Skip to main content
Springer Nature Link
Log in

Collective Communication on Dedicated Clusters of Workstations

  • Conference paper
  • First Online:
Recent Advances in Parallel Virtual Machine and Message Passing Interface (EuroPVM/MPI 1999)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1697))

  • 475 Accesses

Abstract

Fast scalable collective operations are very important for achieving good application performance for highly parallel systems. This paper discusses scalability and absolute performance of various algorithms for collective communication. Performance is measured on the world largest SCI cluster, a machine with 96 dual Pentium II nodes interconnected with SCI, showing good scalability and performance.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Alexandro A., Ionescu M., Schauser K.E., Scheiman C.: LogGP: Incorporating Long Messages into the LogP Model-One Step Closer towards a Realistic Model of Parallel Computation. Proc. 7th Annual ACM Symposium Parallel Algorithms and Architectures (1995)

    Google Scholar 

  2. Barnett M., Gupta S., Payne D., Shuler L., van de Geijn R., Watts J.: Interprocessor Collective Communication Library. Proc. of Supercomputing’ 94 (1994).

    Google Scholar 

  3. Bernaschi M., Iannello G., Lauria M.: Experimental Results about two MPI Collective Communication Operations. Proc. 7th International Conference on High Performance Computing and Networking Europe (1999).

    Google Scholar 

  4. Brewer E.A., Kuszmaul B.C.: How to Get Good Performance from the CM-5 Data Network. Proc. of the 8th International Parallel Processing Symposium (1994).

    Google Scholar 

  5. Bugge H.: Affordable Scalability using Multicubes. Proc. of SCI Europe’ 98 (1998)

    Google Scholar 

  6. Dolphin ICS: PCI-SCI Bridge Functional Specification. Version 3.01 (1996).

    Google Scholar 

  7. IEEE standard for Scalable Coherent Interface IEEE Std 1596-1992 (1993)

    Google Scholar 

  8. Thierry Matthey-Parallab: Personal communication (1999)

    Google Scholar 

  9. Message Passing Interface Forum: MPI: A Message-Passing Interface Standard. Version 1.1 (1995)

    Google Scholar 

  10. MPICH: Portable MPI Model Implementation. Version 1.1.1 (1998)

    Google Scholar 

  11. PC2 Scalable Compute Server: http://www.uni-paderborn.de/pc2/systems/psc

  12. R. Rabenseifner: A new optimized MPI reduce algorithm http://www.hlrs.de/structure/support/parallel_computing/models/mpi/myreduce.html (1997).

  13. ScaMPI users guide Version 1.6.0-April 1999. http://www.scali.com

Download references

Author information

Authors and Affiliations

  1. Scali AS, Hvamstubben 17, N-2013, Skjetten, Norway

    Lars Paul Huse

Authors
  1. Lars Paul Huse
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. OakRidge National Laboratory, University of Tennessee, 107, Ayres Hall, Knoxville, TN, 37996-1301, USA

    Jack Dongarra

  2. Computer Science Department Computer Architecture and Operating Systems Group, Universitat Autònoma of Barcelona, E-08193, Bellaterra, Barcelona, Spain

    Emilio Luque  & Tomàs Margalef  & 

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Huse, L.P. (1999). Collective Communication on Dedicated Clusters of Workstations. In: Dongarra, J., Luque, E., Margalef, T. (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. EuroPVM/MPI 1999. Lecture Notes in Computer Science, vol 1697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48158-3_58

Download citation

  • DOI: https://doi.org/10.1007/3-540-48158-3_58

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-66549-6

  • Online ISBN: 978-3-540-48158-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics