On learning the energy model of an MPSoC for convex optimization

Abstract : The energy efficiency of a Multiprocessor SoC (MPSoC) is enhanced by complex hardware features such as Dynamic Voltage and Frequency Scaling (DVFS) and Dynamic Power Management (DPM). This paper proposes a methodology to learn an energy model from real power measurements. From this energy model, a convex optimization framework can determine the optimal energy efficient operating point in terms of frequency and number of active cores in an MPSoC. Experimental data are reported using a Samsung Exynos 5410 MPSoC. They show that a precise yet relatively simple model can be derived. © 2017 ACM.
Type de document :
Communication dans un congrès
14th ACM International Conference on Computing Frontiers, CF 2017, May 2017, Ischia, Italy. 〈10.1145/3075564.3078893〉
Liste complète des métadonnées

https://hal-univ-rennes1.archives-ouvertes.fr/hal-01622480
Contributeur : Laurent Jonchère <>
Soumis le : mardi 24 octobre 2017 - 14:12:26
Dernière modification le : vendredi 20 avril 2018 - 01:30:22

Identifiants

Citation

E. Nogues, D. Menard, A. Mercat, M. Pelcat. On learning the energy model of an MPSoC for convex optimization. 14th ACM International Conference on Computing Frontiers, CF 2017, May 2017, Ischia, Italy. 〈10.1145/3075564.3078893〉. 〈hal-01622480〉

Partager

Métriques

Consultations de la notice

93