Skip to main content

Three-dimensional network topologies

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 853))

Abstract

This paper presents the derivation and performance results of several new three-dimensional topologies. Various transformations can be applied to the conventional six-neighbor mesh in order to construct these topologies, which vary both in number of neighbors (degree) and logical connectivity. Analysis shows that after normalization for constant pin-count, lower-degree topologies yield lower latencies for long messages on unloaded networks, while higher-degree topologies possess higher bandwidth capacities. Although simulation results generally verify these findings, we also observe a surprising amount of difference in the performance between distinct topologies of the same degree.

This research is sponsored by DARPA contract #DABT63-93-C-0008.

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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Anant Agarwal. Limits on interconnection network performance. IEEE Transactions on Parallel and Distributed Systems, 2(4):398–412, 1991.

    Google Scholar 

  2. Thomas H. Cormen, Charles E. Leiserson, and Ronald L. Rivest. Introduction to Algorithms. MIT Press, Cambridge, Massachusetts, 1990.

    Google Scholar 

  3. William Dally. Virtual channel flow control. IEEE Transactions on Parallel and Distributed Systems, 3(2):194–205, 1992.

    Google Scholar 

  4. William Dally and Charles Seitz. Deadlock-free message routing in multiprocessor interconnection networks. IEEE Transactions on Computers, C-36(5), 1987.

    Google Scholar 

  5. Jae H. Kim, Ziqiang Liu, and Andrew A. Chien. Compressionless routing. In The 21st Annual International Symposium on Computer Architecture, pages 289–300, 1994.

    Google Scholar 

  6. D. Linder and J. Harden. An adaptive and fault tolerant wormhole routing strategy for k-ary n-cubes. IEEE Transactions on Computers, C-40(1):2–12, 1991.

    Google Scholar 

  7. Allen D. Malony. Regular processor arrays. In The 2nd Symposium on the Frontiers of Massively Parallel Computation, pages 499–502, 1988.

    Google Scholar 

  8. Lionel M. Ni and Philip K. McKinley. A survey of wormhole routing techniques in direct networks. Computer, 26(2):62–76, 1993.

    Google Scholar 

  9. Gill Pratt, Steve Ward, John Nguyen, and Chris Metcalf. The diamond interconnect. In press.

    Google Scholar 

  10. Supercomputing Research Center. Five year review, March 1991.

    Google Scholar 

  11. Steve Ward, et al. A scalable, modular, 3D interconnect. In 1993 International Conference on Supercomputing, pages 230–239, 1993.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Kevin Bolding Lawrence Snyder

Rights and permissions

Reprints and permissions

Copyright information

© 1994 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Nguyen, J., Pezaris, J., Pratt, G., Ward, S. (1994). Three-dimensional network topologies. In: Bolding, K., Snyder, L. (eds) Parallel Computer Routing and Communication. PCRCW 1994. Lecture Notes in Computer Science, vol 853. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58429-3_31

Download citation

  • DOI: https://doi.org/10.1007/3-540-58429-3_31

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-58429-2

  • Online ISBN: 978-3-540-48787-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics