Title :
Leakage-aware intraprogram voltage scaling for embedded processors
Author :
Huang, Po-Kuan ; Ghiasi, Soheil
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., Davis, CA
Abstract :
With scaling of technology feature sizes, the share of leakage in total power consumption of digital systems continues to grow. Conventional dynamic voltage scaling (DVS) techniques fail to accurately address the impact of scaling on system power consumption and hence, are incapable of achieving energy efficient solutions. To overcome this problem, we utilize adaptive body biasing (ABB) to adjust transistors´ threshold voltage at runtime. We develop a leakage-aware compilation methodology that targets embedded processors with both DVS and ABB capabilities. Our technique has the unique advantage of jointly optimizing active and leakage energy dissipation. Considering the delay and energy penalty of switching between operating modes of the processor and under deadline constraint, our compiler improves the energy consumption of the generated code by average of 13.07% and up to 30.26% at 90nm. While our technique´s improvement in energy dissipation over conventional DVS is marginal (4.54%) at 130nm, the average improvement continues to grow to 7.8%, 15.94% and 29.56% for 90nm, 65nm and 45 technology nodes, respectively
Keywords :
embedded systems; integrated circuit design; microprocessor chips; 130 nm; 45 nm; 65 nm; 90 mm; adaptive body biasing; dynamic voltage scaling; embedded processors; intraprogram voltage scaling; leakage power; CMOS technology; Delay; Digital systems; Dynamic voltage scaling; Energy consumption; Energy dissipation; Frequency; Runtime; Threshold voltage; Voltage control; Algorithms; Management; Performance;
Conference_Titel :
Design Automation Conference, 2006 43rd ACM/IEEE
Conference_Location :
San Francisco, CA
Print_ISBN :
1-59593-381-6
DOI :
10.1109/DAC.2006.229301