inria-00158027, version 2
Scheduling multiple divisible loads on a linear processor network
Matthieu Gallet
1, 2Yves Robert
1, 2Frédéric Vivien
a, 1, 2
N° RR-6235 (2007)
Résumé : Min, Veeravalli, and Barlas have recently proposed strategies to minimize the overall execution time of one or several divisible loads on a heterogeneous linear network, using one or more installments. We show on a very simple example that their approach does not always produce a solution and that, when it does, the solution is often suboptimal. We also show how to find an optimal schedule for any instance, once the number of installments per load is given. Then, we formally state that any optimal schedule has an infinite number of installments under a linear cost model as the one assumed in the original papers. Therefore, such a cost model cannot be used to design practical multi-installment strategies. Finally, through extensive simulations we confirmed that the best solution is always produced by the linear programming approach, while solutions of the original papers can be far away from the optimal.
- a – INRIA
- 1 : Laboratoire de l'Informatique du Parallélisme (LIP)
- Université de Lyon – CNRS : UMR5668 – INRIA – École Normale Supérieure - Lyon – Université Claude Bernard - Lyon I
- 2 : GRAAL (INRIA Grenoble Rhône-Alpes / LIP Laboratoire de l'Informatique du Parallélisme)
- CNRS : UMR5668 – INRIA – École Normale Supérieure - Lyon – Université Claude Bernard - Lyon I – Laboratoire d'informatique du Parallélisme
- Domaine : Informatique/Calcul parallèle, distribué et partagé
- Référence interne : RR-6235
- Versions disponibles : v1 (27-06-2007) v2 (28-06-2007)
- inria-00158027, version 2
- http://hal.inria.fr/inria-00158027
- oai:hal.inria.fr:inria-00158027
- Contributeur : Rapport De Recherche Inria
- Soumis le : Jeudi 28 Juin 2007, 17:01:40
- Dernière modification le : Jeudi 28 Juin 2007, 17:02:13






Documents associés

Exporter