Logo Environmental XPRT
Companies
Products
Services
Software
Training
Applications
Sign in
List your business
The Potsdam Institute for Climate Impact Research (PIK)
About
  2. Companies
  3. The Potsdam Institute for Climate ...
  4. Services
  5. Compute Service Overview

Compute Service Overview

SHARE

The IT-Services Group operates a high performance cluster computer at the institute for scientific calculations (numerical simulation experiments). The current cluster has been ordered in 2008 and is in operation since spring 2009. The cluster is available to all members of scientific staff of the institute and as well to external scientists in the context of scientific co-operations. Registration is required in order to access the system.

Most popular related searches
numerical modeling
  • 2.560 CPU cores for batch processing.*
  • CPU cores are organized in 320 compute nodes with 2 x 4-core Intel Harpertown CPU and 32 GByte RAM each.
  • Compute nodes are divided into two network domains (green, blue) with 160 nodes each (blue: dx001 - dx160; green: dx161 - dx320).
  • Infiniband DDR interconnect,
  • 800 TByte total disk space.
  • Login via secure shell (ssh) using publickey authentication to interactive host(s): cluster.pik-potsdam.de.***
  • /iplex/01/
    A parallel file system for project groups with storage requirements of 1 to 20 TByte each. These project file systems will be created upon request only. Regular automated backup of data is default.
  • /scratch/01
    A parallel file system for temporary output only. Can be used by any scientist directly. Current user quota is 10 TByte. No backup. Files which have not been accessed for a given time - currently 3 months - will be deleted  automatically.

  • User initiated archive/retrieve available via the dsmj command on interactive nodes.
  • Introduction to Cluster Computing at PIK - presentation slides
  • For complete user documentation please refer to the High Performance Cluster User Guide

Statistics (total, group, user) - as sound statistics are indispensable to justify funding for machine enhancements and replacements all users are asked to submit  job files with the proper project group specified.

  • Cluster usage 2009
  • Cluster usage 2010
  • Cluster Usage 2011
  • Cluster Usage 2012