Energy-efficient multiplier-less discrete convolver through probabilistic domain transformation

  • Authors:
  • Mohammed Alawad;Yu Bai;Ronald DeMara;Mingjie Lin

  • Affiliations:
  • UCF, Orlando, USA;UCF, Orlando, USA;UCF, Orlando, USA;UCF, Orlando, USA

  • Venue:
  • Proceedings of the 2014 ACM/SIGDA international symposium on Field-programmable gate arrays
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

Energy efficiency and algorithmic robustness typically are conflicting circuit characteristics, yet with CMOS technology scaling towards 10-nm feature size, both become critical design metrics simultaneously for modern logic circuits. This paper propose a novel computing scheme hinged on probabilistic domain transformation aiming for both low power operation and fault resilience. In such a computing paradigm, algorithm inputs are first encoded through probabilistic means, which translates the input values into a number of random samples. Subsequently, light-weight operations, such as sim- ple additions will be performed onto these random samples in order to generate new random variables. Finally, the resulting random samples will be decoded probabilistically to give the final results.