@InProceedings{chen:panda-model,
  author = {Y. Chen and M. Winslett and S. Kuo and Y. Cho and M. Subramaniam
  and K. E. Seamons},
  title = {Performance Modeling for the {Panda} Array {I/O} Library},
  booktitle = {Proceedings of Supercomputing '96},
  year = {1996},
  month = {November},
  publisher = {ACM Press and IEEE Computer Society Press},
  URL = {http://www.supercomp.org/sc96/proceedings/SC96PROC/YING/INDEX.HTM},
  keywords = {performance modeling, parallel I/O, pario-bib},
  abstract = {We present an analytical performance model for Panda, a library
  for synchronized i/o of large multidimensional arrays on parallel and
  sequential platforms, and show how the Panda developers use this model to
  evaluate Panda's parallel i/o performance and guide future Panda development.
  The model validation shows that system developers can simplify performance
  analysis, identify potential performance bottlenecks, and study the design
  trade-offs for Panda on massively parallel platforms more easily than by
  conducting empirical experiments. More importantly, we show that the outputs
  of the performance model can be used to help make optimal plans for handling
  application i/o requests, the first step toward our long-term goal of
  automatically optimizing i/o request handling in Panda.},
  comment = {On Web and CDROM only. They derive a detailed but fairly simple
  model of the Panda 2.0.5 parallel I/O library, by carefully enumerating the
  costs involved in a collective I/O operation. They measure Panda, AIX, and
  MPI to obtain parameters, and then they validate the model by comparison with
  the actual Panda implementation running a basic benchmark and an actual
  application. The model predicts the benchmark performance very well, and is
  as much as 20\% off on the performance of the application. They have embedded
  the performance model in a "simulator", which predicts the performance of a
  given sequence of collective I/O requests, and they plan to use it in future
  versions of Panda to formulate I/O plans by predicting the performance
  resulting from several different Panda parameter settings, and choosing the
  best.}
}