Title :
A comprehensive analysis of energy savings in dynamic supply voltage scaling systems using data dependent voltage level selection
Author :
Chandrasena, Lama H. ; Liebelt, Michael J.
Author_Institution :
Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
Abstract :
We extend our analysis of the data-dependent quantized voltage level selection (DDLS) technique for dynamic supply voltage scaling (DSVS) systems. The energy analysis was performed using a very conservative energy model considering all combinations of two, three and four quantized voltage levels, and the minimum-energy-yielding quantized voltage levels were selected. For test data, we used nine 300-frame MPEG-2 video sequences in QCIF (Quarter Common Intermediate Format). Our results indicate that energy savings of up to 12% are achievable by selecting quantized voltage levels based on the workload distribution
Keywords :
CMOS integrated circuits; electric potential; image sequences; power consumption; video coding; CMOS circuits; MPEG-2 video sequences; QCIF; Quarter Common Intermediate Format; conservative energy model; data-dependent quantized voltage level selection; dynamic supply voltage scaling systems; energy dissipation; energy savings; minimum energy-yielding quantized voltage levels; workload distribution; Capacitance; Circuit testing; Clocks; Data engineering; Delay; Dynamic voltage scaling; Energy dissipation; Power engineering and energy; Threshold voltage; Video sequences;
Conference_Titel :
Multimedia and Expo, 2000. ICME 2000. 2000 IEEE International Conference on
Conference_Location :
New York, NY
Print_ISBN :
0-7803-6536-4
DOI :
10.1109/ICME.2000.871527
