Task partitionings for parallel triangular solver on a MIMD computer

Author

Qin, Junming ; Chan, Tony Kai Yun

Author_Institution

Div. of Comput. Eng., Nanyang Technol. Univ., Singapore

fYear

1996

fDate

6-9 Aug. 1996

Firstpage

365

Lastpage

373

Abstract

Considers a parallel triangular solver on a distributed-memory MIMD computer. Three task partitioning methods are discussed, with both task assignment and task scheduling. Their estimated times are provided by using a performance model and a parallel performance evaluation methodology. The optimal task granularities are deduced by the analysis of their performance. Experiences on a transputer-based multicomputer are given.

Keywords

distributed memory systems; mathematics computing; matrix algebra; parallel algorithms; processor scheduling; resource allocation; software performance evaluation; distributed-memory MIMD computer; estimated times; optimal task granularities; parallel performance evaluation methodology; parallel triangular solver; performance model; task assignment; task partitioning methods; task scheduling; transputer-based multicomputer; Algorithm design and analysis; Application software; Concurrent computing; Distributed computing; Heart; Linear systems; Parallel algorithms; Parallel processing; Processor scheduling; Scientific computing;

fLanguage

English

Publisher

ieee

Conference_Titel

High Performance Distributed Computing, 1996., Proceedings of 5th IEEE International Symposium on

Conference_Location

Syracuse, NY, USA

ISSN

1082-8907

Print_ISBN

0-8186-7582-9

Type

conf

DOI

10.1109/HPDC.1996.546207

Filename

546207