L'équipe ATLAS (INRIA) - IDC (LIRMM) vous invite au séminaire suivant :

Jeudi 14 octobre 2010 à 10h30
Salle du conseil, LIRMM

The role of provenance in scientific workflows – a high performance approach

Marta Mattoso, Federal University of Rio de Janeiro (UFRJ), Brazil.

Résumé
One of the main advantages of using a scientific workflow management system (SWfMS) to orchestrate data flows among scientific activities is to control and register the whole workflow execution. The execution of activities within a workflow with high performance computing (HPC) presents challenges in SWfMS execution control. Remote execution control and provenance registry of the parallel activities is a challenge to the SWfMS. In this talk we will address the life cycle of a scientific experiment and the main challenges to support it. We will also discuss problems and directions towards supporting workflow design and provenance management combined to MTC (Many-task computing). We will present the Hydra middleware that aims at providing a bridge between SWfMS and HPC. Hydra provides a set of components to be included on the workflow specification of any SWMfS to control parallelization of activities as MTC. In addition, these components gather provenance data during remote parallel workflow execution. Through these components, an MTC parallelization strategy can be registered, reused, and provenance may be uniformly gathered.
Hydra aims to reduce the complexity involved in designing and managing activity/workflow parallel executions within scientific experiments. We have evaluated Hydra in numerical methods for the oil industry as well as in bioinformatics workflows. Experimental results show that a systematic approach for distributing parallel activities is viable, sparing scientist time and diminishing operational errors, with the additional benefits of distributed provenance support.