DocumentCode
2429788
Title
Application Specific Low Power ALU Design
Author
Zhou, Yu ; Guo, Hui
Author_Institution
Sch. of Comput. Sci. & Eng., Univ. of New South Wales, Sydney, NSW
Volume
1
fYear
2008
fDate
17-20 Dec. 2008
Firstpage
214
Lastpage
220
Abstract
Power consumption is a critical design issue in embedded processor design. One of common components in the processor is the Arithmetic and Logic Unit (ALU). Usually, ALUs are designed with a combinational logic circuit containing a number of functional components for different arithmetic and logic operations. An ALU can be constructed with a tree or a chain structure. Existing approaches to reduce power often achieve power reduction at the cost of increased design complexity, thus resulting in delay and area overheads. In this paper, we present a customization approach for the chain-structure based ALU design by repositioning functional components in the chain. The approach can be easily integrated into a processor design environment to effectively reduce ALU power consumption for a given application. We have applied our approach to a set of benchmarks. Ourexperimental results show that the power savings range from 43.5% to 49.6%; on average, 46.9% of ALU power reduction can be achieved. Most importantly, this achievement is at cost of neither hardware complexity nor processor performance, and the implementation is extremely straightforward.
Keywords
application specific integrated circuits; circuit complexity; combinational circuits; embedded systems; logic design; low-power electronics; trees (mathematics); ALU power consumption; arithmetic and logic unit; chain structure; combinational logic circuit; design complexity; embedded processor design; functional components; hardware complexity; low power ALU design; power reduction; processor design environment; processor performance; tree structure; Arithmetic; Combinational circuits; Costs; Delay; Energy consumption; Hardware; Logic design; Process design; Tree data structures; Ubiquitous computing;
fLanguage
English
Publisher
ieee
Conference_Titel
Embedded and Ubiquitous Computing, 2008. EUC '08. IEEE/IFIP International Conference on
Conference_Location
Shanghai
Print_ISBN
978-0-7695-3492-3
Type
conf
DOI
10.1109/EUC.2008.81
Filename
4756341
Link To Document