@TechReport{poole:sio-survey,
  author = {James T. Poole},
  title = {Preliminary Survey of {I/O} Intensive Applications},
  year = {1994},
  number = {CCSF-38},
  institution = {Scalable I/O Initiative},
  address = {Caltech Concurrent Supercomputing Facilities, Caltech},
  URL = {http://www.cacr.caltech.edu/SIO/pubs/SIO_apps.ps},
  keywords = {parallel I/O, pario-bib, multiprocessor file system, file access
  pattern, checkpoint},
  comment = {Goal is to collect a set of representative applications from
  biology, chemistry, earth science, engineering, graphics, and physics, use
  performance-monitoring tools to analyze them, create templates and benchmarks
  that represent them, and then later to evaluate the performance of new I/O
  tools created by rest of the SIO initiative. Seem to be four categories of
  I/O needs: input, output, checkpoint, and virtual memory (``out-of-core''
  scratch space). Not all types are significant in all applications. (Two
  groups mention databases and the need to perform computationally complex
  queries.) Large input is typically raw data (seismic soundings, astronomical
  observations, satellite remote sensing, weather information). Sometimes there
  are real-time constraints. Output is often periodic, e.g., the state of the
  system every few timesteps; typically the volume would increase along with
  I/O capacity and bandwidth. Checkpointing is a common request; preferably
  allowing application to choose what and when to checkpoint, and definitely
  including the state of files. Many kinds of out-of-core: 1) temp files
  between passes (often written and read sequentially), 2) regular patterns
  like FFT, matrix transpose, solvers, and single-pass read/compute/write, 3)
  random access, e.g., to precomputed tables of integrals. Distinct differences
  in the ways people choose to divide data into files; sometimes all in one
  huge file, sometimes many ``small'' files (e.g., one per processor, one per
  timestep, one per region, etc.). Important: overlap of computation and I/O,
  independent access by individual processors. Not always important: ordering
  of records read or written by different processors, exposing the I/O model to
  the application writer. Units of I/O seem to be either (sub)matrices (1--5
  dimensions) or items in a collection of objects (100--10000 bytes each). Data
  sets varied up to 1~TB; bandwidth needs varied up to 1~GB/s. See also
  bagrodia:sio-character, choudhary:sio-language, bershad:sio-os.}
}