Skip to main content
SpringerLink
Log in

Partage de tâches entre processeurs homogenes

Task sheduling between two homogeneous processors

  • Published:
Acta Informatica Aims and scope Submit manuscript

Résumé

Une méthode de partage de tâches entre deux processeurs homogènes interconnectés est proposée. Nous supposons que l'un des deux processeurs est plus rapide que l'autre et nous donnons un algorithme s'appuyant sur une modélisation du système, permettant de diminuer les temps d'exécution des tâches du processeur le plus lent en les sous-traitant au processeur le plus rapide. L'algorithme proposé tient compte à la fois de la charge du processeur le plus rapide et des temps de transmission. L'efficacité de l'algorithme est montré à travers une étude théorique et une étude expérimentale mettant en æuvre un PDP 11/03 et un PDP 11/34.

Summary

A method for task scheduling between two homogeneous interconnected processors is proposed. We assume that one of the processors is faster than the other and we develop an algorithm based on a model of the system, which minimizes the execution delay of tasks arriving to the slow processor by taking into account the load of the fastest processor and the transmission delay. The performance of the algorithm is investigated experimentally using a PDP 11/03 connected to a PDP 11/34.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Références

  1. Agrawala, A.K., Tripathi, S., Ricart, G.: Adaptive routing using a virtual waiting time technique. Technical report TR-817, University of Maryland, Computer Science Department, 1979

  2. Balachandran, V.: An integer generalized transportation model for optimal job assignment in computer networks. Operations Res. 24, 4, 742–759 (1976)

    Google Scholar 

  3. Bryant, R.M., Finkel, R.A.: A stable distributed scheduling algorithm. Proceedings of the 2nd International Conference on Distributed Computing Systems, Paris, 314–323 (1981)

  4. Kleinrock, L.: Queueing systems, vol. I, John Wiley and Sons, 1975

  5. Kleinrock, L.: Queueing systems, vol. II, John Wiley and Sons, 1976

  6. Morgan, H.L., Levin, K.D.: Optimal program and data locations in computer networks. Comm. ACM 20, 5, 315–321 (1977)

    Google Scholar 

  7. Stone, H.S.: Multiprocessor scheduling with the aid of network flow analysis. IEEE Trans. Software Engrg. SE-3, 5, 315–321 (1977)

    Google Scholar 

  8. Stone, H.S.: Control of distributed processes. IEEE Computer 97–106 (1978)

  9. Van Tilborg, A.M., Wittie, L.D.: Wave scheduling: distributed allocation of task forces in network computers. Proceedings of the 2nd Conference on Distributed Computing Systems, Paris, 337–347 (1981)

  10. Yuon-Chieh Cho, Kohler, K.H.: Models for dynamic load balancing in a heterogeneous multiple processor system. IEEE Trans. Computers C-28, 5, 354–361 (1979)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. INRIA, Domaine de Voluceau, B.P. 105, F-78150, Le Chesnay, France

    Philippe Nain

Authors
  1. Philippe Nain
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Ce travail a été réalisé au laboratoire de Recherche en Université Paris-Sud, F-91405 Orsay, France

Rights and permissions

Reprints and permissions

About this article

Cite this article

Nain, P. Partage de tâches entre processeurs homogenes. Acta Informatica 18, 449–466 (1983). https://doi.org/10.1007/BF00289580

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00289580

Search

Navigation