A distributed management scheme for partitionable parallel computers

Author

Jeng, Menkae ; Siegel, Howard Jay

Author_Institution

Dept. of Comput. Sci., Houston Univ., TX, USA

Volume

1

Issue

1

fYear

1990

fDate

1/1/1990 12:00:00 AM

Firstpage

120

Lastpage

126

Abstract

A distributed scheme for dynamic partitioning is investigated. Distributed procedures to split a subsystem and to combine subsystems are presented. The correctness of each of these two procedures is shown, and the complexity is analyzed. The procedures are applicable to parallel computers that use interconnection networks, such as hypercube, omega, multistage cube, and extra-stage cube networks

Keywords

computational complexity; multiprocessor interconnection networks; parallel architectures; PASM; correctness; distributed combining process; distributed management scheme; distributed splitting process; dynamic partitioning; extra-stage cube networks; hypercube; interconnection networks; multistage cube; omega; parallel computation; partitionable parallel computers; resource fragments; speed-up oriented; task allocation; throughput oriented; Application software; Computer networks; Concurrent computing; Distributed computing; Hypercubes; Intelligent networks; Large-scale systems; Multiprocessor interconnection networks; Parallel processing; Resource management;

fLanguage

English

Journal_Title

Parallel and Distributed Systems, IEEE Transactions on

Publisher

ieee

ISSN

1045-9219

Type

jour

DOI

10.1109/71.80130

Filename

80130