@InProceedings{li:synthesizing,
  author = {Zhiyong Li and John H. Reif and Sandeep K. S. Gupta},
  title = {Synthesizing Efficient Out-of-Core Programs for Block Recursive
  Algorithms using Block-Cyclic Data Distributions},
  booktitle = {Proceedings of the 1996 International Conference on Parallel
  Processing},
  year = {1996},
  month = {August},
  pages = {II:142--149},
  publisher = {IEEE Computer Society Press},
  address = {St. Charles, IL},
  earlier = {li:synthesizing-tr},
  keywords = {parallel I/O algorithm, pario-bib},
  abstract = {This paper presents a framework for synthesizing I/O-efficient
  out-of-core programs for block recursive algorithms, such as the fast Fourier
  transform and matrix transpositions. the programs are synthesized from tensor
  (Kronecker) product representations of algorithms. These programs are
  optimized for a striped two-level memory model where in the out-of-core data
  can have block-cyclic distributions on multiple disks.}
}