@TechReport{delrosario:two-phase-tr,
  author = {Juan Miguel del Rosario and Rajesh Bordawekar and Alok Choudhary},
  title = {Improving Parallel {I/O} Performance using a Two-Phase Access
  Strategy},
  year = {1993},
  number = {SCCS--406},
  institution = {NPAC at Syracuse University},
  later = {delrosario:two-phase},
  keywords = {parallel I/O, multiprocessor file system, pario-bib},
  comment = {They show performance measurements of various data distributions
  on an nCUBE and the Touchstone Delta, for reading matrix from a column-major
  file striped across disks, into some distribution across procs. Distributions
  that don't match the I/O distribution are really terrible, due to having
  more, smaller requests, and sometimes mismatching the stripe size (getting
  seg-like contention) or block size (reading partial blocks). They find it is
  better to read the file using the `best' distribution, then to reshuffle the
  data in memory. Big speedups.}
}