Abstract

One of the hallmarks of current science experiments is the large volume of data that must be managed. For example, next generation particle physics experiments will generate petabytes of data per year. These data sets form important community resources, so not only must be manage to store and process this data, but we must be able to share it as well. In this talk, I will introduce the concept of data grids, a distributed grid infrastructure for sharing and managing large data sets. Using several examples, I will present a data grid architecture and illustrate how it can be used to address a number of current applications.

Date

2001

Authors

Carl Kesselman

Conference

Applied Parallel Computing. New Paradigms for HPC in Industry and Academia: 5th International Workshop, PARA 2000 Bergen, Norway, June 18–20, 2000 Proceedings 5

Pages

17-17

Publisher

Springer Berlin Heidelberg