Statistical Error Analysis for Low Power Approximate Adders

• DOI: 10.1145/3061639.3062319
• Publication Date: 2017-06-13T08:18:42Z
• Authors: Muhammad Kamran Ayub; Osman Hasan; Muhammad Shafique
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Low-power approximate adders provide basic building blocks for computing hardware that have shown remarkable energy efficiency error-resilient applications (like image/video processing, computer vision, etc.), especially battery-driven portable systems. In this paper, we present a novel scalable, fast yet accurate analytical method to evaluate the output error probability of multi-bit low power predetermined input bits. Our recursively computes by considering cases only, which are considerably smaller than erroneous ones. can handle analysis wider-range with negligible computational overhead. To ensure its rapid adoption in industry and academia, open-sourced our LabVIEW MATLAB libraries.