GARUDA: Pan-Indian distributed e-infrastructure for compute-data intensive collaborative science

摘要

GARUDA is a nation-wide grid of computational nodes, mass storage and scientific instruments with an aim to provide technological advancements required to enable compute-data intensive, collaborative applications for the twenty-first century. From a Proof-of-Concept, the GARUDA has evolved to an operational grid, aggregating nearly 70TF-15TB compute–storage power, via high-speed National Knowledge Network and hosts a stack of middleware and tools to enable hundreds of users from diverse communities like life science, earth science, computer aided engineering, material science, etc. Evolution and confluence of research and technologies has led to the maturity of GARUDA grid: there have been addition of several hundred CPUs, large data stores, standardization of grid middleware, research on interoperability between grids and participation from varied application communities that have made significant impact to GARUDA. The GARUDA partner institutes are using this e-infrastructure to grid enable applications of societal and national importance. The authors in this paper present the manner of building a nation-wide operational grid and its evolution, its deliverables, architecture and applications.