Analytical Model and Performance Analysis of a Network Interface Card

N. Cherukuri, G.B. Kandira ju, N. Gautam, and A. Sivasubramaniam


  1. [1] Myricom, Inc., Arcadia, CA, USA,
  2. [2] T. von Eicken, A. Basu, V. Buch, & W. Vogels, U-Net: A user-level network interface for parallel and distributed computing, Proc. 15th ACM Symp. on Operating Systems Principles, December 1995, 40–53; available at papers/sosp.pd. doi:10.1145/224056.224061
  3. [3] Communication performance on Windows 2000 clusters connected by Fast Ethernet, Gigabit Ethernet, Giganet VIA and SCI networks, available at
  4. [4] Compaq Corp., Intel Corp., and Microsoft Corp., Virtualinterface architecture specification, Version 1.0, available at
  5. [5] M. Banikazemi,V. Moorthy, L. Herger, D. K. Panda, & B.Abali, Efficient virtual interface architecture support for IBMSP switch-connected NT clusters, Proc. Int. Parallel andDistributed Processing Symp., Cancun, Mexico, May 2000. doi:10.1109/IPDPS.2000.845962
  6. [6] F. Berry, E. Deleganes, & A.M. Merritt, The virtual interface architecture proof-of-concept performance results, IntelCorp, available at
  7. [7] P. Buonadonna, A. Geweke, & D. E. Culler, An implementation and analysis of the virtual interface architecture, Proc. ACM/IEEE Supercomputing, San Jose, CA, November 1998, 1–15.
  8. [8] L. Prylli, B. Tourancheau, & R. Westrelin, Modeling of ahigh speed network to maximize throughput performance: Theexperience of BIP over Myrinet, in H.R. Arabnia (ed.), Parallel and Distributed Processing Techniques and Applications(PDPTA ’98), vol. 2, Las Vegas, NV, 1998, 341–349.
  9. [9] D. Ponomarev, K. Ghose, & E. Saksonov, Optimal polling forlatency-throughput tradeoffs in queue-based network interfacesfor clusters, 7th ACM Euro-Par Conf., Manchester, UK;published as LNCS 2150 ISBN 3-540-42495-4 (Springer-Verlag,2001), 86–95.
  10. [10] L. Kleinrock, Queueing systems, vol. 2: Computer applications(New York: John Wiley and Sons, 1976).
  11. [11] M. Schwartz, Computer-communications network design andanalysis (Englewood Cliffs, NJ: Prentice-Hall, 1977).
  12. [12] C.H. Sauer & K.M. Chandy, Computer systems performancemodeling (Englewood Cliffs, NJ: Prentice-Hall, 1981).
  13. [13] R.F. Garzia & M.R. Garzia, Network modeling, simulationand analysis (New York: Marcel Dekker, 1990).
  14. [14] Rockwell Software, Sewickley, PA, USA,
  15. [15] S. Nagar, C. Liu, G. Kandiraju, A. Sivasubramaniam, &N. Gautam, Incorporating quality-of-service in the virtualinterface architecture, Proc. IPDPS, Santa Fe, NM, April 2002,CD-rom.
  16. [16] W. Whitt, the queueing network analyzer, Bell System Technical Journal, 62 (9), 1983, 2779–2815.
  17. [17] W. Whitt, Performance of the queueing network analyzer, BellSystem Technical Journal, 62 (9), 1983, 2817–2843.
  18. [18] N. Gautam, Course lecture notes: Queueing theory, Department of Industrial and Manufacturing Engineering, Pennsylvania State University, 2001.
  19. [19] J.A. Buzacott & J.G. Shanthikumar, Stochastic models ofmanufacturing systems (Englewood Cliffs, NJ: Prentice Hall,1993).
  20. [20] G. Bolch, S. Greiner, H. de Meer, & K.S. Trivedi, Queueingnetworks and Markov chains: Modeling and performanceevaluation with computer science applications (WileyEurope,1998).
  21. [21] H. Takagi, Queueing analysis of polling models, ACM Computing Surveys, 20 (1), 1988, 5–28. doi:10.1145/62058.62059
  22. [22] H. Takagi, Analysis of polling systems (Cambridge, MA: MITPress, 1986).
  23. [23] H. Takagi & L. Kleinrock, Analysis of polling systems, JSIResearch Report TR87-0002, IBM Japan Science Institute,Tokyo, January 1985.
  24. [24] G. Antchev, E. Cano, S. Cittolin, S. Erhan, B. Faure, D. Gigi, J. Gutleber, C. Jacobs, F. Meijers, E. Meschi, A. Ninane, L. Orsini, L. Pollet, A. Racz, D. Samyn, & N. Sinanis, Evaluation of myrinet for event builder of the CMS experiment, available through NEC Research Index.

Important Links:

Go Back