Partitioned Global Address Space Languages

Mattias De Wael 1 Stefan Marr 2, 1 Bruno De Fraine 1 Tom Van Cutsem 1 Wolfgang De Meuter 1
1 Software Languages Lab
SLL - Software Languages Lab
2 RMOD - Analyses and Languages Constructs for Object-Oriented Application Evolution
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe
Abstract : The Partitioned Global Address Space (PGAS) model is a parallel programming model that aims to improve programmer productivity while at the same time aiming for high performance. The main premise of PGAS is that a globally shared address space improves productivity, but that a distinction between local and remote data accesses is required to allow performance optimizations and to support scalability on large-scale parallel architectures. To this end, PGAS preserves the global address space while embracing awareness of non-uniform communication costs. Today, about a dozen languages exist that adhere to the PGAS model. This survey proposes a definition and a taxonomy along four axes: how parallelism is introduced, how the address space is partitioned, how data is distributed among the partitions and finally how data is accessed across partitions. Our taxonomy reveals that today's PGAS languages focus on distributing regular data and distinguish only between local and remote data access cost, whereas the distribution of irregular data and the adoption of richer data access cost models remain open challenges.
Type de document :
Article dans une revue
ACM Computing Surveys, Association for Computing Machinery, 2016, pp.29
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01109405
Contributeur : Lse Lse <>
Soumis le : lundi 26 janvier 2015 - 11:52:21
Dernière modification le : jeudi 11 janvier 2018 - 06:22:25
Document(s) archivé(s) le : lundi 27 avril 2015 - 10:21:20

Fichier

acm-csur-de-wael-et-al-partiti...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01109405, version 1

Citation

Mattias De Wael, Stefan Marr, Bruno De Fraine, Tom Van Cutsem, Wolfgang De Meuter. Partitioned Global Address Space Languages. ACM Computing Surveys, Association for Computing Machinery, 2016, pp.29. 〈hal-01109405〉

Partager

Métriques

Consultations de la notice

366

Téléchargements de fichiers

569