Statistics Computing Lab

New mailing list for the High Performance Computing cluster

  • Tue, 01/30/2018 - 1:27pm - Posted by: Michael Cammilleri

    All, we have a mailing list hosted by for cluster users. Please join this list to keep up with news, announcements, updates, outages, etc. To join, send mail to:

    join-stats-hpc-announce AT

Statistics Computing Lab Manual 2017

  • Tue, 08/22/2017 - 2:34pm - Posted by: Mike Cammilleri

    We have created an "operators manual" for the department computing resources. Please download this pdf for your reference when trying to answer common questions regarding day-to-day computing as well as research computing tasks.

HPC Cluster Page Updated with Julia Example Script

  • Wed, 11/02/2016 - 10:39am - Posted by: Mike Cammilleri

    We've added a simple example of submitting a Julia job to the SLURM cluster along with some important notes regarding Julia package directories and setting the appropriate environment variables. Be sure to check for updates to the HPC cluster info page here

High Performance Cluster now online using SLURM

  • Wed, 10/05/2016 - 11:02am - Posted by: Mike Cammilleri


    Statistics is now running our own high performance compute cluster consisting of six - many core, high memory nodes. The cluster will eventually replace the bigmemXX servers and the open, un-restricted way of running R, MATLAB, and other jobs. BigmemXX servers will be considered deprecated and will no longer be monitored for efficiency (if there was any).

    The new HPC cluster is considered in BETA as we continue to test and adjust the configuration. The system uses a job scheduler called SLURM ( which is much like Condor in that it uses simple submit scripts to start and run jobs. The scheduler will allocate the requested resources and queue your jobs so that it will run well with other users.

    ... read more

Help Docs Only Available From Stat Machines

  • Mon, 01/04/2016 - 11:03am - Posted by: Mike Cammilleri

    Currently our Statlab Help Docs are only available from department computer terminals. This is due to some security issues to the wiki. We are currently moving the documentation into the main website. Thank you for your patience.

Network connectivity sporadic

  • Mon, 02/02/2015 - 1:37pm - Posted by: Mike Cammilleri

    We are experiencing some network issues that cause desktop computers to be unable to boot within the department. This is a campus level network issue and there is some delay in getting it resolved. If your computer can not boot either use a machine in the lab or contact us. Thanks for your patience.

How to perform long running jobs

  • Tue, 11/04/2014 - 9:30am - Posted by: Mike Cammilleri
    In order to maintain network permissions over time (days, weeks, etc.) you will need to take extra steps before executing your code. Here is an example of the commands to run using bigmem03:

    /s/std/bin/runauth /usr/bin/screen
    ssh bigmem03
    R CMD BATCH your_r_code_file &
    Ctrl-A d

    Then, reattach to your screen session by logging back into the server and typing

    screen -r

    If you need to know more about screen, see the man page for screen (man screen). The idea is to run an ssh session inside a screen session. This will ensure that your AFS tokens remain valid after you leave the computer for hours, days, or weeks at a... read more