@InProceedings{mowry:prefetch,
  author = {Todd C. Mowry and Angela K. Demke and Orran Krieger},
  title = {Automatic compiler-inserted {I/O} prefetching for out-of-core
  applications},
  booktitle = {Proceedings of the 1996 Symposium on Operating Systems Design
  and Implementation},
  year = {1996},
  month = {October},
  pages = {3--17},
  publisher = {USENIX Association},
  later = {mowry:jprefetch},
  URL =
  {http://www.usenix.org/publications/library/proceedings/osdi96/mowry.html},
  keywords = {compiler, prefetch, parallel I/O, pario-bib},
  abstract = {Current operating systems offer poor performance when a numeric
  application's working set does not fit in main memory. As a result,
  programmers who wish to solve ``out-of-core'' problems efficiently are
  typically faced with the onerous task of rewriting an application to use
  explicit I/O operations (e.g., read/write). In this paper, we propose and
  evaluate a fully-automatic technique which liberates the programmer from this
  task, provides high performance, and requires only minimal changes to current
  operating systems. In our scheme, the compiler provides the crucial
  information on future access patterns without burdening the programmer, the
  operating system supports non-binding prefetch and release hints for managing
  I/O, and the operating system cooperates with a run-time layer to accelerate
  performance by adapting to dynamic behavior and minimizing prefetch overhead.
  This approach maintains the abstraction of unlimited virtual memory for the
  programmer, gives the compiler the flexibility to aggressively move
  prefetches back ahead of references, and gives the operating system the
  flexibility to arbitrate between the competing resource demands of multiple
  applications. We have implemented our scheme using the SUIF compiler and the
  Hurricane operating system. Our experimental results demonstrate that our
  fully-automatic scheme effectively hides the I/O latency in out-of-core
  versions of the entire NAS Parallel benchmark suite, thus resulting in
  speedups of roughly twofold for five of the eight applications, with two
  applications speeding up by threefold or more.},
  comment = {Best Paper Award.}
}