@InProceedings{ali:enhancing,
  author = {Zeyad Ali and Qutaibah Malluhi},
  title = {Enhancing data-intensive applications performance by tuning the
  distributed storage policies},
  booktitle = {Proceedings of the International Conference on Parallel and
  Distributed Processing Techniques and Applications, PDPTA'04},
  year = {2004},
  month = {June},
  volume = {3},
  pages = {1515--1522},
  copyright = {(c)2005 Elsevier Engineering Information, Inc.},
  address = {Las Vegas, NV},
  keywords = {application-specific storage policies, pario-app, DTViewer,
  access patterns, data layout, pario-bib},
  abstract = {This paper describes the performance improvements achieved by a
  data-intensive application by controlling the storage policies and algorithms
  of a distributed storage system. The Network Storage Manager (NSM) is a mass
  distributed storage framework with a unique architecture that provides
  applications with the high-performance features they need. It also provides
  the standard most commonly used implementation for storage policies.
  Distributed Terrain Viewer (DTViewer) is an application that utilizes NSM
  architecture and for efficient and reliable data delivery. Moreover, it
  exploits NSM controllable architecture by plugging-in its
  application-specific optimized implementations. DTViewer overrides the
  default NSM policies that do not understand its sophisticated access
  patterns, partitioning, and storage layout requirements. Experimental results
  have show significant improvement achieved when the application-tailored
  implementation are used. Such speedups are not achievable on storage systems
  with no application control such as the Parallel Virtual File System PVFS.
  (44 Refs.)}
}

@InProceedings{baer:grid-io,
  author = {Troy Baer and Pete Wyckoff},
  title = {A parallel {I/O} mechanism for distributed systems.},
  booktitle = {Proceedings of the 2004 IEEE International Conference on Cluster
  Computing},
  year = {2004},
  month = {September},
  pages = {63--69},
  publisher = {IEEE Computer Society Press},
  address = {San Diego, CA},
  keywords = {grid I/O, MPI-I/O, grid middleware, gridFTP, pario-bib},
  abstract = {Access to shared data is critical to the long term success of
  grids of distributed systems. As more parallel applications are being used on
  these grids, the need for some kind of parallel I/O facility across
  distributed systems increases. However, grid middleware has thus far had only
  limited support for distributed parallel I/O. In this paper, we present an
  implementation of the MPI-2 I/O interface using the Globus GridFTP client
  API. MPI is widely used for parallel computing, and its I/O interface maps
  onto a large variety of storage systems. The limitations of using GridFTP as
  an MPI-I/O transport mechanism are described, as well as support for parallel
  access to scientific data formats such as HDF and NetCDF. We compare the
  performance of GridFTP to that of NFS on the same network using several
  parallel I/O benchmarks. Our tests indicate that GridFTP can be a workable
  transport for parallel I/O, particularly for distributed read-only access to
  shared data sets. (26 refs.)}
}

@Article{cha:subgroup,
  author = {Kwangho Cha and Taeyoung Hong and Jeongwoo Hong},
  title = {The subgroup method for collective {I/O}},
  journal = {Lecture Notes in Computer Science},
  booktitle = {5th International Conference on Parallel and Distributed
  Computing; December 8-10, 2004; Singapore, SINGAPORE},
  editor = {Liew, KM; Shen, H; See, S; Cai, W; Fan, P; Horiguchi, S},
  year = {2004},
  month = {December},
  volume = {3320},
  pages = {301--304},
  institution = {Korea Inst Sci \& Technol Informat, Supercomp Ctr, 52 Eoeun,
  Taejon 305806, South Korea; Korea Inst Sci \& Technol Informat, Supercomp
  Ctr, Taejon 305806, South Korea},
  publisher = {SPRINGER-VERLAG BERLIN},
  copyright = {(c)2005 The Thomson Corporation},
  URL =
  {http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=3320&spage=301},
  keywords = {collective I/O, MPI subgroup, pario-bib},
  abstract = {Because many scientific applications require large data
  processing, the importance of parallel I/O has been increasingly recognized.
  For collective I/O, one of the considerable features of parallel I/O, we
  suggest the subgroup method. It is the way of using collective I/O of MPI
  effectively in terms of application programs. From the experimental results,
  we could conclude that the subgroup method for collective I/O is more
  efficient than plain collective I/O.}
}

@InProceedings{cortes:lessons,
  author = {Toni Cortes},
  title = {Parallel {I/O}: lessons learnt in the last 20 years},
  booktitle = {Proceedings of the 2004 IEEE International Conference on Cluster
  Computing},
  year = {2004},
  month = {September},
  publisher = {Piscataway, NJ, USA : IEEE, 2004},
  copyright = {(c)2005 IEE},
  address = {San Diego, CA},
  keywords = {tutorial, parallel I/O overview, pario-bib},
  abstract = {Summary form only given. After these two decades, it is now a
  good time to go through all the done work and try to learn the important
  lessons all these parallel I/O initiatives have taught us. This paper aims at
  giving this global overview. The focus is not on commercial/academic
  systems/prototypes, but on the concepts that lay behind them. These concepts
  have normally been applied at different levels, and thus, such an overview
  can be of interest to many people ranging from the hardware design to the
  application implementation. Some of the most important concepts that are
  discussed are, among others, data placement (RAIDs, 2D and 3D files, ...),
  network architectures for parallel I/O (Network attached devices, SAN, ...),
  parallel caching and prefetching (cooperative caching, Informed caching and
  prefetching, ...), and interfaces (collective I/O, data distribution
  interfaces, ...).},
  comment = {Tutorial given at Cluster 2004.}
}

