A Performance and Energy Analysis of I/O Management Approaches for Exascale Systems

Abstract : The advent of fast, unprecedentedly scalable, yet energy-hungry exascale supercomputers poses a major challenge consisting in sustaining a high performance per watt ratio. While much recent work has explored new approaches to I/O management, aiming to reduce the I/O performance bottle-neck exhibited by HPC applications (and hence to improve application performance), there is comparatively little work investigating the impact of I/O management approaches on energy consumption. In this work, we explore how much energy a supercom-puter consumes while running scientific simulations when adopting various I/O management approaches. We closely examine three radically different I/O schemes including time partitioning, dedicated cores, and dedicated nodes. We im-plement the three approaches within the Damaris I/O mid-dleware and perform extensive experiments with one of the target HPC applications of the Blue Waters sustained-peta-flop/s supercomputer project: the CM1 atmospheric model. Our experimental results obtained on the French Grid'5000 platform highlight the differences between these three ap-proaches and illustrate in which way various configurations of the application and of the system can impact performance and energy consumption.
Type de document :
Communication dans un congrès
DIDC '14 Proceedings of the sixth international workshop on Data Intensive Distributed Computing, Jun 2014, Vancouver, Canada. pp.35-40, 2014, 〈10.1145/2608020.2608026〉
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01076522
Contributeur : Matthieu Dorier <>
Soumis le : mercredi 22 octobre 2014 - 13:43:34
Dernière modification le : mercredi 16 mai 2018 - 11:23:28
Document(s) archivé(s) le : vendredi 23 janvier 2015 - 10:51:14

Fichier

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

Identifiants

Citation

Orcun Yildiz, Matthieu Dorier, Shadi Ibrahim, Gabriel Antoniu. A Performance and Energy Analysis of I/O Management Approaches for Exascale Systems. DIDC '14 Proceedings of the sixth international workshop on Data Intensive Distributed Computing, Jun 2014, Vancouver, Canada. pp.35-40, 2014, 〈10.1145/2608020.2608026〉. 〈hal-01076522〉

Partager

Métriques

Consultations de la notice

684

Téléchargements de fichiers

285