Science on a large scale

Abstract

The TeraGrid, the U.S. National Science Foundation's multi-year project to build a distributed national cyberinfrastructure, entered full production mode in the fall of 2004, providing a coordinated set of services for the science and engineering community. TeraGrid operates a unified user support infrastructure and software environment across its eight resource partner sites, which together provide more than 40 teraflops of computing capability and mass storage capability in the petabytes, linked by networks operating at tens of Gigabit/sec. This unified environment allows TeraGrid users to access storage and information resources as well as over a dozen major computing systems via a single allocation, either as stand-alone resources or as components of a distributed application using Grid software capabilities. Many lessons can be drawn from the dual pursuit of high performance and close integration. The next phase will be even more exciting, with the roll out of a wide range of science gateways and additional advanced applications. Science gateway projects are aimed at supporting access to TeraGrid via web portals, desktop applications or via other grids. An initial set of 10 gateways will address new scientific opportunities in fields from bioinformatics to nanotechnology as well as interoperation between TeraGrid and other Grid infrastructures. TeraGrid is also enabling an impressive array of large scale science applications, where researchers can perform complex simulations and manipulate enormous data sets in novel ways to gain new insights into research questions and societal problems, for example, finding the most efficient and least expensive ways to clean up groundwater pollution. Effort in these and other related areas will allow more researchers and educators access to TeraGrid capabilities and advance compatibility between TeraGrid and other major Grid deployments such as Open Science Grid, Network for Earthquake Engineering Simulation (NEES), and major European and Asian Grid deployments. © Springer-Verlag Berlin Heidelberg 2005.