In-Memory Massive MIMO Linear Detector Circuit with Extremely High Energy Efficiency and Strong Memristive Conductance Deviation Robustness

TL;DR

This paper introduces an energy-efficient, memristive crossbar array-based detector circuit for massive MIMO systems that is robust against conductance deviations, outperforming traditional digital processors in energy efficiency.

Contribution

It proposes a novel MCA-based detector circuit with robustness to conductance deviations, enhancing detection performance and energy efficiency in massive MIMO systems.

Findings

The proposed detector circuit outperforms conventional MCA-based detectors.

Energy efficiency surpasses traditional digital processors by tens to hundreds of times.

Robustness to conductance deviations improves detection reliability.

Abstract

The memristive crossbar array (MCA) has been successfully applied to accelerate matrix computations of signal detection in massive multiple-input multiple-output (MIMO) systems. However, the unique property of massive MIMO channel matrix makes the detection performance of existing MCA-based detectors sensitive to conductance deviations of memristive devices, and the conductance deviations are difficult to be avoided. In this paper, we propose an MCA-based detector circuit, which is robust to conductance deviations, to compute massive MIMO zero forcing and minimum mean-square error algorithms. The proposed detector circuit comprises an MCA-based matrix computing module, utilized for processing the small-scale fading coefficient matrix, and amplifier circuits based on operational amplifiers (OAs), utilized for processing the large-scale fading coefficient matrix. We investigate the impacts of the open-loop gain of OAs, conductance mapping scheme, and conductance deviation level on detection performance and demonstrate the performance superiority of the proposed detector circuit over the conventional MCA-based detector circuit. The energy efficiency of the proposed detector circuit surpasses that of a traditional digital processor by several tens to several hundreds of times.