TechRxiv
article_ieee.pdf (490.93 kB)
Download file

A Non-Volatile All-Spin Analog Matrix Multiplier: An Efficient Hardware Accelerator for Machine Learning

Download (490.93 kB)
preprint
posted on 26.09.2021, 06:42 by Supriyo BandyopadhyaySupriyo Bandyopadhyay, Rahnuma Rahman
We propose and analyze a compact and non-volatile nanomagnetic (all-spin) analog matrix multiplier performing the multiply-and-accumulate (MAC) operation using two magnetic tunnel junctions – one activated by strain to act as the multiplier, and the other activated by spin-orbit torque pulses to act as a domain wall synapse that performs the operation of the accumulator. Each MAC operation can be performed in ~1 ns and the maximum energy dissipated per operation is ~100 aJ. This provides a very useful hardware accelerator for machine learning (e.g. training of deep neural networks), solving combinatorial optimization problems with Ising type machines, and other artificial intelligence tasks which often involve the multiplication of large matrices. The non-volatility allows the matrix multiplier to be embedded in powerful non-von-Neumann architectures.

Funding

NSF CCF-2001255

NSF CCF-2006843

History

Email Address of Submitting Author

sbandy@vcu.edu

ORCID of Submitting Author

0000-0001-6074-1212

Submitting Author's Institution

Virginia Commonwealth University

Submitting Author's Country

United States of America

Usage metrics

Licence

Exports