Advertisement

Performance Analysis of Interconnection Networks Under Bursty and Batch Arrival Traffic

  • Yulei Wu
  • Geyong Min
  • Lan Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4494)

Abstract

Analytical models for adaptive routing in multicomputer inter-connection networks with the traditional non-bursty Poisson traffic have been widely reported in the literature. However, traffic loads generated by many real-world parallel applications may exhibit bursty and batch arrival properties, which can significantly affect network performance. This paper develops a new and concise analytical model for hypercubic networks in the presence of bursty and batch arrival traffic modelled by the Compound Poisson Process (CPP) with geometrically distributed batch sizes. The computation complexity of the model is independent of network size. The analytical results are validated through comparison to those obtained from the simulation experiments. The model is used to evaluate the effects of the bursty traffic with batch arrivals on the performance of interconnection networks.

Keywords

Parallel Processing Multicomputers Interconnection Networks Virtual Channels Compound Poisson Process 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Duato, J., Yalamanchili, S., Ni, L.: Interconnection Networks: An Engineering Approach, IEEE Computer Society Press, Silver Spring, MD (1997)Google Scholar
  2. 2.
    Duato, J.: A New Theory of Deadlock-Free Adaptive Routing in Wormhole Routing Networks. IEEE Trans. Parallel & Distributed Systems 4(12), 1320–1331 (1993)CrossRefGoogle Scholar
  3. 3.
    Dally, W.J.: Virtual Channel Flow Control. IEEE Trans. Parallel and Distributed Systems 3(2), 194–205 (1992)CrossRefGoogle Scholar
  4. 4.
    Dally, W.J., Towles, B.P.: Principles and Practices of Interconnection Network. Morgan Kaufmann, Seattle, Washington (2003)Google Scholar
  5. 5.
    Draper, J.T., Ghosh, J.: A Comprehensive Analytical Model for Wormhole Routing in Multicomputer Systems. Journal of Parallel & Distributed Computing 32(2), 202–214 (1994)CrossRefGoogle Scholar
  6. 6.
    Dinda, P.A., Garcia, B., Leung, K.S.: The Measured Network Traffic of Compiler Parallelized Programs, pp. 175–184, IEEE Computer Society Press, Silver Spring, MD (2001)Google Scholar
  7. 7.
    Kim, J., Das, C.R.: Hypercube Communication Delay with Wormhole Routing, IEEE Trans. Computers 43(7), 806–814 (1994)zbMATHGoogle Scholar
  8. 8.
    Kouvatsos, D.D.: Entropy Maximisation and Queueing Network Models. Annals of Operations Research 48(1), 63–126 (1994)zbMATHCrossRefGoogle Scholar
  9. 9.
    Kouvatsos, D.D., Awan, I.U.: Entropy Maximisation and Open Queueing Networks with Priorities and Blocking. Performance Evaluation 51(2-4), 191–227 (2003)CrossRefGoogle Scholar
  10. 10.
    Kouvatsos, D.D., Assi, S., Ould-khaoua, M.: Performance Modelling of Wormhole- Routed Hypercubes with Bursty Traffic and Finite Buffers. Int. Journal of Simulation, Practics, Systems, Science & Technology 6(3-4), 69–81 (2005)Google Scholar
  11. 11.
    Kleinrock, L.: Queueing Systems, vol. 1. John Wiley, New York (1975)zbMATHGoogle Scholar
  12. 12.
    Loucif, S., Ould-Khaoua, M., Mackenzie, L.M.: Modelling Fully-Adaptive Routing in Hypercubes. Telecommunication Systems 13(1), 111–118 (2000)CrossRefGoogle Scholar
  13. 13.
    Min, G., Ould-Khaoua, M.: Message Latency in Hypercubic Computer Networks with the Bursty Traffic Pattern. Computers and Electrical Engineering 30(3), 207–222 (2004)zbMATHCrossRefGoogle Scholar
  14. 14.
    Min, G., Ould-Khaoua, M.: A Performance Model for Wormhole-Switched Interconnection Networks under Self-Similar Traffic. IEEE Trans. Computers 53(5), 601–613 (2004)CrossRefGoogle Scholar
  15. 15.
    Ould-Khaoua, M., Sarbazi-Azad, H.: An Analytical Model of Adaptive Wormhole Routing in Hypercubes in the Presence of Hot Spot Traffic. IEEE Trans. Parallel and Distributed Systems 12(3), 283–292 (2001)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Ould-Khaoua, M.: A Performance Model for Duato’s Fully Adaptive Routing Algorithm in k-Ary n-Cubes. IEEE Trans. Computers 48(12), 1297–1304 (1999)CrossRefMathSciNetGoogle Scholar
  17. 17.
    Silla, F., Malumbres, M.P., Duato, J., Dai, D., Panda, D.K.: Impact of Adaptivity on the Behavior of Networks of Workstations under Bursty Traffic, pp. 88–95, IEEE Computer Society Press, Silver Spring, MD (1998)Google Scholar
  18. 18.
    Wu, J.: Maximum Entropy Analysis of Open Queueing Networks with Group Arrivals. Journal of the Operational Research Society 43(11), 1063–1078 (1992)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Yulei Wu
    • 1
  • Geyong Min
    • 1
  • Lan Wang
    • 1
  1. 1.Department of Computing, School of Informatics, University of Bradford, Bradford, BD7 1DPU.K.

Personalised recommendations