CaltechAUTHORS
  A Caltech Library Service

Distributed Linear Algebra on Networks of Workstations

Carlin, Peter (1994) Distributed Linear Algebra on Networks of Workstations. Computer Science Technical Reports, California Institute of Technology , Pasadena, CA. (Unpublished) http://resolver.caltech.edu/CaltechCSTR:1994.cs-tr-94-14

[img]
Preview
Postscript - Submitted Version
See Usage Policy.

437Kb
[img]
Preview
PDF - Submitted Version
See Usage Policy.

1059Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechCSTR:1994.cs-tr-94-14

Abstract

This thesis describes the development of a portion of a distributed linear algebra library for use on networks of workstations. The library was designed with special consideration towards three characterists of networks of workstations: small numbers of processes, availability of multithreading, and high communication latency. Two aspects of the library are highlighted. First, modifications to message passing primitives to permit their use in a multithreaded environment. Second, modifications to basic linear algebra algorithms to improve their performance on networks of stations. A model of distributed linear algebra on networks of workstations is developed, and used to predict the performance of the modified algorithms. These predictions are compared to experimental results on several networks of workstations.


Item Type:Report or Paper (Technical Report)
Additional Information:© 1994 California Institute of Technology. July 17, 1994. I am indebted primarily to K. Mani Chandy Carl Kesselman and Eric Van de Velde for guidance support and inspiration The distributed linear algebra library described in this thesis was jointly developed with Tom Zavisca. We were able to work so well together because of his perseverance and sense of humor I would like to thank all those who have contributed to the development of CC++. This includes the entire Compositional Systems group at Caltech as well as many people at Argonne In particular I would like to thank John Garnett Tal Lancaster James Patton and Mei-Hui Su for their assistance in using the current implementations of CC++. I would like to thank Rajit Manohar Paul Sivilotti and John Thornley for discussion suggestions and proofreading. This research This research was supported in part by NSF CCR-9120008. I wish to thank Microsoft Green Hills, the Barry Goldwater Foundation and Caltech for supporting my education.
Group:Computer Science Technical Reports
Funders:
Funding AgencyGrant Number
NSFCCR-9120008
Microsoft Green HillsUNSPECIFIED
CaltechUNSPECIFIED
Barry Goldwater FoundationUNSPECIFIED
DOI:10.7907/Z9VH5KV8
Record Number:CaltechCSTR:1994.cs-tr-94-14
Persistent URL:http://resolver.caltech.edu/CaltechCSTR:1994.cs-tr-94-14
Usage Policy:You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.
ID Code:26869
Collection:CaltechCSTR
Deposited By: Imported from CaltechCSTR
Deposited On:14 May 2001
Last Modified:02 May 2017 21:33

Repository Staff Only: item control page