Title :
Highly energy-efficient and quality-tunable inexact FFT accelerators
Author :
Lingamneni, Avinash ; Enz, Christian ; Palem, Krishna ; Piguet, Christian
Author_Institution :
Dept. of Electr. & Comput. Eng., Rice Univ., Houston, TX, USA
Abstract :
We present inexact Fast Fourier Transform (FFT) accelerators that can realize energy-accuracy tradeoffs taking advantage of various inexact design techniques in conjunction with a machine-learning inspired waveform shaping technique. A 65nm ASIC test chip with several inexact FFTs shows a reduction in datapath energy consumption upto 75% and the total energy consumption upto 45% (a factor of 4X and 1.8X respectively) when compared to a conventional exact FFT at marginal Signal-to-Noise Ratio (SNR) losses between 0.0002 dB to 1 dB.
Keywords :
application specific integrated circuits; fast Fourier transforms; datapath energy consumption; energy efficient FFT accelerators; fast Fourier transform accelerators; quality tunable inexact FFT accelerators; waveform shaping technique; Adders; Computer architecture; Delays; Energy consumption; Hardware; Signal to noise ratio; Vectors;
Conference_Titel :
Custom Integrated Circuits Conference (CICC), 2014 IEEE Proceedings of the
Conference_Location :
San Jose, CA
DOI :
10.1109/CICC.2014.6946047
