Energy-Efficiency Metric for Real-Time Monitoring of OpenMP Programs Executing on Multicore Systems - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Poster De Conférence Année : 2019

Energy-Efficiency Metric for Real-Time Monitoring of OpenMP Programs Executing on Multicore Systems

Maxime Mirka
Gilles Sassatelli
Abdoulaye Gamatié

Résumé

Energy-efficiency has been a major challenge in compute systems over the last decade. In this paper, we propose an approach for on-line energy-efficiency mesurement when executing OpenMP workloads on multicore systems. The novelty of our approach lies in the ability to monitor energy efficiency at run-time without prior knowledge of the application profile or code annotation. The solution relies on two new metrics: the Chunks per Second (CpS) and Chunks per Joule (CpJ). The former captures the quantity of work achieved by threads per unit time (i.e. a performance indicator). The latter indicates the quantity of work achieved by threads per unit energy, also corresponding to the performance per watt. We show that these new metrics are suitable information making it possible to perform energy efficiency analysis.
Fichier principal
Vignette du fichier
GDR_SOC2_2019.pdf (128.28 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

lirmm-03326276 , version 1 (25-08-2021)
lirmm-03326276 , version 2 (30-08-2021)

Identifiants

  • HAL Id : lirmm-03326276 , version 2

Citer

Maxime Mirka, Gilles Sassatelli, Abdoulaye Gamatié. Energy-Efficiency Metric for Real-Time Monitoring of OpenMP Programs Executing on Multicore Systems. 13e Colloque National du GDR SoC², Jun 2019, Montpellier, France. ⟨lirmm-03326276v2⟩
41 Consultations
42 Téléchargements

Partager

More