This title appears in the Scientific Report : 2008 

QPACE: Quantum Chromodynamics Parallel Computing on the Cell Broadband Engine
Goldrian, G.
Huth, T. / Krill, B. / Lauritsen, J. / Schick, H. / Ouda, I. / Heybrock, S. / Hierl, D. / Maurer, T. / Meyer, N. / Schäfer, A. / Solbrig, S. / Streuer, T. / Wettig, T. / Pleiter, D. / Sulanke, K.-H. / Winter, F. / Simma, H. / Schifano, S.F. / Tripiccione, R. / Nobile, A. / Drochner, M. / Lippert, T. / Fodor, Z.
Jülich Supercomputing Center; JSC
Jülich-Aachen Research Alliance - Simulation Sciences; JARA-SIM
Computing in science and engineering, 10 (2008) S. 46 - 54
College Park, Md. Inst. 2008
46 - 54
10.1109/MCSE.2008.153
Journal Article
Scientific Computing
Computing in Science & Engineering 10
J
Please use the identifier: http://dx.doi.org/10.1109/MCSE.2008.153 in citations.
Application-driven computers for Lattice Gauge Theory simulations have often been based on system-on-chip designs, but the development costs can be prohibitive for academic project budgets. An alternative approach uses compute nodes based on a commercial processor tightly coupled to a custom-designed network processor. Preliminary analysis shows that this solution offers good performance, but it also entails several challenges, including those arising from the processor's multicore structure and from implementing the network processor on a field-programmable gate array.