@TechReport{Dartmouth:TR97-303,
  author = {Thomas H. Cormen and Jake Wegmann and David M. Nicol},
  title = {{Multiprocessor Out-of-Core FFTs with Distributed Memory and Parallel Disks}},
  institution = {Dartmouth College, Computer Science},
  address = {Hanover, NH},
  number = {PCS-TR97-303},
  year = {1997},
  month = {January},
  URL = {http://www.cs.dartmouth.edu/reports/TR97-303.ps.Z},
  comment = {
    Revised version appeared in IOPADS '97.
  },
  abstract = {
    This paper extends an earlier out-of-core Fast Fourier Transform (FFT)
    method for a uniprocessor with the Parallel Disk Model (PDM) to use
    multiple processors.  Four out-of-core multiprocessor methods are
    examined.  Operationally, these methods differ in the size of
    "mini-butterfly" computed in memory and how the data are organized on
    the disks and in the distributed memory of the multiprocessor.  The
    methods also perform differing amounts of I/O and communication.  Two
    of them have the remarkable property that even though they are
    computing the FFT on a multiprocessor, all interprocessor
    communication occurs outside the mini-butterfly computations.
    Performance results on a small workstation cluster indicate that
    except for unusual combinations of problem size and memory size, the
    methods that do not perform interprocessor communication during the
    mini-butterfly computations require approximately 86% of the time of
    those that do.  Moreover, the faster methods are much easier to
    implement.
  }
}