A runtime approach to dynamic resource allocation for sparse direct solvers

A.-E Hugo 1, 2 A Guermouche 1, 3 P.-A Wacrenier 2, 1 R Namyst 2, 1
2 RUNTIME - Efficient runtime systems for parallel architectures
Inria Bordeaux - Sud-Ouest, UB - Université de Bordeaux, CNRS - Centre National de la Recherche Scientifique : UMR5800
3 HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest
Abstract : —To face the advent of multicore processors and the ever increasing complexity of hardware architectures, pro-gramming models based on DAG-of-tasks parallelism regained popularity in the high performance, scientific computing com-munity. In this context, enabling HPC applications to perform efficiently when dealing with graphs of parallel tasks that could potentially run simultaneously is a great challenge. Even if a uniform runtime system is used underneath, scheduling multiple parallel tasks over the same set of hardware resources introduces many issues, such as undesirable cache flushes or memory bus contention. In this paper, we show how runtime system-based scheduling contexts can be used to dynamically enforce locality of parallel tasks on multicore machines. We extend an existing generic sparse direct solver to use our mechanism and introduce a new decomposition method based on proportional mapping that is used to build the scheduling contexts. We propose a runtime-level dynamic context management policy to cope with the very irregular behavior of the application. A detailed performance analysis shows significant performance improvements of the solver over various multicore hardware.
Type de document :
Communication dans un congrès
43rd International Conference on Parallel Processing, Sep 2014, Minneapolis, United States. International Conference on Parallel Processing (ICPP 2014), 2014, 〈10.1109/ICPP.2014.57〉
Liste complète des métadonnées

Littérature citée [44 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01101054
Contributeur : Andra-Ecaterina Hugo <>
Soumis le : vendredi 9 janvier 2015 - 13:57:23
Dernière modification le : jeudi 11 janvier 2018 - 06:22:35
Document(s) archivé(s) le : vendredi 11 septembre 2015 - 01:35:32

Fichier

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

Identifiants

Collections

Citation

A.-E Hugo, A Guermouche, P.-A Wacrenier, R Namyst. A runtime approach to dynamic resource allocation for sparse direct solvers. 43rd International Conference on Parallel Processing, Sep 2014, Minneapolis, United States. International Conference on Parallel Processing (ICPP 2014), 2014, 〈10.1109/ICPP.2014.57〉. 〈hal-01101054〉

Partager

Métriques

Consultations de la notice

188

Téléchargements de fichiers

128