Pittsburgh Supercomputing Center 

Advancing the state-of-the-art in high-performance computing,
communications and data analytics.


Allocation requests being accepted through Oct. 15     More information  

PSC's Computational Resources

This page lists PSC's computational resources. For the data management options PSC provides, see the storage resources page.

Supercomputing-class resources

Click the image or machine name to get specific usage information.


Greenfield  is designed for memory-limited scientific applications in fields as different as biology, chemistry, cosmology, machine learning and economics. Funded by the National Science Foundation (NSF), Greenfield comprises 360 cores and 18TB of memory in three nodes: two HP DL580s and an HP SuperDome X. 

SherlockSherlock is a YarcData uRiKA™ (Universal RDF Integration Knowledge Appliance) data appliance with PSC enhancements. It enables large-scale, high-performance graph analytical processing through massive multithreading (128 hardware threads per processor), a shared address space, sophisticated memory access optimizations and support for heterogeneous applications. Sherlock is funded by the NSF.


Anton is a special purpose supercomputer designed to dramatically increase the speed of molecular dynamics simulations, allowing biomedical researchers to understand the motions and interactions of proteins and other biologically important molecules over longer time periods than previously possible. Designed and built by D.E. Shaw Research (DRES), the Anton machine hosted at PSC was provided without cost by DESRES for non-commerical use by the national biomedical research community.

BioU is a bioinformatics educational resource funded by the NIH. It provides a stable environment in which classroom and individualized research training can occur. Small research projects, such as individualized class projects, graduate student projects, and many typical academic bioinformatics projects can be hosted on BioU. Projects requiring significant computational resources should be carried out on other, larger, PSC computing platforms.