Skip to main content

Memory Management in a combined VIA/SCI Hardware

  • Conference paper
  • First Online:
Parallel and Distributed Processing (IPDPS 2000)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1800))

Included in the following conference series:

Abstract

In this document we make a brief review of memory management and DMA considerations in case of common SCI hardware and the Virtual Interface Architecture. On this basis we expose our ideas for an improved memory management of a hardware combining the positive characteristics of both basic technologies in order to get one completely new design rather than simply adding one to the other. The described memory management concept provides the opportunity of a real zero-copy transfer for Send-Receive operations by keeping full flexibility and efficiency of a nodes’ local memory management system. From the resulting hardware we expect a very good system throughput for message passing applications even if they are using a wide range of message sizes.

Daniel Balkanski and Stanislav Simeonov are from the Burgas Free University, Bulgaria.

The work presented in this paper is sponsored by the SMWK/SMWA Saxony ministries (AZ:7531.50-03-0380-98/6). It is also carried out in strong interaction with the project GRANT SFB393/B6 of the DFG (German National Science Foundation).

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

Access this chapter

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.

Similar content being viewed by others

References

  1. Torsten Amundsen and John Robinson: High-performance cluster-computing with Dolphin’s CluStar PCI adapter card. In: Proceedings of SCI Europe’ 98, Pages 149–152, Bordeaux, 1998

    Google Scholar 

  2. Philip Buonadonna, Andrew Geweke: An Implementation and Analysis of the Virtual Interface Architecture. University of California at Berkeley, Dept.of Computer Science, Berkeley, 1998. http://www.cs.berkeley.edu/~philipb/via/

    Book  Google Scholar 

  3. A new MPI-2-Standard MPI Implementation with support for the VIA. http://www.tu-chemnitz.de/informatik/RA/projects/chempi-html/

  4. Dolphin Interconnect Solutions AS: PCI-SCI Bridge Spec. Rev. 4.01. 1997.

    Google Scholar 

  5. Friedrich Seifert: Design and Implementation of System Software for Transparent Mode Communication over SCI., Student Work, Dept. of Computer Science, University of Technology Chemnitz, 1999. See also: http://www.tu-chemnitz.de/~sfri/publications.html

  6. Friedrich Seifert: Development of System Software to integrate the Virtual Interface Architecture (VIA) into Linux Operating System Kernel for optimized Message Passing. Diploma Thesis, TU-Chemnitz, Sept. 1999. See also: http://www.tu-chemnitz.de/informatik/RA/themes/works.html

  7. Joachim Worringen and Thomas Bemmerl: MPICH for SC-connected Clusters. In: Proceedings of SCI-Europe’99, Toulouse, Sept. 1999, Pages 3–11. See also: http://wwwbode.in.tum.de/events/sci-europe99/

  8. Mario Trams and Wolfgang Rehm: A new generic and reconfigurable PCI-SCI bridge. In: Proceedings of SCI-Europe’99, Toulouse, Sept. 1999, Pages 113–120. See also: http://wwwbode.in.tum.de/events/sci-europe99/

  9. M-VIA: A High Performance Modular VIA for Linux. Project Homepage: http://www.nersc.gov/research/FTG/via/

  10. MPI Software Technology, Inc. Performance of MPI/Pro for cLAN on Linux and Windows. http://www.mpi-softtech.com/performance/perf-win-lin.html

  11. The Open Scalable Cluster ARchitecture (OSCAR) Project. TU Chemnitz. http://www.tu-chemnitz.de/informatik/RA/projects/oscar_html/

  12. IEEE Standard for Scalable Coherent Interface (SCI). IEEE Std. 1596-1992. SCI Homepage: http://www.SCIzzL.com

  13. Mario Trams: Design of a system-friendly PCI-SCI Bridge with an optimized User-Interface. Diploma Thesis, TU-Chemnitz, 1998. See also: http://www.tu-chemnitz.de/informatik/RA/themes/works.html

  14. Mario Trams, Wolfgang Rehm, and Friedrich Seifert: An advanced PCI-SCI bridge with VIA support. In: Proceedings of 2nd Cluster-Computing Workshop, Karlsruhe, 1999, Pages 35–44. See also: http://www.tu-chemnitz.de/informatik/RA/CC99/

  15. The U-Net Project: A User-Level Network Interface Architecture. http://www2.cs.cornell.edu/U-Net

  16. Intel, Compaq and Microsoft. Virtual Interface Architecture Specification V1.0., VIA Homepage: http://www.viarch.org

  17. GigaNet Homepage: http://www.giganet.com

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

Trams, M., Rehm, W., Balkanski, D., Simeonov, S. (2000). Memory Management in a combined VIA/SCI Hardware. In: Rolim, J. (eds) Parallel and Distributed Processing. IPDPS 2000. Lecture Notes in Computer Science, vol 1800. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45591-4_2

Download citation

  • DOI: https://doi.org/10.1007/3-540-45591-4_2

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-67442-9

  • Online ISBN: 978-3-540-45591-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics