Heterogeneous High Performance Computer
Virginia W. Ross · 2005 Users Group Conference (DOD-UGC'05) · 2006
This paper discusses the proven concept of marrying the computing capabilities of a cluster computer with the reconfigurability of adaptive computing systems into a 48 node heterogeneous high performance computer (HHPC) with 34 TOPS peak performance. This system has shown over two years of success supporting the Signal and Image Processing (SIP), Forces Modeling and Simulation (FMS), Computational Electromagnetics and Acoustics (CEA), and Integrated Modeling and Test Environments (IMT) communities. The HHPC supports both local and remote users. Highlights of the research efforts performed on this system, and its advancement of reconfigurable computing, since it was introduced in 2003, are discussed.