Paper Info
Title
Fine grain word length optimization for dynamic precision scaling in DSP systems
Abstract
Dynamic precision scaling is a promising technique to reduce power consumption in Digital Signal Processing (DSP) systems. Power savings are achieved by dynamically adapting word lengths to a time-varying environment. Typical applications are wireless communication systems that operate under different wireless channel conditions. One of the obstacles of such techniques is that they require an optimization of word lengths for all intermediate values at all possible operation points. This makes traditional simulation-based fixed-point optimization infeasible. In this paper, we study efficient heuristics to find optimal sets of word lengths for all variables in a system under a range of operating conditions. We exploit statistical analysis of quantization noise coupled with Additive White Gaussian Noise (AWGN) models of the channel environment. Applied to an example of a Fast Fourier Transform (FFT) block in an Orthogonal Frequency Division Multiplexing (OFDM) system, a more than 5,000x improvement in optimization time compared to an efficient simulation-based word length optimization method can be achieved.
Year
DOI
Venue
2013
10.1109/VLSI-SoC.2013.6673287
VLSI-SOC
Keywords
Field
DocType
optimisation,wireless channel condition,power consumption,awgn channels,wireless communication system,power saving,simulation-based fixed-point optimization,statistical analysis,fast fourier transform,simulation-based word length optimization method,dynamic precision scaling,ofdm modulation,fine grain word length optimization,quantisation (signal),power reduction,digital signal processing system,ofdm system,additive white gaussian noise model,digital signal processing chips,fft,time-varying channels,wireless channels,time-varying environment,orthogonal frequency division multiplexing system,quantization noise coupling,awgn model,dsp system,fast fourier transforms,word length optimization
Digital signal processing,Wireless,Computer science,Communication channel,Electronic engineering,Fast Fourier transform,Heuristics,Quantization (signal processing),Additive white Gaussian noise,Orthogonal frequency-division multiplexing
Conference
Citations 
PageRank 
References 
8
0.66
4
Authors
2
Name
Order
Citations
PageRank
Seogoo Lee1292.84
Andreas Gerstlauer289078.75