@InProceedings{cho:fine-grained,
  author = {Yong Cho and Marianne Winslett and Ying Chen and Szu-wen Kuo},
  title = {Parallel {I/O} Performance of Fine Grained Data Distributions},
  booktitle = {Proceedings of the Seventh IEEE International Symposium on High
  Performance Distributed Computing},
  year = {1998},
  month = {July},
  pages = {163--170},
  publisher = {IEEE Computer Society Press},
  URL = {http://www.computer.org/proceedings/hpdc/8579/85790163abs.htm},
  keywords = {parallel I/O, pario-bib},
  abstract = {Fine grained data distributions are widely used to balance
  computational loads across compute processes in parallel scientific
  applications. When a fine grained data distribution is used in memory,
  performance of I/O intensive applications can be limited not only by disk
  speed but also by message passing, because a large number of small messages
  may be generated by the implementation strategy used in the underlying
  parallel file system or parallel I/O library. Combining (or packetizing) a
  set of small messages into a large message is generally known to speed up
  parallel I/O. However, overall I/O performance is affected not only by small
  messages but also by other factors like cyclic block size and interconnect
  characteristics. We describe small message combination and communication
  scheduling for fine grained data distributions in the Panda parallel I/O
  library and analyze I/O performance on parallel platforms having different
  interconnects: IBM SP2, IBM workstation cluster connected by FDDI and Pentium
  II cluster connected by Myrinet.}
}