The Performance Comparison and Evaluation of Parallel Platforms based on Throughput Model

Author

Ma, Yan ; Li, Guoqing ; Wang, Jian ; Liu, Dingsheng

fYear

2006

fDate

Oct. 2006

Firstpage

482

Lastpage

486

Abstract

Economical and high-efficient parallel computing platform are of great significance to remote sensing image processing. The throughput ability of every step of such processing heavily affects the application of remote sensing image parallel processing technologies. And throughput is a key performance index of high price/performance rate computing platform. Through analyzing the throughput model, we can obtain the characteristics of the parallel processing system throughput, also quantitatively analyze the throughput ability of each processing step brought by various peripheries and their matching relationships. This paper discusses the throughput characteristics of super computer and common COW (cluster of workstation), which are typical parallel computing platforms. And the study of real cases has been given to show the quantitative analysis method to construct economical and high-performance computing platform according to throughput characteristics

Keywords

geophysical signal processing; image processing; mainframes; parallel machines; performance evaluation; remote sensing; workstation clusters; parallel computing platform; performance comparison; performance evaluation; remote sensing image processing; super computer; throughput model; workstation cluster; Bandwidth; Clustering algorithms; Concurrent computing; High performance computing; Image processing; Parallel processing; Performance analysis; Remote sensing; System performance; Throughput;

fLanguage

English

Publisher

ieee

Conference_Titel

Grid and Cooperative Computing Workshops, 2006. GCCW '06. Fifth International Conference on

Conference_Location

Hunan

Print_ISBN

0-7695-2695-0

Type

conf

DOI

10.1109/GCCW.2006.91

Filename

4031595