@Article{shen:data-management,
  author = {X. H. Shen and W. K. Liao and A. Chouldhary and G. Memik and M.
  Kandemir},
  title = {A high-performance application data environment for large-scale
  scientific computations},
  journal = {IEEE Transactions on Parallel and Distributed Systems},
  year = {2003},
  month = {December},
  volume = {14},
  number = {12},
  pages = {1262--1274},
  keywords = {data management, scientific applications, workflow, parallel file
  systems, pario-bib},
  abstract = {Effective high-level data management is becoming an important
  issue with more and more scientific applications manipulating huge amounts of
  secondary-storage and tertiary-storage data using parallel processors. A
  major problem facing the current solutions to this data management problem is
  that these solutions either require a deep understanding of specific data
  storage architectures and file layouts to obtain the best performance (as in
  high-performance storage management systems and parallel file systems), or
  they sacrifice significant performance in exchange for ease-of-use and
  portability (as in traditional database management systems). We discuss the
  design, implementation, and evaluation of a novel application development
  environment for scientific computations. This environment includes a number
  of components that make it easy for the programmers to code and run their
  applications without much programming effort and, at the same time, to
  harness the available computational and storage power on parallel
  architectures. (39 refs.)}
}