Advertisement

Scheduling with Communication Delays and On-Line Disturbances

  • Aziz Moukrim
  • Eric Sanlaville
  • Frédéric Guinand
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1685)

Abstract

This paper considers the problem of scheduling tasks on multiprocessors. Two tasks linked by a precedence constraint and executed by two different processors must communicate. The resulting delay depends on the tasks and on the processor network. In our model an estimation of the delay is known at compile time; but disturbances due to network contention, link failures,... may occur at execution time. Algorithms computing separately the processor assignment and the sequencing on each processor are considered. We propose a partially on-line scheduling algorithm based on critical paths to cope with the possible disturbances. Some theoretical results and an experimental study show the interest of this approach compared with fully on-line scheduling.

Keywords

Critical Path Precedence Constraint Task Graph Communication Delay List Schedule 
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.

References

  1. [1]
    Bampis E., Guinand F., Trystram D., Some Models for Scheduling Parallel Programs with Communication Delays, Discrete Applied Mathematics, 51, pp. 5–24, 1997.Google Scholar
  2. [2]
    Cheétienne Ph., Picouleau C., Scheduling with communication delays: a survey, in Scheduling Theory and its Applications, P. Chrétienne, E.G. Coffman, J.K. Lenstra, Z. Liu (Eds), John Wiley Ltd 1995.Google Scholar
  3. [3]
    Gerasoulis A., Yang T., A Comparison of Clustering Heuristics for Scheduling DAGs on Multiprocessors, J. of Parallel and Distributed Computing, 16, pp. 276–291, 1992.Google Scholar
  4. [4]
    Hanen C, Munier A, Performance of Coffman Graham schedule in the presence of unit communication delays, Discrete Applied Mathematics, 81, pp. 93–108, 1998.Google Scholar
  5. [5]
    Hwang J.J., Chow Y.C., Anger F.D., Lee C.Y., Scheduling precedence graphs in systems with interprocessor communication times, SIAM J. Comput., 18(2), pp.244–257, 1989.Google Scholar
  6. [6]
    Lenstra J.K., Veldhorst, M., Veltman B., The complexity of scheduling trees with communication delays, J. of Algorithms 20, pp. 157–173, 1996.Google Scholar
  7. [7]
    Moukrim A., Quilliot A., Scheduling with communication delays and data routing in Message Passing Architectures, LNCS, vol. 1388, pp. 438–451, 1998.Google Scholar
  8. [8]
    Papadimitriou C.H., Yannakakis M., Towards an Architecture-Independent Analysis of Parallel Algorithms, SIAM J. Comput., 19(2), pp. 322–328, 1990.Google Scholar
  9. [9]
    Rayward-Smith V.J., UET scheduling with interprocessor communication delays, Discrete Applied Mathematics, 18, pp. 55–71, 1986.Google Scholar
  10. [10]
    Sarkar V., Partitioning and Scheduling Parallel Programs for Execution on Multiprocessors, The MIT Press, 1989.Google Scholar
  11. [11]
    Sih G.C., Lee E.A., A compile-time scheduling heuristic for interconnection-constrained heterogeneous processor architectures, IEEE Trans. on Parallel and Distributed Systems, 4, pp. 279–301, 1993.Google Scholar
  12. [12]
    Yang T., Gerasoulis A., List scheduling with and without communication delay, Parallel Computing, 19, pp 1321–1344, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Aziz Moukrim
    • 1
  • Eric Sanlaville
    • 1
  • Frédéric Guinand
    • 2
  1. 1.LIMOS, Université de Clermont-IIAubière CedexFrance
  2. 2.LIH, Université du HavreLe Havre CedexFrance

Personalised recommendations