Efficient Approximate Multiplier for Image Processing Application

Abstract

The field of approximate computing has garnered significant interest as a promising area for relatively error-resistant applications. At its core, approximate computing revolves around a trade-off between efficiency and accuracy. To optimize power consumption, delay, and area, a certain level of accuracy is sacrificed, provided it remains within acceptable limits. This research introduces a novel design for an approximate 4:2 compressor. Two distinct configurations for implementing this compressor are proposed and evaluated within the framework of an 8x8 Dadda multiplier. The study assesses both technology-dependent and technology-independent parameters, comparing them with the most recent approximate multipliers reported in recent literature. The performance of these multipliers is tested using a 45-nm standard CMOS technology node. Additionally, the quality and precision of the proposed approximate multiplier are evaluated using a range of statistical metrics. To demonstrate their practical utility, the proposed multipliers are applied to image processing tasks. The results indicate that the proposed designs outperform existing approximate multipliers in terms of efficiency for image processing applications.