Soft NMR: Analysis & application to DSP systems

Eric P. Kim, Naresh R. Shanbhag

Abstract

We have recently proposed the concept of soft N-modular redundancy (soft NMR) in order to design robust and energy-efficient computing systems in nanoscale processes, where soft NMR was shown to achieve orders-of-magnitude improvement in robustness with significant power savings over NMR. In this paper, we analyze the performance of soft NMR and compare it with that of NMR and algorithmic noise-tolerance (ANT). An 8-b multiplier and a DCT-based still image compression system in a commercial 45nm CMOS process is considered. Two metrics of system performance: system reliability P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e,sys</sub> , and signal-to-noise ratio (SN R) are analyzed. We show that soft NMR always outperforms NMR and that our analysis predicts P <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e,sys</sub> and SNR to within 4.2% and 2.7dB on average, respectively, of the results of Monte Carlo simulations.
BibTeX
@inproceedings{kim2010soft,
  author = {Eric P. Kim and Naresh R. Shanbhag},
  title = {{Soft NMR: Analysis \&amp;\#x00026; application to DSP systems}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2010},
  url = {https://openreview.net/forum?id=CtopardhwCu},
}

Loading related content...

Figure