Détail d'une fiche   Version PDF

DREAMPAL (SR0683RR)

Dynamic Reconfigurable Massively Parallel Architectures and Languages

DREAMPAL (SR0548UR) →  DREAMPAL


Statut: Terminée

Responsable : Vlad Rusu

Mots-clés de "A - Thèmes de recherche en Sciences du numérique - 2023" : Aucun mot-clé.

Mots-clés de "B - Autres sciences et domaines d'application - 2023" : Aucun mot-clé.

Domaine : Algorithmique, programmation, logiciels et architectures
Thème : Architecture, langages et compilation

Période : 01/01/2015 -> 31/12/2016
Dates d'évaluation : 22/03/2016

Etablissement(s) de rattachement : <sans>
Laboratoire(s) partenaire(s) : <sans UMR>

CRI : Centre Inria de l'Université de Lille
Localisation : Centre Inria de l'Université de Lille
Code structure Inria : 101046-1

Numéro RNSR : 201321075F
N° de structure Inria: SR0683RR

Présentation

Standard Integrated Circuits are reaching their limits and need to evolve to meet the requirements of next-generation computing. One of the most promising evolutions are the next-generation 3D FPGAs (three-dimensional Field Programmable Gate Arrays), which will allow efficient dynamic reconfigurations in a massively parallel manner. Software applications running on such architectures can efficiently reconfigure the hardware at runtime according to their needs, thereby achieving significant savings in circuit space, energy consumption, and execution time. This new hardware paradigm opens many opportunities for research since there are no no execution models and no dedicated tools for programming software applications on them.


Axes de recherche

We shall address the following topics: designing massively parallel dynamically reconfigurable architectures; proposing execution models as well as dedicated programming languages for them; and designing software engineering tools for those languages: compilers, simulators, and formal verifiers, for enabling the rigorous, efficient, and safe programming of software applications on the new hardware. Our application domain is safety-critical embedded applications performing intensive computation.


Relations industrielles et internationales