Energy Efficiency and Performance Management of Parallel Dataflow Applications

Simon Holmbacka 1 Erwan Nogues 2 Maxime Pelcat 2 Sébastien Lafond 1 Johan Lilius 1
1 Åbo Academy University
2 IETR - Institut d'Electronique et de Télécommunications de Rennes
Abstract : Parallelizing software is a popular way of achieving high energy efficiency since parallel applications can be mapped on many cores and the clock frequency can be lowered. Perfect parallelism is, however, not often reached and different program phases usually contain different levels of parallelism due to data dependencies. Applications have currently no means of expressing the level of parallelism, and the power management is mostly done based on only the workload. In this work, we provide means of expressing QoS and levels of parallelism in applications for more tight integration with the power management to obtain optimal energy efficiency in multi-core systems. We utilize the dataflow framework PREESM to create and analyze program structures and expose the parallelism in the program phases to the power management. We use the derived parameters in a NLP (NonLinear Programming) solver to determine the minimum power for allocating resources to the applications.
Type de document :
Communication dans un congrès
The 2014 Conference on Design & Architectures for Signal & Image Processing, Oct 2014, Madrid, Spain
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-01078573
Contributeur : Erwan Nogues <>
Soumis le : mercredi 29 octobre 2014 - 15:00:44
Dernière modification le : jeudi 7 février 2019 - 17:50:23
Document(s) archivé(s) le : vendredi 14 avril 2017 - 14:23:22

Fichier

inpHoNoPeLaLi14a.full.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01078573, version 1

Collections

UNIV-NANTES | IETR | SUP_IETR | IETR-INSA | UR1-UFR-ISTIC | IETR-VAADER | UNIV-RENNES

Citation

Simon Holmbacka, Erwan Nogues, Maxime Pelcat, Sébastien Lafond, Johan Lilius. Energy Efficiency and Performance Management of Parallel Dataflow Applications. The 2014 Conference on Design & Architectures for Signal & Image Processing, Oct 2014, Madrid, Spain. 〈hal-01078573〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

278

Téléchargements de fichiers

312

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD