A Beowulf Cluster for Computational Chemistry
We have constructed a Beowulf cluster of networked PCs that is dedicated to solving chemistry problems using standard software packages such as Gaussian and GAMESS. We describe the economic and performance trade-offs in the design of the cluster, and present some some selected benchmark results for a parallel version of GAMESS. We believe that the Beowulf we have constructed offers the best price/performance ratio for our chemistry applications, and that commodity clusters can now provide dedicated supercomputer performance within the budget of most university departments.
KeywordsParallel Version Standard Software Package Beowulf Cluster Distribute Memory Architecture Shared Memory Programming
Unable to display preview. Download preview PDF.
- 1.Distributed and High-Performance Computing Group, University of Adelaide, Perseus: A Beowulf for computational chemistry, http://dhpc.adelaide.edu.au/projects/beowulf/perseus.html.
- 2.Gaussian, Inc., Gaussian, http://www.gaussian.com/.
- 3.Gordon Research Group, Iowa State University, GAMESS-US, http://www.msg.ameslab.gov/GAMESS/GAMESS.html.
- 4.Computing for Science Ltd, GAMESS-UK, http://www.dl.ac.uk/CFS/.
- 5.The Condor Project, University of Wisconsin, Condor: High Throughput Computing, http://www.cs.wisc.edu/condor/.
- 6.NASA CESDIS, Beowulf Project, http://www.beowulf.org/.
- 7.Scientific Computing Associates, Linda, http://www.sca.com/linda.html.
- 8.M.F. Guest, Performance of Various Computers in Computational Chemistry, Proc. of the Daresbury Machine Evaluation Workshop, Nov 1996. Updated version available at http://www.dl.ac.uk/CFS/benchmarks/compchem.html, June 1999.
- 10.M.F. Guest, P. Sherwood and J.A. Nichols, Massive Parallelism: The Hardware for Computational Chemistry?, http://www.dl.ac.uk/CFS/parallel/MPP/mpp.html.