Adaptive Technique for Automatic Communication Access Pattern Discovery Applied to Data Prefetching in Distributed Applications Using Neural Networks and Stochastic Models

  • Evgueni Dodonov
  • Rodrigo Fernandes de Mello
  • Laurence Tianruo Yang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4330)


The distributed computing performance is usually limited by the data transfer rate and access latency. Techniques such as data caching and prefetching were developed to overcome this limitation. However, such techniques require the knowledge of application behavior in order to be effective. In this sense, we propose new application communication behavior discovery techniques that, by classifying and analyzing application access patterns, is able to predict future application data accesses. The proposed techniques use stochastic methods for application state change prediction and neural networks for access pattern discovery based on execution history, and is evaluated using the NAS Parallel Benchmark suite.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kotz, D., Ellis, C.S.: Practical prefetching techniques for multiprocessor file systems. Journal of Distributed and Parallel Databases 1(1), 33–51 (1993)CrossRefGoogle Scholar
  2. 2.
    Madhyastha, T.M., Reed, D.A.: Input/output access pattern classification using hidden Markovmodels. In: Proceedings of the Fifth Workshop on Input/Output in Parallel and Distributed Systems, San Jose, CA, pp. 57–67. ACM Press, New York (1997)CrossRefGoogle Scholar
  3. 3.
    Lei, H., Duchamp, D.: An analytical approach to file prefetching. In: 1997 USENIX Annual Technical Conference, Anaheim, California, USA (1997)Google Scholar
  4. 4.
    Dodonov, E., Sousa, J.Q., Guardia, H.C.: Gridbox: securing hosts from malicious and greedy applications. In: Proceedings of the 2nd workshop on Middleware for grid computing, pp. 17–22. ACM Press, New York (2004)CrossRefGoogle Scholar
  5. 5.
    Mello, R., Senger, L., Yang, L.: Automatic text classification using an artificial neural network. High Performance Computational Science and Engineering 1, 1–21 (2005)Google Scholar
  6. 6.
    Bailey, D.H., Barszcz, E., Barton, J.T., Browning, D.S., Carter, R.L., Dagum, D., Fatoohi, R.A., Frederickson, P.O., Lasinski, T.A., Schreiber, R.S., Simon, H.D., Venkatakrishnan, V., Weeratunga, S.K.: The nas parallel benchmarks. The International Journal of Supercomputer Applications 5(3), 63–73 (1991)CrossRefGoogle Scholar
  7. 7.
    Cao, P., Felten, E.W., Karlin, A.R., Li, K.: A study of integrated prefetching and caching stategies. In: Proceedings of the 1995 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems, pp. 188–197. ACM Press, New York (1995)Google Scholar
  8. 8.
    Dodonov, E., Guardia, H.C.: An architecture for integrated caching and prefetching mechanisms for distributed parallel file systems. In: Proceedings of the 2002 CLEI (2002)Google Scholar
  9. 9.
    Reddy, A.L.N.: Evaluation of caching strategies for a multimedia storage server. In: International Conference on Multimedia Computing and Systems, pp. 118–125 (1997)Google Scholar
  10. 10.
    Cortes, T., Labarta, J.: Linear aggressive prefetching: A way to increase the performance of cooperative caches. In: Proceedings of the Joint International Parallel Processing Symposium and IEEE Symposium on Parallel and Distributed Processing, San Juan, Puerto Rico, pp. 45–54 (1999)Google Scholar
  11. 11.
    Bianchini, R., Pinto, R., Amorim, C.L.: Data prefetching for software DSMs. In: International Conference on Supercomputing, pp. 385–392 (1998)Google Scholar
  12. 12.
    Mehrotra, S., Harrison, L.: Examination of a memory access classification scheme for pointer-intensive and numeric programs. In: ICS 1996, pp. 133–140 (1996)Google Scholar
  13. 13.
    Senger, L.J., Mello, R.F., Santana, M.J., Santana, R.C.: An on-line approach for classifying and extracting application behavior on linux. In: Yang, L.T., Guo, M. (eds.) High Performance Computing: Paradigm and Infrastructure, John Wiley and Sons, Chichester (2005)Google Scholar
  14. 14.
    Carpenter, G.A., Grossberg, S.: Art 2: Selforganisation of stable category recognition codes for analog input patterns. Applied Optics 26, 4919–4930 (1987)CrossRefGoogle Scholar
  15. 15.
    Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.: Phoneme recognition using time delay neural networks. IEEE Transactions on Accoustics, Speech and Signal Processing 37, 328–339 (1989)CrossRefGoogle Scholar
  16. 16.
    Burns, G., Daoud, R., Vaigl, J.: LAM: An Open Cluster Environment for MPI. In: Proceedings of Supercomputing Symposium, pp. 379–386 (1994)Google Scholar
  17. 17.
    Dodonov, E., de Mello, R.F., Yang, L.T.: A network evaluation for lan, man and wan grid environments. In: Yang, L.T., Amamiya, M., Liu, Z., Guo, M., Rammig, F.J. (eds.) EUC 2005. LNCS, vol. 3824, pp. 1133–1146. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  18. 18.
    Zell, A., Mache, N., Sommer, T., Korb, T.: Design of the snns neural network simulator. In: Kaindl, H. (ed.) 7. Österreichische Artificial-Intelligence-Tagung, pp. 93–102. Springer, Heidelberg (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Evgueni Dodonov
    • 1
  • Rodrigo Fernandes de Mello
    • 1
  • Laurence Tianruo Yang
    • 2
  1. 1.Instituto de Ciências Matemáticas e de ComputaçãoUniversidade de São PauloSão CarlosBrazil
  2. 2.St. Francis Xavier UniversityAntigonishCanada

Personalised recommendations