We present a particle-mesh N-body integrator running on GPU using CUDA. Relying on a grid-based description of the gravitational potential, it can simulate the evolution of self-interacting `stars' in order to model e.g. galaxies. All the steps of the application have been ported on the GPU , namely 1/ an histogramming algorithm with CUDPP, 2/ of the resolution of the Poisson equation by means of FFT with CUFFT and multi-grid relaxation, 3/ of an optimized finite difference scheme to compute the accelerations of stars and 4/ of an update procedure for positions and velocities. We present several tests at different resolution, and reach a speedup from 2 to 50 depending on the resolution and on the test case.

We present load-balancing strategies to improve the performances of parallel MPI applications running in a Grid environment. We analyze the data distribution constraints found in two scientific codes and propose adapted code transformations to load-balance computations. Experimental results confirm that such source code transformations can improve Grid application performances.

Les grilles informatiques s’averent d’un interet majeur pour l’acces a des ressources distribuees heterogenes, qu’il s’agisse de ressources de calcul ou de donnees. Cet article presente la realisation d’une grille dediee a l’execution d’applications paralleles MPI. Il presente le deploiement de l’intergiciel en prenant en compte differentes contraintes des sites participants. Des exemples de fonctionnement sur cette infrastructure de test (testbed) sont presentes. L’utilisation simultanee de plusieurs grilles ainsi que les limites de l’infrastructure de test sont abordees.