@InProceedings{schulz:semantic,
  author = {Martin Schulz and Daniel A. Reed},
  title = {Using Semantic Information to Guide Efficient I/O on Clusters},
  booktitle = {Proceedings of the Eleventh IEEE International Symposium on High
  Performance Distributed Computing},
  year = {2002},
  pages = {135--142},
  publisher = {IEEE Computer Society Press},
  address = {Edinburgh, Scotland},
  keywords = {I/O, data distribution, medical imaging application, parallel
  I/O, pario-bib},
  comment = {The paper describes DIOM (Distributed I/O management), a system to
  manage data distributed to local disks of a cluster of workstations. The
  distribution process uses semantic information from both the data set and the
  application to decide how to distribute the data. The data is stored using a
  self-describing format (similar to HDF). The description of the data is
  either stored in a file header, or it is part of a central repository (format
  identified by file suffix). DIOM decides how to distribute the data based on
  the application-supplied splitting-pattern , of which there are three types:
  single (copy all data to a single node), block (divide data evenly between
  the nodes), round (stripe blocks in a round-robin fashion). Parameters such
  as stripe size, initial node, etc, are defined by the app.}
}