Guest Editors' Introduction: Approximate Computing

Abstract

Ih classicial technology scaling, also known as Dennard's scaling has tremendously improved computer's performance over the past decades, which in turn has enabled countless innovative applications benefiting our daily lives today. However, as the classical technology scaling has approached its fundamental physical limit, the improvement in computer's performance has been sluggish, whereas the amount of information for computers to process exponentially grows. Meanwhile, computers are increasingly used to process, comprehend, and use a large amount of information originated from interaction with the physical world, as computers and their applications become pervasive. While approximate computing has gained significant traction in recent years, it is still in its infancy and the research and industrial communities need new design methodologies and innovative concepts to address the challenges in this area before it becomes mainstream energy-efficient computing solution. The articles in this special section highlight recent investigations in this field.