The UMBC High Performance Computing Facility (HPCF) is the
community-based, interdisciplinary core facility for high performance 
computing available to all researchers at UMBC. Started in 2008 by more 
than 20 researchers from more than ten departments and research centers 
from all three colleges, it is supported by faculty contributions, 
federal grants, and the UMBC administration. More information on HPCF is 
available at www.umbc.edu/hpcf. Installed in Fall 2009, HPCF has 
an 86-node distributed-memory cluster, consisting of 82 compute nodes, 
2 development nodes, 1 user node, and 1 management node. Each node has 
two quad-core Intel Nehalem processors, 24 GB memory, and a 170 GB local 
harddrive. Access to the system is via a user node with 48 GB memory and 
a 500 GB harddrive, which also contains the users' home directories. A 
central 160 TB storage solution is provided. All components are 
connected by a state-of-the-art quad-data rate InfiniBand interconnect 
that provides both low latency and wide bandwidth for communications in 
parallel programs. The cluster offers standard scientific software 
including C, C++, FORTRAN compilers, numerical libraries, as well as 
MATLAB. Several implementations of the MPI libraries are available. 
System administration is provided by the UMBC Division of Information 
Technology, and users have access to consulting support provided by a 
dedicated full-time GRA. UMBC is committed to keeping the resources in 
the High Performance Computing Facility current and is planning on 
future regular upgrades. For dedicated priority access necessary for 
long-term jobs, users must contribute $5,000 per node to the system's 
funding, as stipulated in the usage policy at the HPCF webpage. For this 
purpose, we budget the purchase of four (4) compute nodes in this 
proposal to give our project the needed priority.