1. Networks

All servers are connected to both the primary engineering network as well as a second private high speed network for improved performance of parallel jobs.

2. Servers

  • A mix of EM64T (136 systems with 652 CPU's) and AMD64 (47 systems with 130 CPU's) giving a total of 782 CPU's with a total of 2.3 TB RAM and an estimated performance of 7.414 Terra Flops
  • Current systems are owned by the schools of EECS, Mechanical Engineering, Civil Engineering, College of Science and Nuclear Engineering Radiation Health Physics whose users enjoy high priority access to the systems that they own and a lower priority access on the shared group of the cluster nodes
  • Parallel program execution is available via the MPI (message passing interface) Library – Argonne’s mpich2
  • The server room is protected with both a UPS for short term power fluctuations and a diesel motor generator for long term power outages

3. Software

  • All servers are running RedHat Enterprise Linux 4 in a Sun Grid Engine environment
  • Fortran and C programs can be compiled to run parallel