DocumentCode :
294859
Title :
Power minimization in DSP application specific systems using algorithm selection
Author :
Potkonjak, Miodrag ; Rabaey, Jan M.
Author_Institution :
C&C Res. Labs., NEC Res. Inst., Princeton, NJ, USA
Volume :
4
fYear :
1995
fDate :
9-12 May 1995
Firstpage :
2639
Abstract :
We introduce the algorithm selection problem for power minimization. After demonstrating the high impact of this synthesis task on the power consumption of the final implementation using a case study, we studied its computational complexity. We present an efficient optimization intensive algorithm for power minimization using algorithm selection. We applied the marginal utility-based algorithm for algorithm selection on three DSP examples. A table illustrates the effectiveness of the power optimization using algorithm selection on one audio (LMS DCT transform domain filter) and two video (NTSC formatter and DPCM coder) applications. On several DSP examples more than an order of magnitude reduction in power is demonstrated
Keywords :
discrete cosine transforms; filtering theory; least mean squares methods; optimisation; power consumption; signal processing; video coding; video equipment; DPCM coder; DSP application specific systems; LMS DCT transform domain filter; NTSC formatter; algorithm selection; audio applications; computational complexity; marginal utility-based algorithm; optimization intensive algorithm; power minimization; synthesis task; video applications; Band pass filters; Computational complexity; Design automation; Digital signal processing; Discrete cosine transforms; Energy consumption; Filters; Least squares approximation; Minimization methods; Sparse matrices; Throughput; Voltage;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
Conference_Location :
Detroit, MI
ISSN :
1520-6149
Print_ISBN :
0-7803-2431-5
Type :
conf
DOI :
10.1109/ICASSP.1995.480103
Filename :
480103
Link To Document :
بازگشت