@Article{cannataro:data-intensive,
  author = {Mario Cannataro and Domenico Talia and Pradip K. Srimani},
  title = {Parallel data intensive computing in scientific and commercial
  applications},
  journal = {Parallel Computing},
  year = {2002},
  month = {May},
  volume = {28},
  number = {5},
  pages = {673--704},
  publisher = {Elsevier Science},
  URL = {http://www.elsevier.com/gej-ng/10/35/21/60/57/28/abstract.html},
  keywords = {parallel application, parallel I/O, pario-bib},
  abstract = {Applications that explore, query, analyze, visualize, and, in
  general, process very large scale data sets are known as Data Intensive
  Applications. Large scale data intensive computing plays an increasingly
  important role in many scientific activities and commercial applications,
  whether it involves data mining of commercial transactions, experimental data
  analysis and visualization, or intensive simulation such as climate modeling.
  By combining high performance computation, very large data storage, high
  bandwidth access, and high- speed local and wide area networking, data
  intensive computing enhances the technical capabilities and usefulness of
  most systems. The integration of parallel and distributed computational
  environments will produce major improvements in performance for both
  computing intensive and data intensive applications in the future. The
  purpose of this introductory article is to provide an overview of the main
  issues in parallel data intensive computing in scientific and commercial
  applications and to encourage the reader to go into the more in-depth
  articles later in this special issue.}
}