Daily Bulletin Archive

Oct. 3, 2017

Cheyenne: Downtime Tuesday, October 3, 8:00 am - 12:00 am

HPSS: Downtime Tuesday, October 3, 7:30 am - 9:30 am

No Downtime: Yellowstone, Geyser_Caldera, GLADE

Oct. 3, 2017

The Cheyenne cluster will be unavailable from 8 a.m. to midnight MDT on Tuesday, October 3, to allow CISL staff to perform maintenance on several critical system components.

A system reservation will be put in place on batch jobs Monday afternoon. Jobs submitted with specified job times that overlap the reservation period will remain on hold until the system is restored to service. Running jobs that have not finished when maintenance begins will be killed and will need to be resubmitted after the maintenance period.

Users will be informed via the CISL Notifier service when the systems are returned to production.

Sep. 27, 2017

Allinea Software will hold a free webinar on Thursday, October 5, dealing with memory-bound code in high-performance and scientific applications. Attendees will see how the right checks and ongoing tuning can improve software run-times and identify bottlenecks that can slow down applications.  Click here to register or to find out more.

Sep. 27, 2017

Acknowledging the support of NCAR and CISL computing when you publish research results helps ensure continued support from the National Science Foundation and other sources of funding for future high-performance computing (HPC) systems. It is also a requirement of receiving an allocation, as noted in your award letter.

The reporting requirements, how to cite your use of various systems, and recommended wording of acknowledgments can be found on this CISL web page. The content of citations and acknowledgments varies depending on the type of allocation that was awarded.

Sep. 27, 2017

CISL staff are recommending that users avoid the tar command’s -S and --sparse options for handling sparse files when creating an archive. A recently discovered data corruption issue resulting from use of those options can affect tarballs that users create and it also has corrupted some automated GLADE user home directory backups over the past several months. Snapshots have not been affected, so users who suspect some file corruption may be able to use those to recover files.

Users are encouraged to avoid using the -S or --sparse options until a fix is in place and to watch for a Notifier message announcing that the work is complete.

Sep. 18, 2017

CISL is now accepting requests from university-based researchers for large-scale allocations for the new 5.34-petaflops Cheyenne cluster; submissions are due September 18.

Large allocations on Cheyenne are those of more than 400,000 core-hours. CISL accepts requests from university researchers for these large-scale allocations every six months. For submission instructions and information regarding available resources, see the CISL HPC Allocations Panel (CHAP) page.

Please contact cislhelp@ucar.edu if you have any questions about this opportunity.

Sep. 15, 2017

NCAR researchers and computational scientists are encouraged to submit requests for NCAR Strategic Capability (NSC) projects to be run on the Cheyenne system.

The deadline for NSC submissions is September 15. NSC allocations target large-scale projects lasting one year to a few years that align with NCAR’s scientific priorities and strategic plans.

For information please see the NSC Allocation homepage
Sep. 15, 2017

Course material for a self-paced Fortran workshop is being made available on GLADE for easy access by Cheyenne users. Files for the Scalar Fortran portion of the workshop are ready now, to be followed by Array Fortran, Object-Oriented Fortran, and Parallel Fortran material.

Users are encouraged to copy the files from this directory to their own GLADE space, where they can read, compile, and execute the examples:

/glade/u/apps/ch/opt/ftools/workshop/

Taken in order, the examples show how definition and scope work in Fortran. Declarations, control flow, bit models, interacting with the operating system, input/output transfers, and formats are covered.

Those interested are encouraged to subscribe to the Fortran Interest Group mailing list for updates and to contact Dan Nagle in the CISL Consulting Services Group with questions or comments.

Sep. 12, 2017

The maximum usable memory on Cheyenne’s batch nodes has been reduced by 1 GB, to 45 GB and 109 GB for the small and large memory nodes respectively. Also, the maximum PBS job script size has been set to 10 MB. Previously no limit was in effect.

The purpose of these changes is to improve overall system stability and the reliability of jobs running on shared nodes. Most users will be unaffected, but jobs that previously were close to using all available job memory may now fail. Please contact cislhelp@ucar.edu if you need assistance modifying your job scripts to meet these new limits.

Sep. 12, 2017

The Cheyenne cluster will be unavailable Tuesday, September 12, from 8 a.m. until noon MDT  to allow CISL staff to perform important system updates.

A system reservation will be put in place on batch jobs Monday afternoon. Jobs submitted with specified job times that overlap the reservation period will remain on hold until the system is restored to service. Running jobs that have not finished when the outage begins may be killed and need to be resubmitted after the system is restored to service. Users are advised to take this into account before submitting long jobs after 8 p.m. on Monday.

We apologize for any inconvenience this might cause. Users will be informed via the CISL Notifier service when the system is returned to production.

Pages