PROJECT TITLE :

Approximate Sum-of-Products Designs Based on Distributed Arithmetic - 2018

ABSTRACT:

Approximate circuits give high performance and need low power. Total-of-products (SOP) units are key components in many Digital Signal Processing applications. In this brief, 3 approximate SOP (ASOP) models that are primarily based on the distributed arithmetic are proposed. They are designed for different levels of accuracy. 1st model of ASOP achieves an improvement up to 64percent on area and 70% on power, compared with standard unit. Alternative two models offer an improvement of 32% and 48percent on area and 54% and 58% on power, respectively, with a reduced error rate compared with the first model. Third model achieves the mean relative error and normalized error distance as low as 0.05% and zero.009%, respectively. Performance of approximate units is evaluated with a loud image smoothing application, where the proposed models are capable of achieving higher peak signal-to-noise ratio than the present state-of-the-art techniques. It's shown that the proposed approximate models achieve higher processing accuracy than existing works however with important enhancements in power and performance.