Ultraefficient imprecise multipliers based on innovative 4:2 approximate compressors

摘要

This study proposes two ultraefficient imprecise multipliers based on innovative 4:2 approximate compressor designs. The first proposed multiplier employs an ultracompact 8-transistor 4:2 compressor to reduce the transistor count and energy dissipation. To improve the accuracy of the first proposed imprecise multiplier, the second multiplier also benefits from a semiaccurate 24-transistor 4:2 approximate compressor for the high-order bits. The 7-nm fin field-effect transistor (FinFET) technology, as one of the leading commercial technologies, is utilized to simulate the proposed multipliers in theHSPICE (R) environment. The simulation results indicate that the proposed imprecise multipliers show significant improvements regarding transistor count, delay, power, and power-delay product as compared to their state-of-the-art imprecise and exact counterparts. Along with the superior hardware efficiency, the MATLAB simulations demonstrate that the proposed multipliers also provide reasonable levels of accuracy. Moreover, a figure of merit (FOM) considering hardware efficiency and output quality is considered in order to evaluate the multipliers comprehensively. The FOM simulation results indicate that the proposed imprecise multipliers make a significant trade-off between hardware efficiency and quality for approximate-computing applications dealing with image multiplication.