@InProceedings{nitzberg:collective,
  author = {Bill Nitzberg and Virginia Lo},
  title = {Collective Buffering: Improving Parallel {I/O} Performance},
  booktitle = {Proceedings of the Sixth IEEE International Symposium on High
  Performance Distributed Computing},
  year = {1997},
  month = {August},
  pages = {148--157},
  publisher = {IEEE Computer Society Press},
  address = {Portland, OR},
  later = {nitzberg:bcollective},
  keywords = {parallel I/O, collective I/O, pario-bib},
  abstract = {"Parallel I/O" is the support of a single parallel application
  run on many nodes; application data is distributed among the nodes, and is
  read or written to a single logical file, itself spread across nodes and
  disks. Parallel I/O is a mapping problem from the data layout in node memory
  to the file layout on disks. Since the mapping can be quite complicated and
  involve significant data movement, optimizing the mapping is critical for
  performance. \par We discuss our general model of the problem, describe four
  Collective Buffering algorithms we designed, and report experiments testing
  their performance on an Intel Paragon and an IBM SP2 both housed at NASA Ames
  Research Center. Our experiments show improvements of up to two order of
  magnitude over standard techniques and the potential to deliver peak
  performance with minimal hardware support.}
}