OpenLAB

From UMIACS
Revision as of 14:26, 8 August 2016 by Kmerrick (talk | contribs) (minor text fixes)
Jump to navigation Jump to search

The OpenLAB computing facility is a collection of initial nodes that all our users can use for their basic computer needs. They are backed by our NFShomes home directories. We currently run Red Hat Enterprise Linux 6.

Remote Login Nodes

Please connect to openlab.umiacs.umd.edu as it will connect you one of the two following remote login nodes. These are available via SSH.

  • opensub00.umiacs.umd.edu
  • opensub01.umiacs.umd.edu

The RSA SSH fingerprint for "openlab.umiacs.umd.edu" and all these specific hosts is,

 79:b3:dc:99:d8:ee:56:b8:51:63:bc:10:aa:4e:db:b3

OpenLAB Cluster

These nodes are not explicitly available to login to. They can either be scheduled from the submit/remote login nodes via SLURM.

There are two types of nodes we have:

  • 8 Sun Fire X2200 M2 nodes with Dual Operon (2.2ghz) Quad Core Processors (8 logical processors each), 8GB of ram and a local 750GB 7200RPM scratch disk. These can be scheduled with the basic SLURM partition dpart.
    • openlab00.umiacs.umd.edu
    • openlab01.umiacs.umd.edu
    • openlab02.umiacs.umd.edu
    • openlab03.umiacs.umd.edu
    • openlab04.umiacs.umd.edu
    • openlab05.umiacs.umd.edu
    • openlab06.umiacs.umd.edu
    • openlab07.umiacs.umd.edu
  • 2 nodes with Dual E5-2690 @ 2.90GHz (8 logical processors each), 128GB of ram, l1 cache: 512kB, l2 cache: 1024kB, l3 cache: 2042kB, and 2 400GB local scratch disks. Additionally these each have two Tesla K20c GPUs available in each node. These nodes need to be scheduled with the SLURM partition gpu. To learn how to request GPUs in SLURM please make sure to read the section in the SLURM documentation on requesting GPUs
    • openlab08.umiacs.umd.edu
    • openlab09.umiacs.umd.edu
  • 1 Dell Precision R5400 node with Dual Intel(R) Xeon(R) X5260 CPUs with 8GB RAM. This node can also be scheduled using the basic dque.
    • openlab10.umiacs.umd.edu - NVIDIA Tesla C2050 GPU with a total of Four (4x) C2080 GPU processors

OpenLAB Desktop Resources

  • Windows 7 Enterprise
    • jackson.pc.umiacs.umd.edu (AVW 4430)
  • Mac OS X 10.11
    • panda.umiacs.umd.edu (AVW 4430)