Service Communautaire d'Information sur la Recherche et le Développement - CORDIS


DEEPSEA Résumé de rapport

Project ID: 308246
Financé au titre de: FP7-IDEAS-ERC
Pays: France

Mid-Term Report Summary - DEEPSEA (Parallelism and Beyond: Dynamic Parallel Computation for Efficiency and High Performance)

This project aims to extend the frontiers of two major themes in computing, parallelism and dynamism, and develop a novel paradigm of computing: dynamic-parallelism. To this end, the project follows two lines of research. First, we develop techniques for extracting efficiency and high performance from parallel programs written in high-level programming languages. Second, we develop the dynamic-parallelism model, where computations can respond to a wide variety of dynamic changes to their data automatically and efficiently, by developing novel abstractions (calculi), high-level programming-language constructs, and compilation techniques.

The research has thus far culminated techniques for automatically controlling granularity in parallel computations, new scheduling algorithms for fine-grained parallelism, new parallel algorithms.
These techniques have been implemented as library extensions to the broadly used C++ programming language and are publicly available.


Catherine Zimmermann
Tél.: +33 1 39 63 59 01
Numéro d'enregistrement: 183383 / Dernière mise à jour le: 2016-05-27
Source d'information: SESAM