M06 Approximate Computing: Circuits, Systems and Applications

Monday, 21 March 2022 13:15
Monday, 21 March 2022 17:15
Weiqiang Liu, Nanjing University of Aeronautics and Astronautics, China
Jie Han, University of Alberta, Canada
Alberto Bosio, Lyon Institute of Nanotechnology, France
Fabrizio Lombardi, Northeastern University, United States

Tutorial Abstract:

Computing systems are conventionally designed to operate as accurately as possible. However, this trend faces severe technology challenges, such as power dissipation, circuit reliability, and performance. There are a number of pervasive computing applications (such as machine learning, pattern recognition, digital signal processing, communication, robotics, and multimedia), which are inherently error-tolerant or error-resilient, i.e., in general, they require acceptable results rather than fully exact results. Approximate computing has been proposed for highly energy-efficient systems targeting the above-mentioned emerging error-tolerant applications; approximate computing consists of approximately (inexactly) processing data to save power and achieve high performance, while results remain at an acceptable level for subsequent use. This tutorial starts with the motivation of approximate computing and then it reviews current techniques for approximate hardware designs. This tutorial will cover the following topics:  Approximate Arithmetic Circuits, Approximate DSP Modules, Machine Learning Applications and Security, and Approximate Computing for Safety-Critical Applications. Directions for future works in approximate computing will also be provided. This tutorial will be presented and tailored to the EDA community and its technical interests.