@Article{thakur:jext2phase,
  author = {Rajeev Thakur and Alok Choudhary},
  title = {{An Extended Two-Phase Method for Accessing Sections of Out-of-Core
  Arrays}},
  journal = {Scientific Programming},
  year = {1996},
  month = {Winter},
  volume = {5},
  number = {4},
  pages = {301--317},
  earlier = {thakur:ext2phase2},
  URL = {http://www.mcs.anl.gov/~thakur/papers/ext2ph.ps},
  keywords = {parallel I/O, pario-bib},
  abstract = {A number of applications on parallel computers deal with very
  large data sets that cannot fit in main memory. In such applications, data
  must be stored in files on disks and fetched into memory during program
  execution. Parallel programs with large out-of-core arrays stored in files
  must read/write smaller sections of the arrays from/to files. In this
  article, we describe a method for accessing sections of out-of-core arrays
  efficiently. Our method, the extended two-phase method, uses collective I/O:
  Processors cooperate to combine several I/O requests into fewer larger
  granularity requests, reorder requests so that the file is accessed in proper
  sequence, and eliminate simultaneous I/O requests for the same data. In
  addition, the I/O workload is divided among processors dynamically, depending
  on the access requests. We present performance results obtained from two real
  out-of-core parallel applications---matrix multiplication and a Laplace's
  equation solver---and several synthetic access patterns, all on the Intel
  Touchstone Delta. These results indicate that the extended two-phase method
  significantly outperformed a direct (noncollective) method for accessing
  out-of-core array sections.}
}