updates in the Daily Bulletin.

May 18, 2020

The CISL User Services Section will present an online tutorial at 9:30 a.m. MDT on Wednesday, May 27. Participants will learn about using the HPC resources provided by CISL. The 45-minute tutorial, presented by Rory Kelly of the CISL Consulting Services Group, will include time for users to ask questions. Topics will include:

  • Overview of available HPC systems
  • Access and the user environment
  • Data storage
  • Job scheduling with PBS and Slurm 
  • Compiling and running parallel programs
  • Remote visualization
  • Getting further help

Please use this link to register.

May 18, 2020

No scheduled downtime: Cheyenne, Casper, Campaign Storage, GLADE, HPSS

May 13, 2020

Registration is open for a free ACI-REF Virtual Residency Workshop on how to be an effective research computing facilitator. Participants will attend remotely via videoconference from Monday, June 1, to Friday, June 5.

This intermediate/advanced Research Computing Facilitation workshop is intended for those who want to be more effective at helping researchers and educators use research cyberinfrastructure. The only prerequisite is having an interest in helping researchers with their computing-intensive/data-intensive research. Previous attendance at a Virtual Residency workshop is not required. The workshop agenda and registration link are available here

May 12, 2020

XSEDE and the Pittsburgh Supercomputing Center will present an online-only Hybrid Computing workshop June 2-5. Registration is now open for this Summer Boot Camp event.

The workshop will include MPI, OpenMP, and GPU programming using OpenACC and accelerators. It will conclude with a special hybrid exercise contest that will challenge the students to apply their skills over the following three weeks to be awarded the Annual XSEDE Summer Boot Camp Championship Trophy. In addition, an XSEDE Badge will be available to those who complete the challenge.

Registration closes on May 29 or when the class reaches capacity. See this web page for more information and a registration link.

May 11, 2020

None planned for Cheyenne, Casper, HPSS, Glade, or Campaign Store

May 7, 2020

The Cheyenne and Casper login nodes are shared by everyone in the user community, so it’s important to keep in mind their intended purposes.

Cheyenne – You can run short, non-memory-intensive processes on the Cheyenne login nodes. These include tasks such as text editing and running small serial scripts or programs. Memory-intensive processes that slow login node performance for all users are killed automatically and the responsible parties are notified by email.

Casper – The Casper login nodes have one purpose: Logging in to start jobs on the cluster’s compute nodes. Any compute processes found running on the login nodes will be killed.

Learn more about using shared resources and other best practices right here.

May 6, 2020

CISL storage administrators estimate less than 43% of the data remaining on the High Performance Storage System (HPSS) can still be read for migration to other storage spaces before the system is decommissioned on October 1, 2021. The estimate is based on an aggressive but possible data-transfer rate of 2 PB per month.

Given the limited bandwidth and time available, users who have not already done so should begin moving valuable data to alternative storage systems and to delete files that are no longer needed.

Documentation and training are available on recommended processes for identifying and organizing HPSS holdings, copying files that need to be preserved to another storage resource, and deleting files that are no longer needed.

Please contact CISL for advice on individual workflows and storage options.