A Modeling Approach based on UML/MARTE for GPU Architecture

Antonio Wendell De Oliveira Rodrigues 1 Frédéric Guyomarc'H 1 Jean-Luc Dekeyser 1
1 DART - Contributions of the Data parallelism to real time
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe
Abstract : Nowadays, the High Performance Computing is part of the context of embedded systems. Graphics Processing Units (GPUs) are more and more used in acceleration of the most part of algorithms and applications. Over the past years, not many efforts have been done to describe abstractions of applications in relation to their target architectures. Thus, when developers need to associate applications and GPUs, for example, they find difficulty and prefer using API for these architectures. This paper presents a metamodel extension for MARTE profile and a model for GPU architectures. The main goal is to specify the task and data allocation in the memory hierarchy of these architectures. The results show that this approach will help to generate code for GPUs based on model transformations using Model Driven Engineering (MDE).
Type de document :
Communication dans un congrès
Symposium en Architectures nouvelles de machines (SympA'14), May 2011, Saint Malo, France. 2011
Liste complète des métadonnées

Littérature citée [7 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00593863
Contributeur : Antonio Wendell De Oliveira Rodrigues <>
Soumis le : jeudi 19 mai 2011 - 15:23:24
Dernière modification le : vendredi 30 mars 2018 - 16:12:16
Document(s) archivé(s) le : samedi 20 août 2011 - 02:20:37

Fichiers

sympa2011.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00593863, version 1
  • ARXIV : 1105.4424

Citation

Antonio Wendell De Oliveira Rodrigues, Frédéric Guyomarc'H, Jean-Luc Dekeyser. A Modeling Approach based on UML/MARTE for GPU Architecture. Symposium en Architectures nouvelles de machines (SympA'14), May 2011, Saint Malo, France. 2011. 〈inria-00593863〉

Partager

Métriques

Consultations de la notice

308

Téléchargements de fichiers

362