Application Performance of a Linux Cluster using Converse

Workshop on Runtime Systems for Parallel Programming at IPDPS (RTSPP) 2000

Pulication Type: Paper

Download: pdf ps

Abstract

Clusters of PCs are an attractive platform for parallel applications because of their cost effectiveness. We have implemented an interoperable runtime system called Converse on a cluster of Linux PCs connected by an inexpensive switched Fast Ethernet. This paper presents our implementation and its performance evaluation. We consider the question of the performance impact of using inexpensive communication hardware on real applications, using a large production-quality molecular dynamics program, NAMD, that runs on this cluster.

Research Areas

Text Ref

Laxmikant Kale and Robert Brunner and James Phillips and Krishnan Varadarajan,
"Application Performance of a Linux Cluster using Converse", Proceedings of 3rd
Workshop on Runtime Systems for Parallel Programming, Rolim et al (Eds), Lecture Notes in Computer Science 1586, IPPS/SPDP, Publ: Springer, 1999, pp. 483-495.

BibTex

@InProceedings{LinuxPerfRTSPP99,
  author =       "Laxmikant Kale and Robert Brunner and James Phillips
                  and Krishnan Varadarajan",
  title =        "Application Performance of a Linux Cluster using Converse",
  booktitle =    "Proceedings of 3rd Workshop on Runtime Systems for Parallel Programming, Rolim et al (Eds)",
  year =         1999,
  pages = "483-495",
  series = "Lecture Notes in Computer Science 1586",
  organization = "IPPS/SPDP",
  publisher =    "Springer",
}