About the Gecko Cluster

From HPC

The cluster was was deliverded to the school at the end of the summer 2008. It was purchased from StreamLine Computing with SRIF funding, to provide a central HPC resource for research at the School. The service is hosted by IT Services in the Keppel Street building.

The cluster as delivered in 2008 consists of 30 compute nodes, 1 Head node, Ininfband and Gig Ethernet backbone. The os running on the cluster is Suse 10.1 (hence the gecko name) and the Job Scheduler is Sun Grid Engine 6.

A quick over view:

• Suse 10.1 64bit Linux OS
• 30 compute nodes 2x 2.5GHz Quad Core Intel Xeons with 8GB of memory (i.e. 8 jobs with 2GB memory each per node)
• Infiniband network for parallel computation
• openMPI (intel and gcc) for parallel computation across the inifiniband network.
• Sun Grid Engine 6 to manage job submission and queue management
• Intel C++/Fortran, GNU, Java 1.4,1.5,1.6 and R compilers
• Stata 10 se
• Also MPICH2 and SCORE for parallel computation, however these rely on gigabit ethernet which is much slower than the openMPI/ininfinband option.