Energy-Aware Scheduling of Flow Applications on Master-Worker Platforms

Abstract : We consider the problem of scheduling an application composed of independent tasks on a fully heterogeneous master-worker platform with communication costs. We introduce a bi-criteria approach aiming at maximizing the throughput of the application while minimizing the energy consumed by participating resources. Assuming arbitrary super-linear power consumption laws, we investigate different models for energy consumption, with and without start-up overheads. Building upon closed-form expressions for the uniprocessor case, we derive optimal or asymptotically optimal solutions for both models.
Type de document :
Communication dans un congrès
Sips, Henk and Epema, Dick and Lin, Hai-Xiang. Euro-Par 2009 Parallel Processing, Aug 2009, Delft, Netherlands. Springer Berlin Heidelberg, 5704, pp.281-292, 2009, Lecture Notes in Computer Science. 〈10.1007/978-3-642-03869-3_28〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01064145
Contributeur : Equipe Roma <>
Soumis le : lundi 15 septembre 2014 - 15:53:54
Dernière modification le : lundi 15 octobre 2018 - 01:06:50

Lien texte intégral

Identifiants

Collections

Citation

Jean-François Pineau, Yves Robert, Frédéric Vivien. Energy-Aware Scheduling of Flow Applications on Master-Worker Platforms. Sips, Henk and Epema, Dick and Lin, Hai-Xiang. Euro-Par 2009 Parallel Processing, Aug 2009, Delft, Netherlands. Springer Berlin Heidelberg, 5704, pp.281-292, 2009, Lecture Notes in Computer Science. 〈10.1007/978-3-642-03869-3_28〉. 〈hal-01064145〉

Partager

Métriques

Consultations de la notice

202