Exploiting Performance Counters to Predict and Improve Energy Performance of HPC Systems - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Future Generation Computer Systems Année : 2013

Exploiting Performance Counters to Predict and Improve Energy Performance of HPC Systems

Résumé

Hardware monitoring through performance counters is available on almost all modern processors. Although these counters are originally designed for performance tuning, they have also been used for evaluating power consumption. We propose two approaches for modelling and understanding the behaviour of high performance computing (HPC) systems relying on hardware monitoring counters. We evaluate the effectiveness of our system modelling approach considering both optimising the energy usage of HPC systems and predicting HPC applications' energy consumption as target objectives. Although hardware monitoring counters are used for modelling the system, other methods -- including partial phase recognition and cross platform energy prediction -- are used for energy optimisation and prediction. Experimental results for energy prediction demonstrate that we can accurately predict the peak energy consumption of an application on a target platform; whereas, results for energy optimisation indicate that with no a priori knowledge of workloads sharing the platform we can save up to 24\% of the overall HPC system's energy consumption under benchmarks and real-life workloads.
Fichier principal
Vignette du fichier
TSAFACK_CHETSA_FGCS_hal.pdf (455.37 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00925306 , version 1 (07-01-2014)

Identifiants

Citer

Ghislain Landry Tsafack Chetsa, Laurent Lefèvre, Jean-Marc Pierson, Patricia Stolf, Georges da Costa. Exploiting Performance Counters to Predict and Improve Energy Performance of HPC Systems. Future Generation Computer Systems, 2013, vol. 36, pp. 287-298. ⟨10.1016/j.future.2013.07.010⟩. ⟨hal-00925306⟩
1005 Consultations
1295 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More