DocumentCode :
3385189
Title :
Exploiting power-area tradeoffs in High-Level Synthesis through dynamic functional unit allocation
Author :
Wu, Feng ; Xu, Ning ; Yu, Junbo ; Zheng, Fei ; Bian, Jinian
Author_Institution :
Sch. of Comput. Sci. & Technol., Wuhan Univ. of Technol., Wuhan, China
fYear :
2009
fDate :
23-25 July 2009
Firstpage :
1092
Lastpage :
1096
Abstract :
The increasing power consumption levels of integrated circuits (ICs) have become a major concern of the semiconductor industry. Excessive power dissipation causes overheating, which can lead to soft errors or permanent damage. It also limits battery life in portable equipments. High power consumption can be reduced by properly increasing area. However, arbitrarily large area, namely high number of functional unit (FU) in high-level view, dramatically increases IC cost. This paper describes a new dynamic-power aware High Level Synthesis (HLS) data path approach that considers dynamic FU allocation whilst attempting to minimize area, power, or make a tradeoff between them. The experimental results have shown that when the area is nearly same, our approach delivers a 5.99% reduction in power consumption. And when the power consumption is nearly same, a 11.81% reduction in total FU area is got. The optimal power-area tradeoffs values can be obtained by adjusting power and area ratios.
Keywords :
high level synthesis; integrated circuit design; power consumption; HLS data path approach; dynamic FU allocation; dynamic functional unit allocation; dynamic-power aware high level synthesis; integrated circuit power consumption; optimal power-area tradeoff value; portable equipment; power dissipation; semiconductor industry; Computer science; Cost function; Digital systems; Energy consumption; Hardware; High level synthesis; Power dissipation; Process design; Resource management; Scheduling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communications, Circuits and Systems, 2009. ICCCAS 2009. International Conference on
Conference_Location :
Milpitas, CA
Print_ISBN :
978-1-4244-4886-9
Electronic_ISBN :
978-1-4244-4888-3
Type :
conf
DOI :
10.1109/ICCCAS.2009.5250345
Filename :
5250345
Link To Document :
بازگشت