 |
|
|
|
| HAL : hal-00497792, version 1 |
| DOI : 10.1016/j.procs.2010.04.115 |
| Fiche détaillée |  Récupérer au format |
|
|
| procedia computer science 1, 1 (2010) 1029-1038 |
|
|
|
|
| SysCellC: a data-flow programming model on multi-GPU |
|
|
| Dominique Houzet 1Sylvain Huet 1 |
|
|
| (01/05/2010) |
|
|
|
| High performance computing with low cost machines becomes a reality with GPU. Unfortunately, high performances are achieved when the programmer exploits the architectural specificities of the GPU processors: he has to focus on inter-GPU communications, task allocations among the GPUs, task scheduling, external memory prefetching, and synchronization. In this paper, we propose and evaluate a compile flow. It automates the transformation of a program expressed with the high level system design language SystemC, to its implementation on a cluster of multi-GPU. SystemC constructs and scheduler are directly mapped to the GPU API, preserving their semantic. Inter-GPU communications are abstracted by means of SystemC channels. |
|
|
|
|
|
|
|
|
|
|
|
| 1 : | Grenoble Images Parole Signal Automatique (GIPSA-lab) |
|
|
|
CNRS : UMR5216 – Université Joseph Fourier - Grenoble I – Université Pierre-Mendès-France - Grenoble II – Université Stendhal - Grenoble III – Institut Polytechnique de Grenoble - Grenoble Institute of Technology |
|
|
|
|
|
|
|
|
|
| Domaine | : | Informatique/Calcul parallèle, distribué et partagé Informatique/Traitement du signal et de l'image Sciences de l'ingénieur/Traitement du signal et de l'image |
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|||||
|
|
|
| hal-00497792, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00497792 | |
| oai:hal.archives-ouvertes.fr:hal-00497792 | |
| Contributeur : Dominique Houzet | |
| Soumis le : Lundi 5 Juillet 2010, 23:25:52 | |
| Dernière modification le : Lundi 30 Mai 2011, 16:45:25 | |
