Message passing vs. shared address space on a cluster of SMPs

H. Shan, Jaswinder Pal Singh, L. Oliker, R. Biswas

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations

Abstract

The emergence of scalable computer architectures using clusters of PCs (or PC-SMPs) with commodity networking has made them attractive platforms for high-end scientific computing. Currently, message passing (MP) and shared address space (SAS) are the two leading programming paradigms for these systems. MP has been standardized with MPI, and is the most common and mature parallel programming approach. However, MP code development can be extremely difficult, especially for irregularly structured computations. SAS offers substantial ease of programming, but may suffer from performance limitations due to poor spatial locality and high protocol overhead. In this paper, we compare the performance of and programming effort required for six applications under both programming models on a 32-CPU PC-SMP cluster. Our application suite consists of codes that typically do not exhibit scalable performance under shared-memory programming due to their high communication-to-computation ratios and complex communication patterns. Results indicate that SAS can achieve about half the parallel efficiency of MPI for most of our applications; however on certain classes of problems, SAS performance is competitive with MPI.

Original languageEnglish (US)
Title of host publicationProceedings - 15th International Parallel and Distributed Processing Symposium, IPDPS 2001
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)0769509908, 9780769509907
DOIs
StatePublished - 2001
Event15th International Parallel and Distributed Processing Symposium, IPDPS 2001 - San Francisco, United States
Duration: Apr 23 2001Apr 27 2001

Publication series

NameProceedings - 15th International Parallel and Distributed Processing Symposium, IPDPS 2001

Other

Other15th International Parallel and Distributed Processing Symposium, IPDPS 2001
Country/TerritoryUnited States
CitySan Francisco
Period4/23/014/27/01

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Message passing vs. shared address space on a cluster of SMPs'. Together they form a unique fingerprint.

Cite this