Nonvolatile Spintronic Memory Cells for Neural Networks

Andrew W. Stephan; Qiuwen Lou; Michael Niemier; X. Sharon Hu; Steven J. Koester

Nonvolatile Spintronic Memory Cells for Neural Networks

Emerging Technologies 2019-05-31 v1 Neural and Evolutionary Computing

Authors: Andrew W. Stephan , Qiuwen Lou , Michael Niemier , X. Sharon Hu , Steven J. Koester

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.

Keywords

memristor neuromorphic computing memory hierarchy

Cite

@article{arxiv.1905.12679,
  title  = {Nonvolatile Spintronic Memory Cells for Neural Networks},
  author = {Andrew W. Stephan and Qiuwen Lou and Michael Niemier and X. Sharon Hu and Steven J. Koester},
  journal= {arXiv preprint arXiv:1905.12679},
  year   = {2019}
}

Nonvolatile Spintronic Memory Cells for Neural Networks

Abstract

Keywords

Cite

Related papers