@InProceedings{ma:buffering,
  author = {Xiasong Ma and Marianne Winslett and Jonghyun Lee and Shengke Yu},
  title = {Improving {MPI IO} Output Performance with Active Buffering Plus
  Threads},
  booktitle = {Proceedings of the International Parallel and Distributed
  Processing Symposium},
  year = {2003},
  month = {April},
  publisher = {IEEE Computer Society Press},
  URL = {http://drl.cs.uiuc.edu/pubs/abt.pdf},
  keywords = {parallel I/O, pario-bib},
  abstract = {Efficient collective output of intermediate results to secondary
  storage becomes more and more important for scientific simulations as the gap
  between process-ing power/interconnection bandwidth and the I/O sys-tem
  bandwidth enlarges. Dedicated servers can offload I/O from compute processors
  and shorten the execution time, but it is not always possible or easy for an
  appli-cation to use them. We propose the use of active buffer-ing with
  threads (ABT) for overlapping I/O with com-putation efficiently and flexibly
  without dedicated I/O servers. We show that the implementation of ABT in
  ROMIO, a popular implementation of MPI-IO, greatly reduces the
  application-visible cost of ROMIO s collec-tive write calls, and improves an
  application s overall performance by hiding I/O cost and saving implicit
  syn-chronization overhead from collective write operations. Further, ABT is
  high-level, platform-independent, and transparent to users, giving users the
  benefit of over-lapping I/O with other processing tasks even when the file
  system or parallel I/O library does not support asyn-chronous I/O.}
}