Efficient Approximation Algorithms for Scheduling Malleable Tasks

Grégory Mounié 1, 2, 3 Christophe Rapine 1, 3 Denis Trystram 1, 2, 3
3 APACHE - Parallel algorithms and load sharing
ID-IMAG - Informatique et Distribution, Inria Grenoble - Rhône-Alpes, UJF - Université Joseph Fourier - Grenoble 1
Abstract : A malleable task is a computational unit which may be executed on any arbitrary number of processors, its execution time depend- ing on the amount of resources allotted to it. According to the standard behavior of parallel applications, we assume that the mal- leable tasks are monotonic, i.e. that the execution time is decreas- ing with the number of processors while the computational work increases. This paper presents a new approach for scheduling a set of independent malleable tasks which leads to a worst case guar- antee of for the minimization of the parallel execution time, or makespan. It improves all other existing practical results includ- ing the two-phases method introduced by Turek et al. The main idea is to transfer the difficulty of a two phases method from the scheduling part to the allotment selection. We show how to formu- late this last problem as a knapsack optimization problem. Then, the scheduling problem is solved by a dual-approximation which leads to a simple structure of two consecutive shelves.
Type de document :
Communication dans un congrès
1999, Association for Computing Machinery, pp.23-32, 1999
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00001525
Contributeur : Grégory Mounié <>
Soumis le : vendredi 7 mai 2004 - 16:37:37
Dernière modification le : vendredi 21 décembre 2018 - 10:46:08
Document(s) archivé(s) le : vendredi 17 septembre 2010 - 18:03:57

Identifiants

  • HAL Id : hal-00001525, version 2

Collections

INRIA | IMAG | UGA

Citation

Grégory Mounié, Christophe Rapine, Denis Trystram. Efficient Approximation Algorithms for Scheduling Malleable Tasks. 1999, Association for Computing Machinery, pp.23-32, 1999. 〈hal-00001525v2〉

Partager

Métriques

Consultations de la notice

404

Téléchargements de fichiers

592