Skip to main content
SpringerLink
Log in

MPI Optimization for SMP Based Clusters Interconnected with SCI

  • Conference paper
  • First Online:
Recent Advances in Parallel Virtual Machine and Message Passing Interface (EuroPVM/MPI 2000)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1908))

Abstract

In this paper, we focus on performance of point-to-point communication and collective operations with multiple processes per node over an SCI network. By careful matching of sending and receiving data, performance close to network peak is achieved for point-to-point communication and a variety of collective operations.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

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.

References

  1. H. Bugge, K. Omang: Affordable Scalability using Multicubes. SCI. Architecture & software for high-performance compute clusters. pp 167–175, LNCS 11734-Springer-Verlag (1999)

    Google Scholar 

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

    Google Scholar 

  3. P. Geoffray, L. Prylli, B. Tourancheau: BIP-SMP: High Performance Message Passing over a Cluster of Commodity SMPs. Proceedings of Supercomputing 99 (1999)

    Google Scholar 

  4. W. Gropp, E. Lusk: Reproducible measurement of MPI performance characteristics. Proceedings of the 6th Euro-PVM/MPI pp 11–18 (1999).

    Google Scholar 

  5. L.P. Huse, K. Omang, H. Bugge, H. Ry, A.T. Haugsdal, E. Rustad: ScaMPI-Design and Implementation SCI. Architecture & software for high-performance compute clusters. pp 249–261, LNCS 11734-Springer-Verlag (1999)

    Google Scholar 

  6. L.P. Huse: Collective communication on dedicated clusters of workstations. Proceedings of the 6th Euro-PVM/MPI pp 469–476 (1999).

    Google Scholar 

  7. N. Karonis, B. de Supinski, I. Foster, W. Gropp, E. Lusk, and J. Bresnahan: Exploiting hierarchy in parallel computer networks to optimize collective operation performance, Proceedings of the 14th International parallel and distributed processing symposium (2000)

    Google Scholar 

  8. T. Kielmann, R.F.H. Hofman, H.E. Bal, A. Plaat, R.A.F. Bhoedjang: MagPIe: MPI’s Collective Communication Operations for Clustered Wide Area Systems, Proceedings of the 7th Principles and Practice of Parallel Programming (1999).

    Google Scholar 

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

    Google Scholar 

  10. Pallas MPI Benchmarks Version 2.2 http://www.pallas.com/ (1999)

  11. S.J. Ryan: Efficient Middleware for IO Bus Bridging Cluster Adapters. Dr.Scient, thesis from Department of Informatics, University of Oslo, Norway (1998)

    Google Scholar 

  12. S. Sistare, R. vande Vaart, E. Loh: Optimization of MPI Collectives on Clusters of Large-Scale SMP’s. Proceedings of Supercomputing 99 (1999)

    Google Scholar 

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

    Google Scholar 

  14. MPICH: Portable MPI Model Implementation. Version 1.2.0. Available from http://www.mcs.anl.gov/mpi/mpich (1999)

Download references

Author information

Authors and Affiliations

  1. Scali AS, Olaf Helsets vei 6, P.O. Box 70, Bogerud, N-0621, Oslo, 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. Innovative Computing Lab., University of Tennessee, 104 Yres Hall, Knoxville, TN, 37996, USA

    Jack Dongarra

  2. MTA SZTAKI Computer and Automation Research Institute, P.O. Box 63, Budapest, 1518, Hungary

    Peter Kacsuk  & Norbert Podhorszki  & 

Rights and permissions

Reprints and permissions

Copyright information

© 2000 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Huse, L.P. (2000). MPI Optimization for SMP Based Clusters Interconnected with SCI. In: Dongarra, J., Kacsuk, P., Podhorszki, N. (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. EuroPVM/MPI 2000. Lecture Notes in Computer Science, vol 1908. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45255-9_11

Download citation

  • DOI: https://doi.org/10.1007/3-540-45255-9_11

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-41010-2

  • Online ISBN: 978-3-540-45255-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation