@TechReport{bordawekar:stencil-tr,
  author = {Rajesh Bordawekar and Alok Choudhary and J. Ramanujam},
  title = {Automatic Optimization of Communication in Out-of-core Stencil
  Codes},
  year = {1995},
  month = {November},
  number = {CACR-114},
  institution = {Scalable I/O Initiative, Center of Advanced Computing
  Research, California Insititute of Technology},
  later = {bordawekar:stencil},
  keywords = {compiler, parallel I/O, pario-bib},
  abstract = {In this paper, we describe a technique for optimizing
  commununication for out-of-core distributed memory stencil problems. In these
  problems, communication may require both inter-processor communication and
  file I/O. We show that in certain cases, extra file I/O incurred in
  communication can be completely eliminated by reordering in-core
  computations. The in-core computation pattern is decided by: (1) how the
  out-of-core data distributed into in-core slabs (tiling) and (2) how the
  slabs are accessed. We show that a compiler using the stencil and processor
  information can choose the tiling parameters and schedule the tile accesses
  so that the extra file I/O is eliminated and overall performance is
  improved.}
}