DocumentCode :
928300
Title :
Spanning multiaccess channel hypercube computer interconnection
Author :
Dowd, Patrick W. ; Jabbour, Kamal
Author_Institution :
IBM Glendale Lab., Endicott, NY, USA
Volume :
37
Issue :
9
fYear :
1988
fDate :
9/1/1988 12:00:00 AM
Firstpage :
1137
Lastpage :
1142
Abstract :
A distributed computer system based on a hypercube topology is proposed, where multiaccess channels spanning all dimensional axes provide processor interconnection. The multiprocessor system can be built at relatively low cost by combining the recent advances in high-capacity channels available through fiber optics, and demand-assignment multiple-access protocols, creating a highly fault-tolerant system with good average packet delay and average distance characteristics, at a significantly reduced cost. A totally distributed system has been achieved in which the packets are self-routing, able to take advantage of the multiple paths of equal length between two modes. The proposed structure gives a highly fault tolerant system, degrading gracefully in the presence of failures
Keywords :
fault tolerant computing; multiprocessor interconnection networks; parallel architectures; computer interconnection; distance characteristics; distributed computer system; fault-tolerant system; hypercube topology; multiaccess channel; multiprocessor system; packet delay; processor interconnection; Costs; Degradation; Delay; Distributed computing; Fault tolerant systems; Hypercubes; Multiprocessing systems; Optical fibers; Protocols; Topology;
fLanguage :
English
Journal_Title :
Computers, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9340
Type :
jour
DOI :
10.1109/12.2267
Filename :
2267
Link To Document :
بازگشت