@Misc{messerli:jimage,
  author = {V. Messerli and S. Vetsch and O. Figueiredo and B. Gennart and R.
  D. Hersch},
  title = {Parallelizing {I/O} Intensive Image Access \& Processing
  Applications},
  year = {1998},
  howpublished = {Submitted to IEEE Concurrency},
  keyword = {parallel I/O, image processing, parallel computing, parallel I/O
  application, pario-bib},
  comment = {See also gennart:CAP, messerli:tomographic, vetsch:visiblehuman.}
}

@InProceedings{messerli:tomographic,
  author = {V. Messerli, B. Gennart, R.~D. Hersch},
  title = {Performances of the {PS$^2$} Parallel Storage and Processing System
  for Tomographic Image Visualization},
  booktitle = {Proceedings of the Seventeenth International Conference on
  Distributed Computer Systems},
  year = {1997},
  month = {December},
  pages = {514--522},
  publisher = {IEEE Computer Society Press},
  address = {Seoul, Korea},
  URL = {http://diwww.epfl.ch/w3lsp/pub/publications/ps2/potppsapsftiv.html},
  keyword = {parallel computing, parallel I/O, parallel I/O application, image
  processing, pario-bib},
  abstract = {We propose a new approach for developing parallel I/O-
  andcompute-intensive applications. At a high level of abstraction, a macro
  data flow description describes how processing and disk access operations are
  combined. This high-level description (CAP) is precompiled into compilable
  and executable C++ source language. Parallel file system components specified
  by CAP are offered as reusable CAP operations. Low-level parallel file system
  components can, thanks to the CAP formalism, be combined with processing
  operations in order to yield efficient pipelined parallel I/O and compute
  intensive programs. The underlying parallel system is based on commodity
  components (PentiumPro processors, Fast Ethernet) and runs on top of
  WindowsNT. The CAP-based parallel program development approach is applied to
  the development of an I/O and processing intensive tomographic 3D image
  visualization application. Configurations range from a single PentiumPro
  1-disk system to a four PentiumPro 27-disk system. We show that performances
  scale well when increasing the number of processors and disks. With the
  largest configuration, the system is able to extract in parallel and project
  into the display space between three and four 512x512 images per second. The
  images may have any orientation and are extracted from a 100 MByte 3D
  tomographic image striped over the available set of disks.},
  comment = {See also messerli:jimage, gennart:CAP, vetsch:visiblehuman.}
}

@TechReport{thakur:mpi-io-implement-tr,
  author = {Rajeev Thakur and William Gropp and Ewing Lusk},
  title = {On Implementing {MPI-IO} Portably and with High Performance},
  year = {1998},
  month = {October},
  number = {ANL/MCS-P732-1098},
  institution = {Mathematics and Computer Science Division, Argonne National
  Laboratory},
  later = {thakur:mpi-io-implement},
  URL = {http://www.mcs.anl.gov/~thakur/papers/mpio-impl.ps.gz},
  keyword = {parallel I/O, multiprocessor file system interface, pario-bib},
  abstract = {We discuss the issues involved in implementing MPI-IO portably on
  multiple machines and file systems and also achieving high performance. One
  way to implement MPI-IO portably is to implement it on top of the basic Unix
  I/O functions (open, lseek, read, write, and close), which are themselves
  portable. We argue that this approach has limitations in both functionality
  and performance. We instead advocate an implementation approach that combines
  a large portion of portable code and a small portion of code that is
  optimized separately for different machines and file systems. We have used
  such an approach to develop a high-performance, portable MPI-IO
  implementation, called ROMIO.\par In addition to basic I/O functionality, we
  consider the issues of supporting other MPI-IO features, such as 64-bit file
  sizes, noncontiguous accesses, collective I/O, asynchronous I/O, consistency
  and atomicity semantics, user-supplied hints, shared file pointers, portable
  data representation, file preallocation, and some miscellaneous features. We
  describe how we implemented each of these features on various machines and
  file systems. The machines we consider are the HP Exemplar, IBM SP, Intel
  Paragon, NEC SX-4, SGI Origin2000, and networks of workstations; and the file
  systems we consider are HP HFS, IBM PIOFS, Intel PFS, NEC SFS, SGI XFS, NFS,
  and any general Unix file system (UFS). \par We also present our thoughts on
  how a file system can be designed to better support MPI-IO. We provide a list
  of features desired from a file system that would help in implementing MPI-IO
  correctly and with high performance.}
}

@Misc{vetsch:visiblehuman,
  author = {S. Vetsch and V. Messerli and O. Figueiredo and B. Gennart and R.D.
  Hersch and L. Bovisi and R. Welz and L. Bidaut and O. Ratib},
  title = {Visible Human Slice Server},
  year = {1998},
  howpublished = {http://visiblehuman.epfl.ch/},
  note = {A web site giving access to 2D views of a 3D scan of a human body.},
  URL = {http://visiblehuman.epfl.ch/},
  keyword = {image processing, parallel I/O, pario-bib},
  abstract = {The computer scientists of EPFL (Prof. R.D. Hersch and his
  staff), in collaboration with the Geneva Hospitals and WDS Technologies SA,
  have developed a parallel image server to extract image slices of the Visible
  Human from any orientation. This 3D dataset originates from a prisoner
  sentenced to death who offered his body to science. The dead body was frozen
  and then cut and digitized into 1 mm horizontally spaced slices by the
  National Library of Medicine, Bethesda-Maryland and the University of
  Colorado, USA. The total volume of all slices represents a size of 13 Gbyte
  of data.},
  comment = {Very cool. See also gennart:CAP, messerli:tomographic,
  messerli:jimage.}
}