The Abel computer cluster

Named after the famous Norwegian mathematician Niels Henrik Abel (1802 – 1829), the Linux cluster at UiO is a shared resource for research computing capable of 258 TFLOP/s theoretical peak performance. At the time of installation Abel reached position 96 on the Top500 list of the most powerfull systems in the world.

Abel is an allround, allpurpose cluster designed to handle multiple concurrent jobs / users with varying requirements. Instead of massively parallell applications, the primary application profile is for moderately to smaller parallel applications with high IO and/or memory demand. Frequent users of Abel are from the life sciences, astrophysics, geophysics, chemistry and also humanities. All compute nodes on the cluster have a minimum 64 GB RAM, 16 physical CPU cores and are connected by FDR (56 Gbps) Infiniband.

Abel is a joint investment by the Research Council of Norway and UiO, and access is primarily through the Notur project. The cluster is available to all researchers.

 

Help

Please use hpc-drift at usit.uio.no for your questions and requests.

 

Abel operational log

  • Short stop of queue system at 09:00 Nov. 23, 2016 08:57 AM

    There will be a short stop of the queue system at 09:00 today, due to maintenance. Running jobs will not be affected, but commands like squeue and sbatch will not work during the stop.

  • Errros from module load: can be ignored. Nov. 4, 2016 10:20 AM

    In an attemt to reduce the number of jobs stalling due to processes hanging in disk wait, we deactivated mounting of software images via module load yesterday. Unfortunately the fix meant that module load started showing the following error:

    sh: /cluster/bin/module_load: No such file or directory

    This error can be ignored; the module is loaded as it should. We have now reverted our change, and will find a better way to deactivate the mountings.

    We are sorry for the confusion.

  • Short hang on /cluster Oct. 31, 2016 04:18 PM

    There was a short (~ 15 minutes) hang of /cluster at around 16:00, due to a file system daemon that had stopped working. We do not expect any file errors, and /work shall not have been affected. However, it is always advisable to check your jobs.

    Sorry for the inconvenience!

Further assistance or advice?

Do you need help with the research computing services or advice on how best to use the resources? Send an e-mail to the Department for Reserach Computing.

RCS Course Week

No upcoming events

Newsletter - University of Oslo
  • re-routing... Sep. 18, 2016 07:04 PM
  • Abel Newsletter #2, 2015 May 9, 2016 07:59 AM

    CPU allocation and advanced user support deadlines, our new software request system, and our fall course week, along with the usual list of updated tools and applications now available on Abel or through the Lifeportal.