@Article{tsujita:mpi-io,
  author = {Yuichi Tsujita},
  title = {Effective nonblocking {MPI-I/O} in remote {I/O} operations using a
  multithreaded mechanism},
  journal = {Lecture Notes in Computer Science},
  booktitle = {2nd International Symposium on Parallel and Distributed
  Processing and Applications; December 13-15, 2004; Hong Kong, PEOPLES R
  CHINA},
  editor = {Cao, J; Yang, LT; Guo, M; Lau, F},
  year = {2004},
  month = {November},
  volume = {3358},
  pages = {34--43},
  institution = {Kinki Univ, Fac Engn, Dept Elect Engn \& Comp Sci,
  Higashihiroshima, Hiroshima 7392116, Japan},
  publisher = {SPRINGER-VERLAG BERLIN},
  copyright = {(c)2005 The Thomson Corporation},
  URL =
  {http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=3358&spage=34},
  keywords = {stampi, MPI-I/O, dynamic process creation, multithreaded, overlap
  computation and I/O, pario-bib},
  abstract = {A flexible intermediate library named Stampi realizes seamless
  MPI operations on interconnected parallel computers. Dynamic process creation
  and MPI-I/O operations both inside a computer and among computers are
  available with it. MPI-I/O operations to a remote computer are realized by
  MPI-I/O processes of the Stampi library which are invoked on a remote
  computer using a vendor-supplied MPI-I/O library. If the vendor-supplied one
  is not available, a single MPI-I/O process is invoked on a remote computer,
  and it uses UNIX I/O functions instead of the vendor-supplied one. In
  nonblocking MPI-I/O functions with multiple user processes, the single
  MPI-I/O process carries out I/O operations required by the processes
  sequentially. This results in small overlap of computation by the user
  processes with I/O operations by the MPI-I/O process. Therefore performance
  of the nonblocking functions is poor with multiple user processes. To realize
  effective I/O operations, a Pthreads library has been implemented in the
  MPI-I/O mechanism, and multi-threaded I/O operations have been realized. The
  newly implemented MPI-I/O mechanism has been evaluated on inter-connected PC
  clusters, and higher overlap of the computation with the I/O operations has
  been achieved.},
  comment = {also see tsujita:stampi*.}
}