By Topic

On-chip structure and addressing scheme design for 2-D block data processing in a 64-core array system

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

3 Author(s)
Jing Xie ; School of Microelectronics, Shanghai Jiaotong University, 200240, China ; Huimin Xing ; Zhigang Mao

High throughput and high computation many core based on chip architecture is a development trend for high performance digital signal processing platform design. With frame and block data processing technology feature, the general linear memory architecture and on chip interconnection scheme may cause performance bottleneck for the application. In this paper work, we propose a 64-core array on chip architecture for high throughput and high performance 2-D block data processing, which with the features of hierachical architecture level, mirror symmetric interconnection structure and a Block level 2-D data addressing scheme. From the experiment show, the design can meet real time processing requirement of the 1080P data frame from H.264/AVC specification by use of block level matrix computation with average dynamic power report at 469.3mw.

Published in:

2011 IEEE/IFIP 19th International Conference on VLSI and System-on-Chip

Date of Conference:

3-5 Oct. 2011