@InProceedings{bornstein:reshuffle,
  author = {C. Bornstein and P. Steenkiste},
  title = {Data Reshuffling in Support of Fast {I/O} For Distributed-Memory
  Machines},
  booktitle = {Proceedings of the Third IEEE International Symposium on High
  Performance Distributed Computing},
  year = {1994},
  month = {August},
  pages = {227--235},
  keywords = {parallel I/O, distributed memory, pario-bib},
  comment = {In a sense, this is about a two-phase technique for network I/O.
  They consider the problem of feeding a fast network interface (HIPPI) from a
  distributed-memory parallel machine (iWARP) in which the individual internal
  links are slower than the external network. So they get the processors to
  cooperate to reshuffle the data into a canonical layout that is convenient to
  send to the gateway node, and from there onto the external network.}
}