Energy-Efficient Scheduling of Real-Time Periodic Tasks in Multicore Systems

Abstract : Nowadays, energy savings have become one of the most critical issues. In this paper, we propose an energy-efficient approach to scheduling periodic real-time tasks in the multicore context. Within a voltage/frequency domain (VFD), a simple static voltage/frequency scaling schedule (SimpleVS) is first introduced to select the utilization of the heaviest-loaded core as the shared operating frequency of this VFD. Next, the slack reallocation policy is proposed to further reclaim slack times while satisfying timeliness requirements. The slack reallocation strives to redistribute the slack times uniformly to the cores on the same VFD by appropriate job migrations. Experimental results show that compared with the static frequency schedule, our proposed policy can achieve energy savings up to 22 percent when the system is under-utilized.
Type de document :
Communication dans un congrès
Chen Ding; Zhiyuan Shao; Ran Zheng. IFIP International Conference on Network and Parallel Computing (NPC), Sep 2010, Zhengzhou, China. Springer, Lecture Notes in Computer Science, LNCS-6289, pp.344-357, 2010, Network and Parallel Computing. 〈10.1007/978-3-642-15672-4_29〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01054974
Contributeur : Hal Ifip <>
Soumis le : lundi 11 août 2014 - 09:17:00
Dernière modification le : samedi 25 novembre 2017 - 14:06:40
Document(s) archivé(s) le : mercredi 26 novembre 2014 - 21:36:23

Fichier

npc_crv.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Xiaodong Wu, Yuan Lin, Jian-Jun Han, Jean-Luc Gaudiot. Energy-Efficient Scheduling of Real-Time Periodic Tasks in Multicore Systems. Chen Ding; Zhiyuan Shao; Ran Zheng. IFIP International Conference on Network and Parallel Computing (NPC), Sep 2010, Zhengzhou, China. Springer, Lecture Notes in Computer Science, LNCS-6289, pp.344-357, 2010, Network and Parallel Computing. 〈10.1007/978-3-642-15672-4_29〉. 〈hal-01054974〉

Partager

Métriques

Consultations de la notice

97

Téléchargements de fichiers

357