Skip to main content
Log in

Analytical modelling of networks in multicomputer systems under bursty and batch arrival traffic

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

The hypercube and torus are two important message-passing network architectures of high-performance multicomputers. Analytical models of multicomputer networks under the non-bursty Poisson traffic have been widely reported. Motivated by the convincing evidence of bursty and batch arrival nature of traffic generated by many real-world parallel applications in high-performance computing environments, we develop a new and concise analytical model in this paper for hypercube and torus networks in the presence of batch message arrivals modelled by the compound Poisson process with geometrically distributed batch sizes. The average degree of virtual channel multiplexing is derived by employing a Markov chain which can capture the batch arrival nature. An attractive advantage of the model is its constant computation complexity independent of the network size. The accuracy of the analytical performance results is validated against those obtained from simulation experiments of an actual system.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

References

  1. Alzeidi N, Ould-Khaoua M, Khonsari A (2008) A new modelling approach of wormhole-switched networks with finite buffers. Int J Parallel, Emerg Distrib Syst 23(1):45–57

    Article  MATH  MathSciNet  Google Scholar 

  2. Bahn JH, Bagherzadeh N (2008) Design of simulation and analytical models for a 2D-meshed asymmetric adaptive router. IET Comput Digit Tech 2(1):63–73

    Article  Google Scholar 

  3. Baydal E, Lopez P, Duato J (2005) A family of mechanisms for congestion control in wormhole networks. IEEE Trans Parallel Distrib Syst 16(9):772–784

    Article  Google Scholar 

  4. Dally WJ (1992) Virtual channel flow control. IEEE Trans Parallel Distrib Syst 3(2):194–205

    Article  Google Scholar 

  5. Dally WJ, Towles BP (2004) Principles and practices of interconnection network. Morgan Kaufmann, San Mateo

    Google Scholar 

  6. Dinda PA (2006) Design, implementation, and performance of an extensible toolkit for resource prediction in distributed systems. IEEE Trans Parallel Distrib Syst 17(2):160–173

    Article  Google Scholar 

  7. Draper JT, Ghosh J (1994) A comprehensive analytical model for wormhole routing in multicomputer systems. J Parallel Distrib Comput 32(2):202–214

    Article  Google Scholar 

  8. Duato J (1993) A new theory of deadlock-free adaptive routing in wormhole routing networks. IEEE Trans Parallel Distrib Syst 4(12):1320–1331

    Article  Google Scholar 

  9. Duato J, Yalamanchili S, Ni L (2003) Interconnection networks: an engineering approach. Morgan Kaufmann, San Mateo

    Google Scholar 

  10. El-Affendi MA, Kouvatsos DD (1983) A maximum entropy analysis of the M/G/1 and G/M/1 queueing systems at equilibrium. Acta Inf 19(4):339–355

    Article  MATH  MathSciNet  Google Scholar 

  11. Hashemi-Najafabadi H, Sarbazi-Azad H, Rajabzadeh P (2007) An accurate performance model of fully adaptive routing in wormhole-switched two-dimensional mesh multicomputers. Microprocess Microsyst 31(7):445–455

    Article  Google Scholar 

  12. Heindl A (2003) Decomposition of general queueing networks with MMPP inputs and customer losses. Perform Eval 51(2–4):117–136

    Article  Google Scholar 

  13. Khonsari A, Ould-Khaoua M (2004) Compressionless wormhole routing: an analysis for hypercube with virtual channels. Perform Eval 53(1):23–42

    Google Scholar 

  14. Kleinrock L (1975) Queueing systems, vol. 1. Wiley, New York

    MATH  Google Scholar 

  15. Kocak T, Engel J (2006) Performance evaluation of wormhole routed network processor–memory interconnects. In: Proc of 20th international parallel and distributed processing symposium (IPDPS’06), IEEE Computer Society, Washington, DC, USA, 2006

  16. Kouvatsos DD, Assi S, Ould-khaoua M (2005) Performance modelling of wormhole-routed hypercubes with bursty traffic and finite buffers. Int J Simul Pract Syst Sci Technol 6(3–4):69–81

    Google Scholar 

  17. Kouvatsos DD, Awan IU (2003) Entropy maximisation and open queueing networks with priorities and blocking. Perform Eval 51(2–4):191–227

    Article  Google Scholar 

  18. Loucif S, Ould-Khaoua M, Mackenzie LM (2000) Modelling fully-adaptive routing in hypercubes. Telecommun Syst 13(1):111–118

    Article  Google Scholar 

  19. Mao W, Nicol DM (2003) On k-ary n-cubes: theory and applications. Discrete Appl Math 129(1):171–193

    Article  MATH  MathSciNet  Google Scholar 

  20. Miguel-Alonso J, Izu C, Gregorio JA (2008) Improving the performance of large interconnection networks using congestion-control mechanisms. Perform Eval 65(3–4):203–211

    Article  Google Scholar 

  21. Min G, Ould-Khaoua M (2004) A performance model for wormhole-switched interconnection networks under self-similar traffic. IEEE Trans Comput 53(5):601–613

    Article  Google Scholar 

  22. Min G, Ould-Khaoua M (2004) Performance modelling and evaluation of virtual channels in multicomputer networks with bursty traffic. Perform Eval 58(2–3):143–162

    Article  Google Scholar 

  23. Nelson R (1995) Probability, stochastic processes, and queueing theory: the mathematics of computer performance modeling. Springer, Berlin

    MATH  Google Scholar 

  24. Ould-Khaoua M (1999) A performance model for Duato’s fully adaptive routing algorithm in k-ary n-cubes. IEEE Trans Comput 48(12):1297–1304

    Article  MathSciNet  Google Scholar 

  25. Ould-Khaoua M, Sarbazi-Azad H (2001) An analytical model of adaptive wormhole routing in hypercubes in the presence of hot spot traffic. IEEE Trans Parallel Distrib Syst 12(3):283–292

    Article  MathSciNet  Google Scholar 

  26. Safaei F, Khonsari A, Fathy M, Ould-Khaoua M (2007) Communication delay analysis of fault-tolerant pipelined circuit switching in torus. J Comput Syst Sci 73(8):1131–1144

    Article  MATH  Google Scholar 

  27. Sarbazi-Azad H, Ould-Khaoua M, Mackenzie LM (2001) Analytical modeling of wormhole-routed k-ary n-cubes in the presence of hot-spot traffic. IEEE Trans Comput 50(7):623–634

    Article  MathSciNet  Google Scholar 

  28. Silla F, Malumbres MP, Duato J, Dai D, Panda DK (1998) Impact of adaptivity on the behavior of networks of workstations under bursty traffic. In: Proc. of IEEE international conference on parallel processing (ICPP’98), IEEE Computer Society, Washington, DC, USA, 1998, pp 88–95

  29. Squillante MS, Yao DD, Zhang L (1999) Analysis of job arrival patterns and parallel scheduling performance. Perform Eval 36–37(1):137–163

    Article  Google Scholar 

  30. Stewart IA, Xiang Y (2008) Embedding long paths in k-ary n-cubes with faulty nodes and links. IEEE Trans Parallel Distrib Syst 19(8):1071–1085

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Geyong Min.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wu, Y., Min, G., Ould-Khaoua, M. et al. Analytical modelling of networks in multicomputer systems under bursty and batch arrival traffic. J Supercomput 51, 115–130 (2010). https://doi.org/10.1007/s11227-009-0265-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-009-0265-x

Keywords

Navigation