DocumentCode
3261020
Title
Research on cluster of workstations
Author
Wang, Dingxing ; Zheng, Weimin ; Xiong, Jianxin
Author_Institution
Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
fYear
1997
fDate
18-20 Dec 1997
Firstpage
275
Lastpage
281
Abstract
Cluster of Workstations is becoming an important kind of parallel computing platform. Two issues are essential for promoting the popularization of COW: high-performance communication mechanism and powerful programming environment. In this paper we present our research work on COW, which aims at giving a practical solution to the above issues. In order to build a high performance communication system, we design a reduced communication protocol in addition to making use of high-speed network hardware. Based on PVM, we implement a practical programming environment which include parallel compiling systems, parallel debugger, load balancing tool and execution fault recovery tool. Some performance results are given in this paper
Keywords
parallel architectures; parallel programming; programming environments; COW; PVM; cluster of workstations; execution fault recovery tool; high-performance communication; load balancing; parallel compiling systems; parallel debugger; programming environment; reduced communication protocol; Bandwidth; Costs; High-speed networks; Load management; Parallel processing; Parallel programming; Programming environments; Scalability; Switches; Workstations;
fLanguage
English
Publisher
ieee
Conference_Titel
Parallel Architectures, Algorithms, and Networks, 1997. (I-SPAN '97) Proceedings., Third International Symposium on
Conference_Location
Taipei
ISSN
1087-4089
Print_ISBN
0-8186-8259-6
Type
conf
DOI
10.1109/ISPAN.1997.645108
Filename
645108
Link To Document