Efficient Implicit Parallel Patterns for Geographic Information System

Abstract : With the data growth, the need to parallelize treatments become crucial in numerous domains. But for non-specialists it is still difficult to tackle parallelism technicalities as data distribution, communications or load balancing. For the geoscience domain we propose a solution based on implicit parallel patterns. These patterns are abstract models for a class of algorithms which can be customized and automatically transformed in a parallel execution. In this paper, we describe a pattern for stencil computation and a novel pattern dealing with computation following a pre-defined order. They are particularly used in geosciences and we illustrate them with the flow direction and the flow accumulation computations.
Type de document :
Communication dans un congrès
Petros Koumoutsakos, Michael Lees, Valeria Krzhizhanovskaya, Jack Dongarra and Peter Sloot. International Conference on Computational Science (ICCS 2017), Jun 2017, Zürich, Switzerland. Elsevier, Procedia Computer Science, 108, pp.545-554, 2017, 〈10.1016/j.procs.2017.05.235〉
Liste complète des métadonnées

https://hal-univ-orleans.archives-ouvertes.fr/hal-01557048
Contributeur : Kevin Bourgeois <>
Soumis le : mercredi 5 juillet 2017 - 17:29:51
Dernière modification le : mercredi 28 février 2018 - 10:23:10
Document(s) archivé(s) le : mardi 23 janvier 2018 - 21:33:56

Fichier

iccs17.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Kevin Bourgeois, Sophie Robert, Sébastien Limet, Victor Essayan. Efficient Implicit Parallel Patterns for Geographic Information System. Petros Koumoutsakos, Michael Lees, Valeria Krzhizhanovskaya, Jack Dongarra and Peter Sloot. International Conference on Computational Science (ICCS 2017), Jun 2017, Zürich, Switzerland. Elsevier, Procedia Computer Science, 108, pp.545-554, 2017, 〈10.1016/j.procs.2017.05.235〉. 〈hal-01557048〉

Partager

Métriques

Consultations de la notice

34

Téléchargements de fichiers

15