Accelerating Video-Mining Applications Using Many Small, General-Purpose Cores

Emerging video-mining applications such as image and video retrieval and indexing will require real-time processing capabilities. A many-core architecture with 64 small, in-order, general-purpose cores as the accelerator can help meet the necessary performance goals and requirements. The key video-m...

Full description

Saved in:
Bibliographic Details
Published inIEEE MICRO Vol. 28; no. 5; pp. 8 - 21
Main Authors Li, E., Wenlong Li, Xiaofeng Tong, Jianguo Li, Yurong Chen, Tao Wang, Wang, P.P., Wei Hu, Yangzhou Du, Yimin Zhang, Yen-Kuang Chen
Format Journal Article
LanguageEnglish
Published Los Alamitos IEEE 01.09.2008
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Acceleration
Accelerators
Architecture
Bandwidth
Computer architecture
Data mining
Image retrieval
Image segmentation
Indexing
Information retrieval
Internet
Modules
Processing speed
Real time
Retrieval
Surveillance
Online AccessGet full text

Cover

More Information
Summary:Emerging video-mining applications such as image and video retrieval and indexing will require real-time processing capabilities. A many-core architecture with 64 small, in-order, general-purpose cores as the accelerator can help meet the necessary performance goals and requirements. The key video-mining modules can achieve parallel speedups of 19times to 62times from 64 cores and get an extra 2.3times speedup from 128-bit SIMD vectorization on the proposed architecture.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0272-1732
1937-4143
DOI:10.1109/MM.2008.64