DocumentCode
1957632
Title
Area-aware topology generation for Application-Specific Networks-on-Chip using network partitioning
Author
Morgan, Ahmed A. ; Elmiligi, Haytham ; El-Kharashi, M. Watheq ; Gebali, Fayez
Author_Institution
Dept. of Electr. & Comput. Eng., Univ. of Victoria, Victoria, BC, Canada
fYear
2009
fDate
23-26 Aug. 2009
Firstpage
979
Lastpage
984
Abstract
One of the challenging problems in application-specific networks-on-chip (ASNoC) design is customizing the topological structure of the on-chip network in order to meet the application requirements with the minimum possible cost. In this paper, the area cost of ASNoCs is reduced by using network partitioning techniques. Given the application core graph, the partitioning problem is formulated as an optimization one. Partitioning results in increasing the average delay, which is compensated for by adjusting the network bandwidth. A methodology is proposed for an area-aware custom topology generation employing network partitioning. As a proof of concept, our methodology is applied to three different applications with different number of cores. Results show that the proposed methodology is a promising way to reduce the ASNoC area compared to other standard and custom topology generation techniques.
Keywords
application specific integrated circuits; network topology; network-on-chip; optimisation; application core graph; application specific networks on chip; area aware topology generation; network partitioning; optimization; Computer science; Counting circuits; Educational institutions; Frequency; History; Network topology; Performance loss; Pollution; Runtime; System performance; Application-Specific Networks-on-Chip (ASNoC); Core graph; Network partitioning; Performance analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications, Computers and Signal Processing, 2009. PacRim 2009. IEEE Pacific Rim Conference on
Conference_Location
Victoria, BC
Print_ISBN
978-1-4244-4560-8
Electronic_ISBN
978-1-4244-4561-5
Type
conf
DOI
10.1109/PACRIM.2009.5291235
Filename
5291235
Link To Document