Skip to main content

On the effect of queue sizes and channel scheduling policies in the Segment router

  • Conference paper
  • First Online:
Parallel Computer Routing and Communication (PCRCW 1994)

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

Included in the following conference series:

  • 128 Accesses

Abstract

In this paper, we consider the effect of queue size and channel allocation policy on the performance of the Segment router [10]. The design decisions of the Segment router are motivated by the need to improve the network performance when the traffic consists of messages with widely different lengths. The Segment router provides separate buffer pools and implements different queueing policies for short and long messages. Furthermore it time-multiplexes the physical channels of the network fairly among the classes, possibly giving them different quantums of service.

Our experimental results show that increasing the size of the buffer pool in the Segment router improves the performance of small messages whereas increasing the segment size improves the performance of long messages.

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

Access this chapter

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. S. Borkar, R. Cohn, G. Cox, H.T. Kung, M. Lam, M. Levine, B. Moore, W. Moore, C. Peterson, J. Susman, J. Sutton, J. Urbanski, and J. Webb. Supporting systolic and memory communication in iWARP. In Proc. 17 Annual International Symposium on Computer Architecture, pages 70–81, 1990.

    Google Scholar 

  2. R. Cypher, A. Ho, S. Konstantinidou, and P. Messina. Architectural requirements of parallel scientific applications with explicit communication. In International Symposium on Computer Architecture, pages 2–13, 1993.

    Google Scholar 

  3. J.N. Daigle. Message delays with prioritized HOLP and round-robin packet servicing. IEEE Transactions on Communications, 35:609–619, 1987.

    Google Scholar 

  4. W.J. Dally. Wire-efficient VLSI multiprocessor communication networks. In Proc. Stanford Conference on Advanced Research in VLSI, pages 391–415, 1987.

    Google Scholar 

  5. W.J. Dally. Virtual-channel flow control. In Proc. 17th Annual International Symposium on Computer Architecture, pages 60–68, 1990.

    Google Scholar 

  6. J.-M. Hsu and P. Banerjee. Performance measurement and trace driven simulation of parallel cad and numeric applications on a hypercube multicomputer. In Proc. 17th Annual International Symposium on Computer Architecture, pages 260–269, 1990.

    Google Scholar 

  7. P. Kermani and L. Kleinrock. Virtual cut-through: A new computer communication switching technique. Computer Networks, pages 267–286, September 1979.

    Google Scholar 

  8. J.H. Kim and A.A. Chien. Evaluation of wormhole routed networks under hybrid traffic loads. In Proceedings of the Hawaii International Conference on System Sciences, 1993.

    Google Scholar 

  9. J.H. Kim and A.A. Chien. The impact of packetization in wormhole-routed networks. In Proceedings of PARLE, June 1993.

    Google Scholar 

  10. S. Konstantinidou. The Segment router: a novel router design for parallel computers. In Proc. ACM Symposium on Parallel Algorithms and Architectures, 1994 (to appear).

    Google Scholar 

  11. E.D. Lazowska, J. Zahorjan, G.S. Graham, and K.C. Sevcik. Quantitative System Performance. Prentice Hall, 1984.

    Google Scholar 

  12. C.Y. Lo. Performance analysis and application of a two-priority queue. AT&T Technical Journal, vol. 66:82–96, 1987.

    Google Scholar 

  13. S.P. Morgan. Queueing disciplines and passive congestion control in byte-stream networks. IEEE Transactions on Communications, 39:1097–1106, 1991.

    Google Scholar 

  14. J. Rexford and K. G. Shin Support for Multiple Classes of Traffic in Multicomputer Routers. In Proc. Parallel Computer Routing and Communication Workshop, May 1994.

    Google Scholar 

  15. C.L. Seitz, W.C. Athas, C.M. Flaig, A.J. Martin, J. Seizovic, C.S. Steele, and W.K. Sun. The architecture and programming of the Ametek series 2010 multicomputer. In Third Conference on Hypercube Computers, pages pp. 33–36, 1988.

    Google Scholar 

  16. Y. Tamir and G.L. Frazier. High-performance multi-queue buffers for VLSI communication switches. In Proc. 15th Annual International Symposium on Computer Architecture, pages 343–354, 1988.

    Google Scholar 

  17. Y. Tamir and G.L. Frazier. The design and implementation of a multi-queue buffer for VLSI communication switches. In International Conference on Computer Design, pages 466–471, 1989.

    Google Scholar 

  18. Thinking Machines Corporation. The Connection Machine CM5 Technical Summary. October 1991.

    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

Konstantinidou, S. (1994). On the effect of queue sizes and channel scheduling policies in the Segment router. 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_29

Download citation

  • DOI: https://doi.org/10.1007/3-540-58429-3_29

  • 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