@TechReport{bordawekar:reorganize,
  author = {Rajesh Bordawekar and Alok Choudhary and Rajeev Thakur},
  title = {Data Access Reorganizations in Compiling Out-of-core Data Parallel
  Programs on Distributed Memory Machines},
  year = {1994},
  month = {September},
  number = {SCCS-622},
  institution = {NPAC},
  address = {Syracuse, NY 13244},
  earlier = {bordawekar:efficient},
  URL = {ftp://erc.cat.syr.edu/ece/choudhary/PASSION/access_reorg.ps.Z},
  keywords = {parallel I/O, compilation, pario-bib},
  comment = {Basically they give a case study of out-of-core matrix
  multiplication to emphasize that the compiler's choice of loop ordering and
  matrix distribution for in-core matmult is not a very good choice for
  out-of-core matmult, because it causes too much I/O. By reorganizing the data
  and the loops, they get much better performance. In this particular case
  there are known algorithms which they should have used. In general they make
  the point that the compiler should consider several organizations, and
  estimate their costs, before generating code. They don't propose anything
  more sophisticated than to try all the possible organizations.}
}