loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
20th International Symposium on High-Performance Computing in an Advanced Collaborative Environment (HPCS'06)
Design, Deployment and Bench of a Large Infiniband HPC Cluster
St. John's, Newfoundland
May 14-May 17
ISBN: 0-7695-2582-2
Mehdi Bozzo-Rey, Universite de Sherbrooke, Canada
Michael Jeanson, Universite de Sherbrooke, Canada
Minh-Nghia Nguyen, Universite de Sherbrooke, Canada
Carol Gauthier, Universite de Sherbrooke, Canada
Michel Barrette, Universite de Sherbrooke, Canada
Patrick Vachon, Universite de Sherbrooke, Canada
Karl Gaven-Venet, Universite de Sherbrooke, Canada
Hui Zhong Lu, Universite de Sherbrooke, Canada
Steve Allen, Universite de Sherbrooke, Canada
Alain Veilleux, Universite de Sherbrooke, Canada
This paper provides an overview of the Universite de Sherbrooke (UdeS) experience, in terms of design, deployment and bench of a large InfiniBand HPC cluster. In particular, attention is focused on tuning MVAPICH and the linpack benchmark in order to achieve 83.9% of the theoretical peak, which is usally reserved for high end proprietary clusters.
Citation:
Mehdi Bozzo-Rey, Michael Jeanson, Minh-Nghia Nguyen, Carol Gauthier, Michel Barrette, Patrick Vachon, Karl Gaven-Venet, Hui Zhong Lu, Steve Allen, Alain Veilleux, "Design, Deployment and Bench of a Large Infiniband HPC Cluster," hpcs, pp.8, 20th International Symposium on High-Performance Computing in an Advanced Collaborative Environment (HPCS'06), 2006
Usage of this product signifies your acceptance of the Terms of Use.