Automatic Code Generation of Distributed Parallel Tasks

Abstract : With the advent of clustered systems, more and more parallel computing is required. However a lot of programming skills is needed to write a parallel codes, especially when you want to benefit from the various parallel architectural resources, with heterogeneous units and complex memory organizations. We present in this paper a method that generates automatically, step by step, a task-parallel distributed code from a sequential program. It has been implemented in an existing source-to-source compiler PIPS. Our approach provides two main advantages 1) all the program transformations are simple and applied on source code, thus are visible by the user, 2) a proof of correctness of the parallelization process can be made. This ensures that we end up with a correct distributed-task program for distributed-memory machines. To our knowledge, it is the first tool that automatically generates a distributed code for task parallelization.
Liste complète des métadonnées

Littérature citée [32 références]  Voir  Masquer  Télécharger

https://hal-mines-paristech.archives-ouvertes.fr/hal-01359468
Contributeur : Claire Medrala <>
Soumis le : mardi 7 février 2017 - 15:09:43
Dernière modification le : lundi 12 novembre 2018 - 10:56:54
Document(s) archivé(s) le : lundi 8 mai 2017 - 12:14:55

Fichier

A-641.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Nelson Lossing, Corinne Ancourt, François Irigoin. Automatic Code Generation of Distributed Parallel Tasks. 19th IEEE International Conference on Computational Science and Engineering (CSE 2016), Aug 2016, paris, France. pp.234-241, ⟨10.1109/CSE-EUC-DCABES.2016.190⟩. ⟨hal-01359468⟩

Partager

Métriques

Consultations de la notice

235

Téléchargements de fichiers

170