@InProceedings{gross:io,
  author = {Thomas Gross and Peter Steenkiste},
  title = {Architecture Implications of High-speed {I/O} for Distributed-Memory
  Computers},
  booktitle = {Proceedings of the 8th ACM International Conference on
  Supercomputing},
  year = {1994},
  month = {July},
  pages = {176--185},
  publisher = {ACM Press},
  address = {Manchester, UK},
  keywords = {parallel I/O, parallel architecture, networking, pario-bib},
  comment = {They examine the characteristics of a system that has I/O nodes
  which interface between the internal interconnection network of a
  distributed-memory MIMD machine and some external network, such as HIPPI.
  They build a simple model to show how different components affect the I/O
  throughput. They show the performance of their iWarp-HIPPI interface. They
  conclude that the I/O nodes must have sufficient memory bandwidth to support
  multiple data streams coming from several compute nodes, being combined into
  a single faster external network, or vice versa. They need to support
  scatter/gather, because the data is often distributed in small pieces. For
  the same reason, they need to have low per-message overhead. The internal
  network routing must allow multiple paths between compute nodes and the I/O
  nodes, to avoid congestion.}
}