An Approximate-Computing-Based Adaptive Equalizer for Polarization Mode Dispersion

Abstract

Computational complexity is the most significant defect of coherent optical communication, which consumes a large area and leads to high power consumption, especially for the adaptive filter used for polarization mode dispersion (PMD). In this paper, we implement a 9-tap intro-polarization and 1-tap inter-polarization equalizer, which reduces 34.4% multiplication of the conventional structure. Besides, we proposed an approximate multiplier to save 44.6% full adder. Under the QPSK modulation, the proposed equalizer has a throughput of 114Gb/s and a power of 463mW at 1.786GHz. Synthesis shows that the area of the proposed 16-way parallel adaptive equalizer is 0.365mm2 with a 28 nm process, which has an improvement of 27.86% in area, and 37.88% in energy efficiency to the fix-point structure.