Efficient I/O for Computational Grid Applications. Oldfield, R. Ph.D. Thesis, 5, 2003. Website abstract bibtex 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.
@phdthesis{
title = {Efficient I/O for Computational Grid Applications},
type = {phdthesis},
year = {2003},
keywords = {dartmouth-cs,grid-computing,parallel-i-o,pario-bib},
websites = {http://www.cs.dartmouth.edu/reports/TR2003-459.pdf},
month = {5},
city = {Hanover, NH},
institution = {Dartmouth College Computer Science},
id = {0661d3d1-705b-3e08-9423-50b8d725e9a0},
created = {2018-07-12T21:31:28.861Z},
file_attached = {false},
profile_id = {f954d000-ce94-3da6-bd26-b983145a920f},
group_id = {b0b145a3-980e-3ad7-a16f-c93918c606ed},
last_modified = {2018-07-12T21:31:28.861Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {oldfield:thesis},
source_type = {phdthesis},
notes = {Available as Dartmouth Computer Science Technical Report TR2003-459<br/>Ph.D Dissertation. Advisor: David Kotz.},
private_publication = {false},
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.},
bibtype = {phdthesis},
author = {Oldfield, Ron}
}
Downloads: 0
{"_id":"TYKTmHur6nRChe7Tj","bibbaseid":"oldfield-efficientioforcomputationalgridapplications-2003","downloads":0,"creationDate":"2019-02-15T15:14:59.165Z","title":"Efficient I/O for Computational Grid Applications","author_short":["Oldfield, R."],"year":2003,"bibtype":"phdthesis","biburl":null,"bibdata":{"title":"Efficient I/O for Computational Grid Applications","type":"phdthesis","year":"2003","keywords":"dartmouth-cs,grid-computing,parallel-i-o,pario-bib","websites":"http://www.cs.dartmouth.edu/reports/TR2003-459.pdf","month":"5","city":"Hanover, NH","institution":"Dartmouth College Computer Science","id":"0661d3d1-705b-3e08-9423-50b8d725e9a0","created":"2018-07-12T21:31:28.861Z","file_attached":false,"profile_id":"f954d000-ce94-3da6-bd26-b983145a920f","group_id":"b0b145a3-980e-3ad7-a16f-c93918c606ed","last_modified":"2018-07-12T21:31:28.861Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"oldfield:thesis","source_type":"phdthesis","notes":"Available as Dartmouth Computer Science Technical Report TR2003-459<br/>Ph.D Dissertation. Advisor: David Kotz.","private_publication":false,"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.","bibtype":"phdthesis","author":"Oldfield, Ron","bibtex":"@phdthesis{\n title = {Efficient I/O for Computational Grid Applications},\n type = {phdthesis},\n year = {2003},\n keywords = {dartmouth-cs,grid-computing,parallel-i-o,pario-bib},\n websites = {http://www.cs.dartmouth.edu/reports/TR2003-459.pdf},\n month = {5},\n city = {Hanover, NH},\n institution = {Dartmouth College Computer Science},\n id = {0661d3d1-705b-3e08-9423-50b8d725e9a0},\n created = {2018-07-12T21:31:28.861Z},\n file_attached = {false},\n profile_id = {f954d000-ce94-3da6-bd26-b983145a920f},\n group_id = {b0b145a3-980e-3ad7-a16f-c93918c606ed},\n last_modified = {2018-07-12T21:31:28.861Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {oldfield:thesis},\n source_type = {phdthesis},\n notes = {Available as Dartmouth Computer Science Technical Report TR2003-459<br/>Ph.D Dissertation. Advisor: David Kotz.},\n private_publication = {false},\n 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.},\n bibtype = {phdthesis},\n author = {Oldfield, Ron}\n}","author_short":["Oldfield, R."],"urls":{"Website":"http://www.cs.dartmouth.edu/reports/TR2003-459.pdf"},"bibbaseid":"oldfield-efficientioforcomputationalgridapplications-2003","role":"author","keyword":["dartmouth-cs","grid-computing","parallel-i-o","pario-bib"],"downloads":0},"search_terms":["efficient","computational","grid","applications","oldfield"],"keywords":["dartmouth-cs","grid-computing","parallel-i-o","pario-bib","parallel i/o","grid computing"],"authorIDs":["5c69efe6ac591010000000e0"]}