@InProceedings{pasquale:iowork,
  author = {Barbara K. Pasquale and George C. Polyzos},
  title = {A Static Analysis of {I/O} Characteristics of Scientific
  Applications in a Production Workload},
  booktitle = {Proceedings of Supercomputing '93},
  year = {1993},
  pages = {388--397},
  publisher = {IEEE Computer Society Press},
  address = {Portland, OR},
  keywords = {scientific computing, file access patterns, pario-bib},
  comment = {Analyzed one month of accounting records from Cray YMP8/864 in
  SDSC's production environment. Their base assumption is that scientific
  application I/O is regular and predictable, eg, repetitive periodic bursts,
  with distinct phases, repeating patterns, and sequential access. The goal is
  to characterize a set of I/O-intensive scientific applications and evaluate
  regularity of resource usage. They measure volumes and rates of applications
  and total system. Cumulative and average usage for each distinct non-system
  application. Most resource usage came from the 5\% of applications that were
  not system applications. ``Virtual I/O rate'' is the bytes transferred per
  CPU second, which is IMHO only a rough measure because sometimes I/O overlaps
  CPU time, and sometimes does not. They picked out long-running applications
  with a high virtual I/O rate. Top 50 applications had 71\% of bytes
  transferred and 10\% of CPU time. Of those, 4.66 MB/sec min, 131 MB/sec max.
  Of those they picked the ones executed most often. Cluster analysis showed
  only 1-2 clusters. Correlation between I/O and CPU time. Included in the
  parallel I/O bibliography because it is useful to that community, though they
  did not trace parallel workload.}
}