Inexact Signed Wallace Tree Multiplier Design Using Reversible Logic

This paper proposes an inexact Baugh-Wooley Wallace tree multiplier with novel architecture for 4:2 compressor optimised realisation using reversible logic. The proposed has ±1 Error Distance (ED) and 12.5% Rate (ER). efficacy of the logic based is measured in scales Gate Count (GC), Quantum Cost (QC), Garbage Output (GO) Ancilla Input (AI). able to reduce metrics GC, QC, GO AI by 50%, 15%, 25% 11.11% as compared exact compressor. An 8 × implemented this paper. accuracy MED MRED are found be least among existing designs. 59.16 0.0109 respectively. utilised two applications 1) image processing - one level decomposition rationalised db6 wavelet filter bank smoothing 2) Convolutional Neural Networks (CNN). estimated measuring Structural Similarity Index Measure (SSIM) which 0.96 0.84 In CNN application, efficiency 97.1%.