CIC Portal | IN2P3 | CNRS


A XML-based description language and execution environment for orchestrating grid jobs
authors: Reynaud, S.; Hernandez, F.
IEEE International Conference on Services Computing, 2005

Grids are often used through simplified job submission interfaces that abstract the underlying grid infrastructure as a black box. These interfaces suit well to developers of simple grid applications requiring the coordination of grid jobs, for which monitoring and error handling are done more or less manually. However, developers of advanced grid applications such as grid portals need more flexible tools to develop efficient and robust applications with advanced capabilities such as monitoring, error handling, failure recovery, resource release, etc. In this paper, we present through a typical application example a XML-based language designed to describe applications orchestrating grid jobs. We also present the execution environment supporting the proposed language and we show how even simple grid applications can be expressed in this language and benefit of the advanced capabilities of the execution environment.

       A XML-based description language and execution environment for orchestrating grid jobs

Parallelization of {Monte Carlo} Simulations and Submission to a Grid Environment
authors: Maigne L., Hill D., Calvat P., Breton V., Reuillon R., Lazaro D., Legre Y., Donnarieix D.
Parallel processing letters ISSN 0129-6264

Monte Carlo simulations are increasingly used in medical physics. In scintigraphic imaging these simulations are used to model imaging systems and to develop and assess tomographic reconstruction algorithms and correction methods for improved image quantization. In radiotherapy-brachytherapy the goal is to evaluate accurately the dosimetry in complex phantoms and at interfaces of tissue, where analytic calculations have shown some limits. The main drawback of Monte Carlo simulations is their high computing time. The aim of our research is to reduce the computing time by parallelizing a simulation on geographically distributed processors. The method is based on the parallelization of the Random Number Generator (RNG) used in Monte Carlo simulations. The long serial of numbers used by the sequential simulation is split. Once the partitioning is done, a software application allows the user to generate automatically the files describing each simulation part. Finally, another software executes them on the DataGrid testbed using an API. All these steps have been made transparent for the user by providing a web page asking the user for all the parameters necessary to launch the simulation and retrieve results. Different tests have been done in order to show first, the reliability of the physical results obtained by concatenation of parallelized output data and secondly the time gained for jobs execution.

       Parallelization of {Monte Carlo} Simulations and Submission to a Grid Environment (PDF)

Grid Standard Services Development : feedback
authors: Reynaud, S.; Hernandez, F.
JRES 2003

Since 1995 and every 2 years, CRU, RENATER and UREC organize JRES Net days. JRES 2003 took place from november 17th to november 21st at Lille's Grand Palais.

       Service de grille standardisés : retour d'expérience (PDF - french)

LCG-2 Deployment at CC-IN2P3 : Status report
Presented at NA4 Biomedical Applications Meeting
Creatis - Tuesday, june 8th.
Presented by Fabio Hernandez

       LCG2 Status Report (PDF - English)


CIC Homepage    Site Map    Write to Webmasters