@InProceedings{seamons:compressed,
  author = {K. E. Seamons and M. Winslett},
  title = {A Data Management Approach for Handling Large Compressed Arrays in
  High Performance Computing},
  booktitle = {Proceedings of the Fifth Symposium on the Frontiers of Massively
  Parallel Computation},
  year = {1995},
  month = {February},
  pages = {119--128},
  URL = {http://bunny.cs.uiuc.edu/CADR/pubs/compression.ps},
  keywords = {parallel I/O, pario-bib},
  comment = {``This paper shows how compression can be used to speed up
  parallel i/o of large arrays. The current version of the paper focuses on
  improving write performance.'' They use chunked files like in
  seamons:interface but before writing they compress each chunk on its compute
  node, and after reading they decompress each chunk on its compute node.
  Presumably this is only useful when you plan to read back whole chunks. They
  find better performance for compressing in many cases, even when the
  compression time dominates the I/O time, because it reduces the I/O time so
  much. They found that the compression time and compression ratio can vary
  widely from chunk to chunk, leading to a tremendous load imbalance that
  unfortunately spoils some of the advanatages if all compute nodes must wait
  for the slowest to finish.}
}