@PhdThesis{thakur:thesis,
  author = {Rajeev Thakur},
  title = {{Runtime Support for In-Core and Out-of-Core Data-Parallel
  Programs}},
  year = {1995},
  month = {May},
  school = {Department of Electrical and Computer Engineering, Syracuse
  University},
  URL = {http://www.mcs.anl.gov/~thakur/papers/phd_thesis.ps},
  keywords = {parallel I/O, runtime library, pario-bib},
  abstract = {Distributed memory parallel computers or distributed computer
  systems are widely recognized as the only cost-effective means of achieving
  teraflops performance in the near future. However, the fact remains that they
  are difficult to program and advances in software for these machines have not
  kept pace with advances in hardware. This thesis addresses several issues in
  providing runtime support for in-core as well as out-of-core programs on
  distributed memory parallel computers. This runtime support can be directly
  used in application programs for greater efficiency, portability and ease of
  programming. It can also be used together with a compiler to translate
  programs written in a high-level data-parallel language like High Performance
  Fortran (HPF) to node programs for distributed memory machines. \par In
  distributed memory programs, it is often necessary to change the distribution
  of arrays during program execution. This thesis presents efficient and
  portable algorithms for runtime array redistribution. The algorithms have
  been implemented on the Intel Touchstone Delta and are found to scale well
  with the number of processors and array size. This thesis also presents
  algorithms for all-to-all collective communication on fat-tree and
  two-dimensional mesh interconnection topologies. The performance of these
  algorithms on the CM-5 and Touchstone Delta is studied extensively. A model
  for estimating the time taken by these algorithms on the basis of system
  parameters is developed and validated by comparing with experimental results.
  \par A number of applications deal with very large data sets which cannot fit
  in main memory, and hence have to be stored in files on disks, resulting in
  out-of-core programs. This thesis also describes the design and
  implementation of efficient runtime support for out-of-core computations.
  Several optimizations for accessing out-of-core data are presented. An
  Extended Two-Phase Method is proposed for accessing sections of out-of-core
  arrays efficiently. This method uses collective I/O and the I/O workload is
  divided among processors dynamically, depending on the access requests.
  Performance results obtained using this runtime support for out-of-core
  programs on the Touchstone Delta are presented.}
}