Running Virtual Data Workflows on the Open Science Grid
The NSF-sponsored Grid Physics Network project \226 GriPhyN \226 couples four large-scale experiments in physics and astrophysics (ATLAS, CMS, LIGO, and SDSS)with a team of computer scientists, to create approaches to harness the Grid fordata intensive scientific collaborations. VDS - GriPhyN\222s Virtual Data Systemsoftware technology creates a \223Virtual Data Grid\224 which enables scientiststo leverage large-scale Grid resources with greater ease, creating a powerful environment for data analysis and management that facilitates discovery, collaboration, composition, and validation.
VDS enables scientists to easily create location-independent workflows that run across multiple sites and even multiple Grids, performing automated planning, data management, and failure recovery.
In this demonstration we will show workflows from three additional science projects, running across multiple sites of the new Open Science Grid as well as the NSF TeraGrid. The workflows are running science code from three different projects: The Genome Analysis and Database Update system (GADU) from the ArgonneComputational Biology Group; a functional-MRI workflow from the Dartmouth Brain Imaging Center, and the Montage workflow developed in collaboration between NASA, NVO, and ISI.
Supported by the National Science Foundation and the U.S. Department of Energy's Office of Science