Sensor-Based Approximate Adder Design for Accelerating Error-Tolerant and Deep-Learning Applications

Ning-Chi Huanga, Szu-Ying Chenb and Kai-Chiang Wuc
National Chiao Tung University, Hsinchu, Taiwan
anchuang@cs.nctu.edu.tw
bsandy81917@gmail.com
ckcw@cs.nctu.edu.tw

ABSTRACT


Approximate computing is an emerging strategy which trades computational accuracy for computational cost in terms of performance, energy, and/or area. In this paper, we propose a novel sensor-based approximate adder for highperformance energy-efficient arithmetic computation, while considering the accuracy requirement of error-tolerant applications. This is the first work using in-situ sensors for approximate adder design, based on monitoring online transition activity on the carry chain and speculating on carry propagation/truncation. On top of a fully-optimized ripple-carry adder, the performance of our adder is enhanced by 2.17X. When applied in error-tolerant applications such as image processing and handwritten digit recognition, our approximate adder leads to very promising quality of results compared to the case when an accurate adder is used.



Full Text (PDF)