# Nonvolatile Spintronic Memory Cells for Neural Networks

## TL;DR

This paper introduces a novel nonvolatile spintronic memory cell designed for neural networks, demonstrating improved energy efficiency and performance in image classification tasks through simulation-based evaluation.

## Contribution

It proposes a new spintronic memory cell architecture and a dual-circuit neural network design that leverages these devices for efficient neural computing.

## Key findings

- Spintronic cells outperform charge-based counterparts in energy efficiency.
- The proposed architecture achieves about 100 pJ per image processing.
- Simulations show effective classification performance with varying nanomagnet parameters.

## Abstract

A new spintronic nonvolatile memory cell analogous to 1T DRAM with non-destructive read is proposed. The cells can be used as neural computing units. A dual-circuit neural network architecture is proposed to leverage these devices against the complex operations involved in convolutional networks. Simulations based on HSPICE and Matlab were performed to study the performance of this architecture when classifying images as well as the effect of varying the size and stability of the nanomagnets. The spintronic cells outperform a purely charge-based implementation of the same network, consuming about 100 pJ total per image processed.