@Article{mackay:groundwater,
  author = {David Mackay and G. Mahinthakumar and Ed D'Azevedo},
  title = {A Study of {I/O} in a Parallel Finite Element Groundwater Transport
  Code},
  journal = {The International Journal of High Performance Computing
  Applications},
  year = {1998},
  month = {Fall},
  volume = {12},
  number = {3},
  pages = {307--319},
  keywords = {parallel I/O application, pario-bib},
  abstract = {A parallel finite element groundwater transport code is used to
  compare three different strategies for performing parallel I/O: (1) have a
  single processor collect data and perform sequential I/O in large blocks, (2)
  use variations of vendor specific I/O extensions (3) use the EDONIO I/O
  library. Each processor performs many writes of one to four kilobytes to
  reorganize localdata in a global shared file. Our findings suggest having a
  single processor collect data and perform large block-contiguous operations
  may be quite efficient and portable for up to 32 processor configurations.
  This approach does not scale well for a larger number of processors since the
  single processor becomes a bottleneck for gathering data. The effective
  application I/O rate observed, which includes times for opening and closing
  files, is only a fraction of the peak device read/write rates. Some form of
  data redistribution and buffering in remote memory as performed in EDONIO may
  yield significant improvements for non-contiguous data I/O access patterns
  and short requests. Implementors of parallel I/O systems may consider some
  form of buffering as performed in EDONIO to speed up such I/O requirements.},
  comment = {In a Special Issue on I/O in Parallel Applications, volume 12,
  numbers 3 and 4.}
}