@InProceedings{acharya:tuning,
  author = {Anurag Acharya and Mustafa Uysal and Robert Bennett and Assaf
  Mendelson and Michael Beynon and Jeffrey K. Hollingsworth and Joel Saltz and
  Alan Sussman},
  title = {Tuning the Performance of {I/O} Intensive Parallel Applications},
  booktitle = {Proceedings of the Fourth Workshop on Input/Output in Parallel
  and Distributed Systems},
  year = {1996},
  month = {May},
  pages = {15--27},
  publisher = {ACM Press},
  address = {Philadelphia},
  keywords = {parallel I/O, filesystem workload, parallel application,
  pario-bib},
  abstract = {Getting good I/O performance from parallel programs is a critical
  problem for many application domains. In this paper, we report our experience
  tuning the I/O performance of four application programs from the areas of
  satellite-data processing and linear algebra. After tuning, three of the four
  applications achieve application-level I/O rates of over 100 MB/s on 16
  processors. The total volume of I/O required by the programs ranged from
  about 75 MB to over 200 GB. We report the lessons learned in achieving high
  I/O performance from these applications, including the need for code
  restructuring, local disks on every node and knowledge of future I/O
  requests. We also report our experience on achieving high performance on
  peer-to-peer configurations. Finally, we comment on the necessity of complex
  I/O interfaces like collective I/O and strided requests to achieve high
  performance.}
}