New Approximate 4:2 Compressor for High Accuracy and Small Area Using MUX Logic

Abstract

Approximate computing plays a key role in building energy-efficient high-performance digital systems, as much data and computation are required recently. This paper proposes a new approximate compressor that improves accuracy with faster computation performance. Through analyzing the error occurring cases in the truth table of the compressor, patterns were identified to extract a simplified logic. As a result of evaluating the performance through Vivado simulation, the proposed approximate compressor is operating 16% faster using 43% less power compared to the exact computation and the approximate multiplier using the compressor shows higher accuracy with reduced delay than other multiples.