ABSTRACT
The deployment of a general purpose utility grid can aggregate otherwise disparate and autonomous resources and provide access to grid technology for researchers, faculty and students for learning about grids, testing grid capabilities, deploying applications. Using inter-institutional collaboration to build cooperative, grid computing for all can advance grid technology.Grids for "big science" or specific applications tend to be deployed for long term needs, with significant investment of project specific resources, and perhaps with less concern for integration with enterprise infrastructures. Indeed, such big science grids are "enterprises" in their own right, establishing solutions that sit as a layer of services above, outside and distinct from a researcher's locally affiliated enterprise. There is a need for a utility grid that is differentiated from such application specific grids. Deploying such a utility grid would be a step toward the vision described by Foster et alia in The Physiology of the Grid: An Open Grid Services Architecture for Distributed Systems Integration - serving the "need to integrate services across distributed, heterogeneous, dynamic 'virtual organizations' formed from the disparate resources within a single enterprise and/or from external resource sharing and service provider relationships."Work begun as part of the NSF Middleware Initiative Integration Testbed Program has evolved from deploying individual campus grids to the work of SURAGrid. SURAGrid is engaging a broader collaboration of researchers, educators and students across the southeast and beyond to create a model of cooperative grid computing infrastructure and disseminate exemplars of technology, best practices, policy solutions and grid applications.
Grid computing for all
Recommendations
MGC middleware for grid computing: the Globus Toolkit
ACAI '11: Proceedings of the International Conference on Advances in Computing and Artificial IntelligenceGrid computing has made substantial advances during the last decade. A major concern in Grid environments is dealing with the high degree of heterogeneity of resources that can range from laptops and PCs to supercomputers. The unified virtual view of ...
Comments