DocumentCode :
3016534
Title :
An adaptive algorithm for low-power streaming multimedia processing
Author :
Acquaviva, Andrea ; Benini, Luca ; Ricco, Bruno
Author_Institution :
Dipartimento di Elettronica Inf. e Sistemistica, Bologna Univ., Italy
fYear :
2001
fDate :
2001
Firstpage :
273
Lastpage :
279
Abstract :
This paper addresses the problem of power consumption in multimedia system architectures and presents an algorithmic optimization technique to achieve the goal of power reduction in the context of real time processing. The technique is based on a mixed speed-setting and shutdown policy. We address the problem from both a theoretical and practical point of view, by presenting a power efficient implementation of a MPEG-layer3 real-time decoder algorithm designed for wearable devices as a case study. The target system is the Hewlett-Packard´s SmartBadgeIII prototype of wearable system based on the StrongARM1100 processor. Theoretical analysis as well as quantitative results of power measurements are provided to show the effectiveness of this technique. The experimental set-up is also described
Keywords :
data compression; decoding; digital signal processing chips; low-power electronics; microprocessor chips; multimedia computing; optimisation; portable computers; real-time systems; video coding; Hewlett-Packard; MPEG-layer3 real-time decoder algorithm; SmartBadgeIII prototype; StrongARM1100 processor; adaptive algorithm; algorithmic optimization technique; low-power streaming multimedia processing; mixed speed-setting/shutdown policy; multimedia system architectures; power consumption; power efficient implementation; power reduction; real time processing; wearable devices; Adaptive algorithm; Computer architecture; Decoding; Energy consumption; Frequency; Hardware; Power system reliability; Real time systems; Streaming media; Voltage;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Design, Automation and Test in Europe, 2001. Conference and Exhibition 2001. Proceedings
Conference_Location :
Munich
ISSN :
1530-1591
Print_ISBN :
0-7695-0993-2
Type :
conf
DOI :
10.1109/DATE.2001.915037
Filename :
915037
Link To Document :
بازگشت