Skip to main content

Clustering SMP Nodes with the ATOLL Network: A Look into the Future of System Area Networks

  • Conference paper
  • First Online:
High Performance Computing and Networking (HPCN-Europe 2000)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1823))

Included in the following conference series:

Abstract

Though several System Area Networks (SAN) are available to enhance the communication performance of a cluster, none of them has taken yet into account the special needs of clusters built out of SMP machines. Since single-CPU computers will be more and more replaced by small-scale SMP systems in the near future, an appropriate cluster interconnect should be adopted to the needs of multi-CPU nodes.

In this paper, we investigate the properties of the ATOLL SAN1, which offers with its four replicated network interfaces (NI), the integrated 8×8 switch and its four links the possibility to boost the total communication performance and message throughput inside a SMP node. As the chip design is in its final stage at the time of writing, we use detailed simulations of all hard- and software components to precisely predict the performance of the ATOLL SAN and show that ATOLL is capable of serving efficiently several message transfers at a time while eliminating the need to multiplex the network interface in software.

ATOLL is jointly developed with Siemens PC Systems GmbH, Augsburg, Germany

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

Access this chapter

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
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
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.

Similar content being viewed by others

References

  1. Ishikawa Y., Tezuka H., Hori A., Sumimoto S., Takahashi T., O’Carroll, and Harada H.: RWC PC Cluster II and SCore Cluster System Software — High Performance Linux Cluster. Proceedings of the 5th Annual Linux Expo, (1999) 55–62

    Google Scholar 

  2. Geoffray P., Prylli L., and Tourancheau B.: BIP-SMP: High Performance Message Passing over a Cluster of Commodity SMPs. Proceedings of the ACM/IEEE SC99 Conference, Portland, Oregon, (1999)

    Google Scholar 

  3. May J., and de Supinski B.: Experience with Mixed MPI/Threaded Programming Models. Proceedings of the Intl. Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA), Las Vegas, NV, Vol. VI (1999) 2907–2912

    Google Scholar 

  4. Lumetta S., Mainwaring A., and Culler D.: Multi-protocol Active Messages on a Cluster of SMPs. Proceedings of the ACM/IEEE Supercomputing Conference, San Jose, CA, (1997)

    Google Scholar 

  5. Rzymianowicz L., Brüning U., Kluge J., Schulz P., and Waack M.: ATOLL: A Network on a Chip. Proceedings of the Intl. Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA), Las Vegas, NV, Vol. V (1999) 2307–2313

    Google Scholar 

  6. Intel Corp.: Intel Architecture Software Developer’s Manual. Vol. 3, System Programming Guide, (1997)

    Google Scholar 

  7. Gooch R.: Linux Documentation I’ve written: Performance Monitoring Interface Control. WWW: http://www.atnf.csiro.au/~rgooch/linux/docs/index.html, (1999)

  8. Myricom, Inc.: Performance Measurements: GM API with 64-bit Myrinet/PCI Interfaces. http://www.myri.com/myrinet/performance, (1999)

  9. Prylli L., and Tourancheau B.: BIP: A New Protocol Designed for High Performance Networking on Myrinet. Lecture Notes in Computer Science (LNCS), Vol. 1388 (1998)

    Google Scholar 

  10. Quadrics Supercomputers World Ltd.: QsNet High Performance Interconnect. http://www.quadrics.com/web/public/fliers/qsnet.pdf, (1999)

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2000 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Rzymianowicz, L., Waack, M., Brüning, U., Fischer, M., Kluge, J., Schulz, P. (2000). Clustering SMP Nodes with the ATOLL Network: A Look into the Future of System Area Networks. In: Bubak, M., Afsarmanesh, H., Hertzberger, B., Williams, R. (eds) High Performance Computing and Networking. HPCN-Europe 2000. Lecture Notes in Computer Science, vol 1823. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45492-6_83

Download citation

  • DOI: https://doi.org/10.1007/3-540-45492-6_83

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-67553-2

  • Online ISBN: 978-3-540-45492-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy