1022 articles – 5299 Notices  [english version]
HAL : inria-00431637, version 1

Voir la fiche détaillée  BibTeX,EndNote,...
Cosmological Simulations on a Grid of Computers
Benjamin Depardon1, 2, Eddy Caron1, Frédéric Desprez1, H.M. Courtois3, Jeremy Blaizot4
Grid'5000 Collaboration(s)

The work presented in this paper aims at restricting the input parameter values of the semi-analytical model used in Galics and MoMaF, so as to derive which parameters influence the most the results, e.g., star forma- tion, feedback and halo recycling efficiencies, etc. Our approach is to proceed empirically: we run lots of simulations and derive the correct ranges of values. The computation time needed is so large, that we need to run on a grid of com- puters. Hence, we model Galics and MoMaF execution time and output files size, and run the simulation using a grid middleware: Diet. All the complexity of accessing resources, scheduling simulations and managing data is harnessed by Diet and hidden behind a web portal accessible to the users.
1 :  LIP - Laboratoire de l'Informatique du Parallélisme
2 :  INRIA Grenoble Rhône-Alpes / LIP Laboratoire de l'Informatique du Parallélisme - GRAAL
3 :  IPNL - Institut de Physique Nucléaire de Lyon
4 :  CRAL - Centre de Recherche Astrophysique de Lyon
Cosmologie Observationnelle
Informatique/Calcul parallèle, distribué et partagé
Cosmology – N-body simulations – Parallel computing – Local uni- verse – Middleware – Grid-RPC
Liste des fichiers attachés à ce document :
RR-7093.pdf(665.1 KB)