Abstract:The TeraGrid is an advanced, integrated, nationally-distributed, open, user-driven, US cyberinfrastructure that enables and supports leading edge scientific discovery and promotes science and technology education. It comprises supercomputing resources, storage systems, visualization resources, data collections, software, and science gateways, integrated by software systems and high bandwidth networks, coordinated through common policies and operations, and supported by technology experts. This paper discusses the TeraGrid itself, examples of the science that is occurring on the TeraGrid today, and applications that are being developed to perform science in the future. Key words: computational science applications, high performance computing, grid computing, production grid infrastructure *Steven Manos was a Research Fellow at University College London while this work was conducted CMST SI(1) 81-97 (2010
82effort to build and deploy the world's largest, fastest, most comprehensive, distributed infrastructure for general scientific research. The initial TeraGrid was homogeneous and very "griddy", with users foreseen to be running on multiple systems, both because their codes could run "anywhere", and because in some cases, multiple systems would be needed to support the large runs that were desired. The software that made up the TeraGrid was a set of identical packages on all systems. The TeraGrid has since expanded in capability and number of resource providers. This introduced heterogeneity and thus added complexity to the grid ideals of the initial DTF, as the common software no longer could be completely identical. This led to the concept of common interfaces, with potentially different software underneath the interfaces. Additionally, the users of national center supercomputers were merged into TeraGrid, which led to TeraGrid increasing its focus on supporting these users and their traditional parallel/batch usage modes. The TeraGrid is freely available for US researchers, with allocations determined by a peer-review mechanism. The TeraGrid resources are generally at least 50% dedicated to TeraGrid. Roughly similar to the TeraGrid in terms of a continental-scale set of resources with a focus on HPC users is DEISA/PRACE in Europe, which is a set of national resources with some fractions provided to a set of European users, again determined through a review process. An alternative type of infrastructure is one that is more focused on high throughput computing (HTC), initially in high-energy physics, but increasingly in other domains as well. Filling this role in the US is Open Science Grid (OSG), and in Europe, Enabling Grids for E-sciencE (EGEE), which has recently been transformed into the European Grid Infrastructure (EGI). This paper discusses the TeraGrid itself (Section II), examples of the interesting current uses of the TeraGrid cyberinfrastructure for science (Section III), and examples of applications that are being developed to perform science on the TeraGrid in the future (Section IV) 1 .
...