Skip to main content
Aller à la page d’accueil de la Commission européenne (s’ouvre dans une nouvelle fenêtre)
français français
CORDIS - Résultats de la recherche de l’UE
CORDIS
CORDIScovery podcast 50th episode CORDIScovery podcast 50th episode
Contenu archivé le 2024-04-16

Development of a Distributed Memory MIMD System for Very High Performance Numerical Computing

Objectif

The GENESIS project had the ambitious aim of establishing European leadership in the field of high-performance parallel systems for numerical applications. The project was split into 3 projects, one of which was GENESIS II.
During the project Genesis, a number of benchmark programs were developed to evaluate the performance of the German SUPRENUM distributed memory (DM) computer compared to other parallel computers (including multiple vector and shared memory architectures). The refinement of this benchmark suite to assist in the SUPRENUM evaluation has been assessed. Several new benchmarks were added and extensive changes were made to several other benchmarks, such as the fast Fourier transform routines. In the rush to obtain the highest possible performance on SUPRENUM, some standards were sacrificed. For instance, not everybenchmark has a corresponding Fortran-77 single node baseline code written for it. Sometimes the sequential code was lacking, and sometimes extensive use of Fortran-90 extensions was made. One of the major activities of this project has been the filling in of many of these holes.

The GENESIS project had the ambitious aim of establishingEuropean leadership in the field of high performance parallel systems for numerical applications. The project was split into 3 projects, 1 of which was GENESIS II. Work in GENESIS II concentrated on software environments for high performance numerical computing on distributed memory architectures. Portable programming models and user friendly programming environment are key issues for high performance computing and will broaden the acceptance of large parallel distributed memory systems. In addition, the project included a small but important architectural task concerned with advanced interconnection components. In the long term, only the combination of functionalities for user requirements, user programming model, low level system software support for communication and interconnection components will guarantee highly efficient parallel user program execution. The main results of GENESIS II were:
the development of advanced software environment for highly parallel systems;
the development of a base of commercially relevant application packages and basic libraries;
realization of an implementation of a target testbed (GENESIS-P) as proposed in project 2447, GENESIS;
facilitation of the migration of applications from existing systems and to ensure portability of new implementations;
reflection of current and emerging standards, and participation in corresponding actions.
The main objectives of GENESIS II have been largely met:

develop an advanced software environment for highly parallel systems
develop a base of commercially relevant application packages and basic libraries
realise an implementation of a target testbed which led to the CS-2 machine
facilitate migration of existing applications and ensure portability of new implementations
reflect current and emerging standards, and to participate in corresponding actions.

Portability became a major issue of the project and the PARMACS (GMD/Argonne Portability Macro Library) was chosen as the common central programming model. A complete programming environment supports the development of PARMACS programs. A large set of software components is already in place, and will provide direct support for new architectures based on the advanced interconnection technology.

An ESPRIT special interest group was founded to discuss standardisation. This led to the definition of the Message Passing Interface (MPI) standard.

Champ scientifique (EuroSciVoc)

CORDIS classe les projets avec EuroSciVoc, une taxonomie multilingue des domaines scientifiques, grâce à un processus semi-automatique basé sur des techniques TLN. Voir: Le vocabulaire scientifique européen.

Vous devez vous identifier ou vous inscrire pour utiliser cette fonction

Programme(s)

Programmes de financement pluriannuels qui définissent les priorités de l’UE en matière de recherche et d’innovation.

Thème(s)

Les appels à propositions sont divisés en thèmes. Un thème définit un sujet ou un domaine spécifique dans le cadre duquel les candidats peuvent soumettre des propositions. La description d’un thème comprend sa portée spécifique et l’impact attendu du projet financé.

Données non disponibles

Appel à propositions

Procédure par laquelle les candidats sont invités à soumettre des propositions de projet en vue de bénéficier d’un financement de l’UE.

Données non disponibles

Régime de financement

Régime de financement (ou «type d’action») à l’intérieur d’un programme présentant des caractéristiques communes. Le régime de financement précise le champ d’application de ce qui est financé, le taux de remboursement, les critères d’évaluation spécifiques pour bénéficier du financement et les formes simplifiées de couverture des coûts, telles que les montants forfaitaires.

Données non disponibles

Coordinateur

Gesellschaft für Parallele Anwendungen und Systeme mbH
Contribution de l’UE
Aucune donnée
Adresse
Hermühlheimer Straße 10
50321 Brühl
Allemagne

Voir sur la carte
Coût total

Les coûts totaux encourus par l’organisation concernée pour participer au projet, y compris les coûts directs et indirects. Ce montant est un sous-ensemble du budget global du projet.
Aucune donnée

Participants (22)

Partager cette page Partager cette page sur les réseaux sociaux

Télécharger Télécharger le contenu de la page

Dernière mise à jour: 4 Mai 2023

Mon livret

Permalink: https://cordis.europa.eu/project/id/2702/fr

European Union, 2026

Mon livret 0 0