@Article{chen:tuning,
  author = {Ying Chen and Marianne Winslett},
  title = {Automated Tuning of Parallel {I/O} Systems: An Approach to Portable
  {I/O} Performance for Scientific Applications},
  journal = {IEEE Transactions on Software Engineering},
  year = {2000},
  month = {April},
  volume = {26},
  number = {4},
  pages = {362--383},
  keywords = {parallel I/O, pario-bib},
  abstract = {Parallel I/O systems typically consist of individual processors,
  communication networks, and a large number of disks. Managing and utilizing
  these resources to meet performance, portability, and usability goals of high
  performance scientific applications has become a significant challenge. For
  scientists, the problem is exacerbated by the need to retune the I/O portion
  of their code for each supercomputer platform where they obtain access. We
  believe that a parallel I/O system that automatically selects efficient I/O
  plans for user applications is a solution to this problem. The authors
  present such an approach for scientific applications performing collective
  I/O requests on multidimensional arrays. Under our approach, an optimization
  engine in a parallel I/O system selects high quality I/O plans without human
  intervention, based on a description of the application I/O requests and the
  system configuration. To validate our hypothesis, we have built an optimizer
  that uses rule based and randomized search based algorithms to tune parameter
  settings in Panda, a parallel I/O library for multidimensional arrays. Our
  performance results obtained from an IBM SP using an out-of-core matrix
  multiplication application show that the Panda optimizer is able to select
  high quality I/O plans and deliver high performance under a variety of system
  configurations with a small total optimization overhead.}
}