Close category search window
 

A hybird hierarchical architecture for 3D multi-cluster NoC

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

6 Author(s)
Wang Jiawen ; Inst. of VLSI Design, Nanjing Univ., Nanjing, China ; Li Li ; Zhang Yuang ; Pan Hongbing
more authors

The pursuit of higher performance has driven the bus based architecture toward network-on-chip (NoC). Meanwhile the three dimensional (3D) IC technology was suggested as a promising approach to reduce the wire length since the chip size became larger and larger. Because of the trend of hundreds or even thousands of processor cores integrated on one chip, it trigged a quest for the amalgamation of these two technologies above. As a result, 3D NoC emerged as a potent solution. In this paper, a hybrid hierarchical architecture for 3D multi-cluster NoC is proposed with the goal of optimizing the whole system performance. Each cluster is built based on hierarchical buses while global connections among clusters are formed with mesh topologies. The memory system is also divided into several layers and managed hierarchically. Both architectures and memory systems are discussed in detail and an analytical comparison of the average distance decreasing in the proposed architecture versus a standard NoC is presented. Experimental results indicate that the proposed architecture can improve the performance sharply. For writing operations, it can save 54.7% execution time in the best condition. While for reading operations, this value can reach 63.6%. And in a real communication-intensive application, 42.7% time savings have been observed compared to the conventional NoC.

Published in:
Computer Science & Education (ICCSE), 2011 6th International Conference on

Date of Conference: 3-5 Aug. 2011

Need Help?


IEEE Advancing Technology for Humanity About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2013 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.