Advertisement

Evolutionary Design of OAB and AAB Communication Schedules for Interconnection Networks

  • Miloš Ohlídal
  • Jiří Jaroš
  • Josef Schwarz
  • Václav Dvořák
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3907)

Abstract

Since chip multiprocessors are quickly penetrating new application areas in network and media processing, their interconnection architectures become a subject of sophisticated optimization. One-to-All Broadcast (OAB) and All-to-All Broadcast (AAB) [2] group communications are frequently used in many parallel algorithms and if their overhead cost is excessive, performance degrades rapidly with a processor count. This paper deals with the design of a new application-specific standard genetic algorithm (SGA) and the use of Hybrid parallel Genetic Simulated Annealing (HGSA) to design optimal communication algorithms for an arbitrary topology of the interconnection network. Each of these algorithms is targeted for a different switching technique. The OAB and AAB communication schedules were designed mainly for an asymmetrical AMP [15] network and for the benchmark hypercube network [16] using Store-and-Forward (SF) and Wormhole (WH) switching.

Keywords

Interconnection Network Evolutionary Design Communication Step Collective Communication Standard Genetic Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jantsch, A., Tenhunen, H.: Networks on Chip. Kluwer Academic Publ., Boston (2003) ISBN 1-4020-7392-5Google Scholar
  2. 2.
    Gabrielyan, E., Hersch, R.D.: Network′s Liquid Throughput: Topology Aware Optimization of Collective Communication. Unpublished work (2003)Google Scholar
  3. 3.
    Goldberg, D.: Genetics Algorithms in Search, Optimization, and Machine Learning. Addision-Wesley Publishing Company, Reading (1989)Google Scholar
  4. 4.
    Defago, X., Schiper, A., Urban, P.: Total Order Broadcast and Multicast Algorithms: Taxonomy and Survey, technical report DSC/2000/036 (2003)Google Scholar
  5. 5.
    Duato, J., Yalamanchili, S.: Interconnection Networks – An Engineering Approach. Morgan Kaufman Publishers, Elsevier Science (2003)Google Scholar
  6. 6.
    Staroba, J.: Parallel Performance Modelling, Prediction and Tuning, PhD. Thesis. Brno University of Technology, Brno, Czech Rep. (2004)Google Scholar
  7. 7.
    Ohlídal, M., Schwarz, J.: Hybrid parallel simulated annealing using genetic operations. In: Mendel 2004 10th Internacional Conference on Soft Computing, Brno, CZ, FSI VUT, pp. 89–94 (2004)Google Scholar
  8. 8.
    Goldberg, D.E.: A note on Boltzmann tournament selection for genetic algorithms and population-oriented simulated annealing, Complex Systems, pp. 445–460 (1990)Google Scholar
  9. 9.
  10. 10.
    Kita, H.: Simulated annealing. Proceeding of Japan Society for Fuzzy Theory and Systems 9(6) (1997)Google Scholar
  11. 11.
    Jaroš, J., Dvořák, V.: Speeding-up OAS and AAS Communication in Networking System on Chips. In: Proc. of 8th IEEE Workshop on Design and Diagnostic of Electronic Circuits and Systems, Sopron, HU, UWH, pp. 206–210 (2005)Google Scholar
  12. 12.
    Jaroš, J., Ohlídal, M., Dvořák, V.: Evolutionary Design of Group Communication Schedules for Interconnection Networks. In: Proceedings of 20th International Symposium of Computer and Information Science, Berlin, DE, pp. 472–481. Springer, Heidelberg (2005)Google Scholar
  13. 13.
    Dvořák, V.: Scheduling Collective Communications on Wormhole Fat Cubes. In: Proc. Of the 17th International Symposium on Computer Architecture and High Performance Computing, US. IEEE CS, Los Alamitos, pp. 27–34 (2005)Google Scholar
  14. 14.
    Pelikan, M., Goldberg, E., Sastry, K.: Bayesian Optimization Algorithm, Decision Graphs, and Occams RazorGoogle Scholar
  15. 15.
    Chalmers, A.-T.J.: Practical Parallel Processing. International Thomson Computer Press (1996)Google Scholar
  16. 16.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Miloš Ohlídal
    • 1
  • Jiří Jaroš
    • 1
  • Josef Schwarz
    • 1
  • Václav Dvořák
    • 1
  1. 1.Faculty of Information Technology, Department of Computer SystemsBrno University of TechnologyBrnoCzech Republic

Personalised recommendations