A comparative evaluation of approximate multipliers

A multiplier has a significant impact on the speed and power dissipation of an arithmetic processor. Precise results are not always required in many algorithms, such as those for classification and recognition in data processing. Moreover, many errors do not make an obvious difference in applications such as image processing due to the perceptual limitations of human beings. Error-tolerant algorithms and applications have promoted the development of approximate multipliers to tradeoff accuracy for speed, implementation area and/or power efficiency. This paper briefly reviews the current designs of approximate multipliers and provides a comparative evaluation of their error and circuit characteristics. Image sharpening is performed using the considered approximate multipliers to assess their performance in such applications.