By Topic

Power-Efficient and High-Performance Multi-level Hybrid Nanophotonic Interconnect for Multicores

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
$33 $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

2 Author(s)
Randy Wayne Morris Jr. ; Sch. of Electr. Eng. & Comput. Sci., Ohio Univ., Athens, OH, USA ; Avinash Karanth Kodi

Network-on-Chips (NoCs) are becoming the defacto standard for interconnecting the increasing number of cores in chip multiprocessors (CMPs) by overcoming the scalability and wire delay problems of shared buses. However, recent research has shown that future NoCs will be limited by power dissipation and reduced performance forcing architects to explore other technologies that are complementary metal oxide semiconductor (CMOS) compatible. In this paper, we propose ET-PROPEL (Extended Token based Photonic Reconfigurable On-Chip Power and Area-Efficient Links) architecture to utilize the emerging nanophotonic technology to design a high-bandwidth, low latency and low power multi-level hybrid interconnect that balances cost and performance. We develop our interconnect at three levels: at the first level (x) we design a fully connected network for exploiting locality; at the second level(y), we design a shared channel using optical tokens to reduce power while providing full connectivity and at the third level (z), we propose a novel nanophotonic crossbar that provides scalable bisection bandwidth. The first two levels are combined into T-PROPEL(token-PROPEL, 64 cores) and four separate T-PROPELs are combined into ET-PROPEL (256 cores). We have simulated both T-PROPEL and ET-PROPEL using synthetic and SPLASH-2 traffic, where our results indicate that T-PROPEL and ET-PROPEL significantly reduce power(10-fold) and increase performance (3-fold) over other well known electrical and photonic networks.

Published in:

Networks-on-Chip (NOCS), 2010 Fourth ACM/IEEE International Symposium on

Date of Conference:

3-6 May 2010