@InProceedings{gupta:generating,
  author = {Sandeep K. S. Gupta and Zhiyong Li and John H. Reif},
  title = {Generating Efficient Programs for Two-level Memories from
  Tensor-Products},
  booktitle = {Proceedings of the Seventh IASTED/ISMM International Conference
  on Parallel and Distributed Computing and Systems},
  year = {1995},
  month = {October},
  pages = {510--513},
  address = {Washington, D.C.},
  URL = {ftp://ftp.cs.duke.edu/pub/zli/papers/pdcs95.ps.gz},
  keywords = {parallel I/O algorithm, pario-bib},
  abstract = {This paper presents a framework for synthesizing efficient
  out-of-core programs for block recursive algorithms such as the fast Fourier
  transform (FFT) and Batcher's bitonic sort. The block recursive algorithms
  conside red in this paper are described using tensor (Kronecker) product and
  other matrix operations. The algebraic properties of the matrix
  representation are used to derive efficient out-of-core programs. These
  programs are targeted towards a two-level disk model which allows HPF
  supported cyclic(B) data distribution on a disk array. The effectiveness of
  our approach is demonstrated through an example out-of-core FFT program
  implemented on a work-station.}
}