[hpc-announce] Availability of a large cluster resource for systems researchers

[Garth Gibson]

NSF Parallel Reconfigurable Observational Environment (PRObE) Cluster Resource Availability

Deadline: resource is available during 2013 and 2014

Webpage: http://www.nmc-probe.org/

Contact: probe at newmexicoconsortium.org

The Parallel Reconfigurable Observational Environment (PRObE) is an NSF sponsored research facility housed at the New Mexico Consortium (NMC) in Los Alamos, NM. It was designed to provide large-scale, dedicated computer resources for the systems research community. All PRObE resources are dedicated for systems research and users have full (and remote) access to the system hardware and software through the Emulab (emulab.net) interface developed at the University of Utah. At the moment, three clusters are online: Marmot ~100 nodes, Denali ~100 nodes, and Kodiak ~1000 nodes. Two more clusters will come online in the next six months. The majority of machines are housed at the NMC in Los Alamos and a smaller subset at Carnegie Mellon University in Pittsburgh, PA. Use of the smaller clusters follows standard Emulab online proposal and sharing procedures, and are intended for porting and practice use.  Use of the larger clusters is time shared, not space shared.  PIs write a short proposal justifying the science and their preparation and PRObE allocates the entire resource for days to weeks. All users are required to publish and/or release experimental results gathered using PRObE resources.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.mcs.anl.gov/mailman/private/hpc-announce/attachments/20130213/4a3dba14/attachment.html>