Linux HPC Systems

Linux High Performance Computing Clusters

A High Performance Computing  (HPC) cluster is collection of computers networked together that can be used as a single parallel computing system. HPC is intended for programs that require parallel processing (typically) with Message Passing Interface (MPI).  HPC clusters can provide a massive performance increase with a much lower hardware cost than a traditional symmetric multiprocessing system.  

Parallel computing is heavily used in research domains such as weather forecasting, phylogenetic tree building, computational fluid dynamics modelling, and molecular interaction simulation.

The HPC cluster can also be used for traditional, non-parallelized applications that employ single-threaded and multi-threaded processes like MATLAB, R, and other standard scientific applications.  Clusters can be used to run single isolated processes on a compute node or many copies of the same process (for instance, for the purpose of statistical validation).

OIT RC is working with PSU researchers to increase the number and variety of nodes available for tackling many data and computationally intensive problems.  This includes Intel Xeon and AMD x86_64 processors and Nvidia GPUs.

There is currently one HPC cluster available to PSU faculty, staff, students, and their collaborators who are interested in running existing applications or developing new parallel code.