@Article{garcia:expand-design,
  author = {F\'elix Garcia-Carballeira and Alejandro Calderon and Jesus
  Carretero and Javier Fernandez and Jose M. Perez},
  title = {The Design of the {Expand} Parallel File System},
  journal = {The International Journal of High Performance Computing
  Applications},
  year = {2003},
  volume = {17},
  number = {1},
  pages = {21--38},
  publisher = {Sage Science Press},
  URL =
  {http://www.sagepub.co.uk/JournalIssueAbstract.aspx?pid=105593&jiid=515697&jiaid=33121},
  keyword = {parallel file system, parallel I/O, pario-bib},
  abstract = {This article describes an implementation of MPI-IO using a new
  parallel file system, called Expand (Expandable Parallel File System), which
  is based on NFS servers. Expand combines multiple NFS servers to create a
  distributed partition where files are striped. Expand requires no changes to
  the NFS server and uses RPC operations to provide parallel access to the same
  file. Expand is also independent of the clients, because all operations are
  implemented using RPC and NFS protocols. Using this system, we can join
  heterogeneous servers (Linux, Solaris, Windows 2000, etc.) to provide a
  parallel and distributed partition. The article describes the design,
  implementation and evaluation of Expand with MPI-IO. This evaluation has been
  made in Linux clusters and compares Expand and PVFS.}
}

@Article{isaila:clusterfile,
  author = {Florin Isaila and Walter F. Tichy},
  title = {Clusterfile: a flexible physical layout parallel file system},
  journal = {Concurrency and Computation},
  year = {2003},
  volume = {15},
  number = {7/8},
  pages = {653--679},
  publisher = {Wiley},
  URL =
  {http://www3.interscience.wiley.com/cgi-bin/abstract/104524121/ABSTRACT},
  URLpdf =
  {http://www3.interscience.wiley.com/cgi-bin/fulltext/104524121/PDFSTART},
  keyword = {parallel file system, parallel I/O, pario-bib},
  abstract = {This paper presents Clusterfile, a parallel file system that
  provides parallel file access on a cluster of computers. We introduce a file
  partitioning model that has been used in the design of Clusterfile. The model
  uses a data representation that is optimized for multidimensional array
  partitioning while allowing arbitrary partitions. The paper shows how the
  file model can be employed for file partitioning into both physical subfiles
  and logical views. We also present how the conversion between two partitions
  of the same file is implemented using a general memory redistribution
  algorithm. We show how we use the algorithm to optimize non-contiguous read
  and write operations. The experimental results include performance
  comparisons with the Parallel Virtual File System (PVFS) and an MPI-IO
  implementation for PVFS.}
}

@Article{oldfield:restruct,
  author = {Ron Oldfield and David Kotz},
  title = {Improving data access for computational grid applications},
  journal = {Cluster Computing, The Journal of Networks, Software Tools and
  Applications},
  year = {2003},
  copyright = {the authors},
  note = {Accepted for publication},
  keyword = {parallel I/O, Grid computing, distributed computing, graph
  algorithms, pario-bib},
  abstract = {High-performance computing increasingly occurs on ``computational
  grids'' composed of heterogeneous and geographically distributed systems of
  computers, networks, and storage devices that collectively act as a single
  ``virtual'' computer. A key challenge in this environment is to provide
  efficient access to data distributed across remote data servers. Our parallel
  I/O framework, called Armada, allows application and data-set providers to
  flexibly compose graphs of processing modules that describe the distribution,
  application interfaces, and processing required of the dataset before
  computation. Although the framework provides a simple programming model for
  the application programmer and the data-set provider, the resulting graph may
  contain bottlenecks that prevent efficient data access. In this paper, we
  present an algorithm used to restructure Armada graphs that distributes
  computation and data flow to improve performance in the context of a
  wide-area computational grid.}
}