×
This is the old CSCAMM website made available for archival purposes. For the current CSCAMM website, please visit www.cscamm.umd.edu.

CSCAMM GPU Workstation

In Fall of 2009, Hewlett-Packard awarded CSCAMM a HP Z800 workstation featuring a NVIDIA C1060 GPU capable of 1 teraflop highly parallel computing performance. Installed on this workstation are the NVIDIA CULA (GPU-accelerated LAPACK libraries), standard Intel C and Fortran compilers and math libraries, CUDA 3.0, the 0.2 MAGMA project dense algebra library, and the GPUmat toolbox for Matlab.

Thanks to a grant received by Prof. Millard Alexander, CSCAMM has upgraded the GPU Workstation to the new generation NVIDIA Fermi C2050 GPU, which is capable of 515 Gigaflops of double-precision peak performance and over 1 Teraflop of single precisions peak performance.

Tesla C2050

CSCAMM Tesla S1070 Computation Servers

CSCAMM operates 2 independant Tesla 1070 computation servers. Each computation server features 960 GPU cores capable of 4 Teraflop of single precisions peak performance and 1 Tb of dedicated storage.Tesla S1070
 

If you would like an account on these systems please send email to

The approval of such request requires a brief research plan which highlights the scope and relevance of the usage of the CSCAMM GPU Computation resources.

 

 



University of Maryland    

UM Home | Directories | Calendar
Maintained by CSCAMM
Direct questions and comments to

CSCAMM is part of the
College of Computer, Mathematical & Natural Sciences (CMNS)