@Article{lin:optimizing,
  author = {Yih-Fang Lin and Chien-Min Wang and Jan-Jan Wu},
  title = {Optimizing I/O server placement for parallel I/O on switch-based
  irregular networks},
  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 = {997--1006},
  institution = {Acad Sinica, Inst Sci Informat, Taipei 115, Taiwan; Natl
  Taiwan Univ, Dept Comp Sci \& Informat Engn, Taipei 10764, Taiwan},
  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=997},
  keywords = {I/O server placement, network topologies, switch-based clusters,
  pario-bib},
  abstract = {In this paper, we study I/O server placement for optimizing
  parallel I/O performance on switch-based clusters, which typically adopt
  irregular network topologies to allow construction of scalable systems with
  incremental expansion capability. Finding optimal solution to this problem is
  computationally intractable. We quantified the number of messages travelling
  through each network link by a workload function, and developed three
  heuristic algorithms to find good solutions based on the values of the
  workload function. Our simulation results demonstrate performance advantage
  of our algorithms over a number of algorithms commonly used in existing
  parallel systems. In particular, the load-balance-based algorithm is superior
  to the other algorithms in most cases, with improvement ratio of 10% to 95  in terms of parallel I/O throughput.}
}

@Article{miyamura:adventure-io,
  author = {Tomoshi Miyamura and Shinobu Yoshimura},
  title = {Generalized {I/O} data format and interface library for module-based
  parallel finite element analysis system.},
  journal = {Advances in Engineering Software},
  year = {2004},
  month = {March},
  volume = {35},
  number = {3--4},
  pages = {149--159},
  institution = {Nihon Univ, Coll Engn, Dept Comp Sci, 1 Nakagawara, Koriyama,
  Fukushima 9638642, Japan; Nihon Univ, Coll Engn, Dept Comp Sci, Koriyama,
  Fukushima 9638642, Japan; Univ Tokyo, Grad Sch Frontier Sci, Inst Environm
  Studies, Bunkyo Ku, Tokyo 1138656, Japan},
  publisher = {UK : Elsevier, 2004},
  copyright = {(c)2005 Elsevier Engineering Information, Inc.; IEE; The Thomson
  Corporation},
  keywords = {data format, finite element method, generalized I/O data,
  hierarchical domain decomposition, pario-app, pario-bib},
  abstract = {In this paper, a generalized input/output (I/O) data format and
  library for a module-based parallel finite element analysis system are
  proposed. The module-based system consists of pre-, main- and post-modules,
  as well as some common libraries. The present I/O library, called
  ADVENTURE_IO, and data format are developed specifically for use in parallel
  high-performance computational mechanics system. These are rather simple
  compared to other general-purpose I/O systems such as netCDF and HDF5. A
  simple container called a finite element generic attributes (FEGAs) document
  enables the handling of almost all the I/O data in a parallel finite element
  method code. Due to the simplicity of the present system, tuning up the I/O
  library for a specific parallel environment is easy. Other major features of
  the present system are: (1) it possesses a generalized collaboration
  mechanism consisting of multiple modules in a distributed computing
  environment employing common object request broker architecture, and (2)
  abstracted data description employed in the FEGA/HDDM_FEGA document enables
  the development of a unique domain decomposer that can subdivide any kind of
  input data.}
}

@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*.}
}

@Article{yang:construction,
  author = {Chao-Tung Yang and Chien-Tung Pan and Kuan-Ching Li and Wen-Kui
  Chang},
  title = {On construction of a large file system using {PVFS} for grid},
  journal = {Lecture Notes in Computer Science},
  booktitle = {5th International Conference on Parallel and Distributed
  Computing; December 8-10, 2004; Singapore, SINGAPORE},
  editor = {Liew, KM; Shen, H; See, S; Cai, W; Fan, P; Horiguchi, S},
  year = {2004},
  month = {December},
  volume = {3320},
  pages = {860--863},
  institution = {Tunghai Univ, High Performance Comp Lab, Dept Comp Sci \&
  Informat Engn, Taichung 407, Taiwan; Providence Univ, Parallel \& Distributed
  Proc Ctr, Dept Comp Sci \& Informat Management, Taichung 433, Taiwan},
  publisher = {SPRINGER-VERLAG BERLIN},
  copyright = {(c)2005 The Thomson Corporation},
  URL =
  {http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=3320&spage=860},
  keywords = {grid I/O, PVFS2, cluster file system, pario-bib},
  abstract = {Grid is the largest advance of network after Internet since the
  Grid System provides a specialty that can be used popularly and effectively.
  However, it is a challenge to the consistency and community of use on the
  data storages space of a Grid System. Therefore, the problem of application
  for the Computational Grid and Data Grid is more important. It can set up a
  usability, expandability, high operation capability, and large memory space
  in Grid with the Cluster system and parallel technique in order to solve the
  problem. In this paper, we provided a Grid with high operation capability and
  higher memories to solve the problem. As to the Grid setting, we take use of
  the Cluster computing to increase the operation effect for computing, and a
  PVFS2 with more storages effect for data. It can supply a quite correct
  platform for Grid user whether for large data access or huge operation.}
}