Workflow Global Computing with YML

In this paper we propose a framework dedicated to the development and the execution of parallel applications over large scale global computing platforms. A workflow programming environment will be introduced, based on a new workflow language YvetteML and a Human-GRID middleware interface called YML. This language allows description of different kind of components to be allocated to GRID resources. Depending of the different targeted resources, the components may be associated to computation, data migration or other resource controls. YML is designed to have several back-ends for different middleware, as a well-designed front end is developed independently of any dedicated middleware. In order to make the framework immediately useful, YML comes with pre-configured interfaces to some numerical routines and a numerical library for iterative linear algebra methods. We will present experimentations done on some large scale platforms using a peer to peer middleware with a numerical application case study.