@InProceedings{ghosh:pario,
  author = {Joydeep Ghosh and Bipul Agarwal},
  title = {Parallel {I/O} Subsystems for Distributed-Memory Multiprocessors},
  booktitle = {Proceedings of the Fifth International Parallel Processing
  Symposium},
  year = {1991},
  pages = {381--384},
  keywords = {multiprocessor file system, parallel I/O, pario-bib},
  comment = {They simulate a 128-node hypercube with 16 I/O nodes attached at
  uniformly distributed points. They compare two architectures: one with a
  separate I/O network, and another without a separate I/O network. When there,
  the extra network is used to route I/O packets from the originating I/O node
  to the I/O node closest to the destination processing node (or vice versa).
  They run simulations under workloads with differing amounts of locality, and
  experiment with different bandwidths for the links. They conclude that the
  extra network helps. But they never make the (proper, fair) comparison where
  the total network bandwidth is held constant. See also ghosh:hyper.}
}