@Article{choudhary:jmanagement,
  author = {A. Choudhary and M. Kandemir and J. No and G. Memik and X. Shen and
  W. Liao and H. Nagesh and S. More and V. Taylor and R. Thakur and and R.
  Stevens},
  title = {Data Management for Large-Scale Scientific Computations in High
  Performance Distributed Systems},
  journal = {Cluster Computing},
  year = {2000},
  volume = {3},
  number = {1},
  pages = {45--60},
  publisher = {Baltzer Science Publishers},
  earlier = {choudhary:management},
  URL = {http://www.baltzer.nl/cluster/contents/2000/3-1.html#clus067},
  keywords = {cluster computing, scientific computing, parallel I/O, data
  management, pario-bib},
  abstract = {With the increasing number of scientific applications
  manipulating huge amounts of data, effective high-level data management is an
  increasingly important problem. Unfortunately, so far the solutions to the
  high-level data management problem either require deep understanding of
  specific storage architectures and file layouts (as in high-performance file
  storage systems) or produce unsatisfactory I/O performance in exchange for
  ease-of-use and portability (as in relational DBMSs). In this paper we
  present a novel application development environment which is built around an
  active meta-data management system (MDMS) to handle high-level data in an
  effective manner. The key components of our three-tiered architecture are
  user application, the MDMS, and a hierarchical storage system (HSS). Our
  environment overcomes the performance problems of pure database-oriented
  solutions, while maintaining their advantages in terms of ease-of-use and
  portability. The high levels of performance are achieved by the MDMS, with
  the aid of user-specified, performance-oriented directives. Our environment
  supports a simple, easy-to-use yet powerful user interface, leaving the task
  of choosing appropriate I/O techniques for the application at hand to the
  MDMS. We discuss the importance of an active MDMS and show how the three
  components of our environment, namely the application, the MDMS, and the HSS,
  fit together. We also report performance numbers from our ongoing
  implementation and illustrate that significant improvements are made possible
  without undue programming effort.}
}