@TechReport{Dartmouth:TR2003-459,
  author = {Ron A. Oldfield},
  title = {{Efficient I/O for Computational Grid Applications}},
  institution = {Dartmouth College, Computer Science},
  address = {Hanover, NH},
  number = {TR2003-459},
  year = {2003},
  month = {May},
  URL = {http://www.cs.dartmouth.edu/reports/TR2003-459.ps.Z},
  comment = {
    This is a reformatted version of Ron Oldfield's Ph.D. dissertation. 
    Unlike the dissertation submitted to Dartmouth College, this version 
    is single-spaced, uses 11pt fonts, and is formatted specifically for
    double-sided printing. 
  },
  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. This dissertation explores some of the issues associated 
    with I/O for wide-area distributed computing and describes an I/O 
    system, called Armada, with the following features: a framework to 
    allow application and dataset providers to flexibly compose graphs 
    of processing modules that describe the distribution, application 
    interfaces, and processing required of the dataset before or after 
    computation; an algorithm to restructure application graphs to 
    increase parallelism and to improve network performance in a wide-area 
    network; and a hierarchical graph-partitioning scheme that deploys 
    components of the application graph in a way that is both beneficial 
    to the application and sensitive to the administrative policies of 
    the different administrative domains. Experiments show that 
    applications using Armada perform well in both low- and high-bandwidth 
    environments, and that our approach does an exceptional job of 
    hiding the network latency inherent in grid computing.
  }
}