Skip to main content
Ir a la página de inicio de la Comisión Europea (se abrirá en una nueva ventana)
español español
CORDIS - Resultados de investigaciones de la UE
CORDIS
CORDIScovery podcast 50th episode CORDIScovery podcast 50th episode
Contenido archivado el 2024-04-16

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

Objetivo

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.

Ámbito científico (EuroSciVoc)

CORDIS clasifica los proyectos con EuroSciVoc, una taxonomía plurilingüe de ámbitos científicos, mediante un proceso semiautomático basado en técnicas de procesamiento del lenguaje natural. Véas: El vocabulario científico europeo..

Para utilizar esta función, debe iniciar sesión o registrarse

Programa(s)

Programas de financiación plurianuales que definen las prioridades de la UE en materia de investigación e innovación.

Tema(s)

Las convocatorias de propuestas se dividen en temas. Un tema define una materia o área específica para la que los solicitantes pueden presentar propuestas. La descripción de un tema comprende su alcance específico y la repercusión prevista del proyecto financiado.

Datos no disponibles

Convocatoria de propuestas

Procedimiento para invitar a los solicitantes a presentar propuestas de proyectos con el objetivo de obtener financiación de la UE.

Datos no disponibles

Régimen de financiación

Régimen de financiación (o «Tipo de acción») dentro de un programa con características comunes. Especifica: el alcance de lo que se financia; el porcentaje de reembolso; los criterios específicos de evaluación para optar a la financiación; y el uso de formas simplificadas de costes como los importes a tanto alzado.

Datos no disponibles

Coordinador

Gesellschaft für Parallele Anwendungen und Systeme mbH
Aportación de la UE
Sin datos
Dirección
Hermühlheimer Straße 10
50321 Brühl
Alemania

Ver en el mapa
Coste total

Los costes totales en que ha incurrido esta organización para participar en el proyecto, incluidos los costes directos e indirectos. Este importe es un subconjunto del presupuesto total del proyecto.
Sin datos

Participantes (22)

Compartir esta página Compartir esta página en las redes sociales

Descargar Descargar el contenido de la página

Última actualización: 4 Mayo 2023

Mi folleto

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

European Union, 2026

Mi folleto 0 0