QPACE: Quantum Chromodynamics Parallel Computing on the Cell Broadband Engine

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-designe...

Full description

Saved in:
Bibliographic Details
Published in:Computing in science & engineering 2008-11, Vol.10 (6), p.46-54
Main Authors: Goldrian, Gottfried, Meyer, Nils, Schäfer, Andreas, Solbrig, Stefan, Streuer, Thomas, Wettig, Tilo, Pleiter, Dirk, Sulanke, Karl-Heinz, Winter, Frank, Simma, Hubert, Schifano, Sebastiano Fabio, Huth, Thomas, Tripiccione, Raffaele, Krill, Benjamin, Lauritsen, Jack, Schick, Heiko, Ouda, Ibrahim, Heybrock, Simon, Hierl, Dieter, Maurer, Thilo
Format: Article
Language:English
Subjects:
Broadband
Cell Broadband Engine
Computation
Computational modeling
Computer applications
Computer networks
Computer simulation
Costs
Design engineering
Engines
field-programmable gate array
lattice quantum chromodynamics
Lattices
massively parallel computing
Mathematical models
Microprocessors
Networks
Parallel processing
performance modeling
QCD
Quantum computing
System on chip
System-on-a-chip
torus network
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1521-9615
1558-366X
DOI:10.1109/MCSE.2008.153