MRAM-based Analog Sigmoid Function for In-memory Computing

TL;DR

This paper introduces a novel analog neuron circuit using SOT-MRAM devices that significantly reduces power and area for in-memory computing, enabling more efficient neural network implementations.

Contribution

The paper presents a new SOT-MRAM based analog sigmoid neuron design that integrates seamlessly with memristive crossbars, improving power, area, and speed over existing methods.

Findings

Power consumption reduced by up to 27 times

Area reduced by up to 4931 times

Achieves over 13 times energy savings in in-memory computing

Abstract

We propose an analog implementation of the transcendental activation function leveraging two spin-orbit torque magnetoresistive random-access memory (SOT-MRAM) devices and a CMOS inverter. The proposed analog neuron circuit consumes 1.8-27x less power, and occupies 2.5-4931x smaller area, compared to the state-of-the-art analog and digital implementations. Moreover, the developed neuron can be readily integrated with memristive crossbars without requiring any intermediate signal conversion units. The architecture-level analyses show that a fully-analog in-memory computing (IMC) circuit that use our SOT-MRAM neuron along with an SOT-MRAM based crossbar can achieve more than 1.1x, 12x, and 13.3x reduction in power, latency, and energy, respectively, compared to a mixed-signal implementation with analog memristive crossbars and digital neurons. Finally, through cross-layer analyses, we provide a guide on how varying the device-level parameters in our neuron can affect the accuracy of multilayer perceptron (MLP) for MNIST classification.