Unconventional computing based on magnetic tunnel junction

Abstract

The conventional computing method based on the von Neumann architecture is limited by a series of problems such as high energy consumption, finite data exchange bandwidth between processors and storage media, etc., and it is difficult to achieve higher computing efficiency. A more efficient unconventional computing architecture is urgently needed to overcome these problems. Neuromorphic computing and stochastic computing have been considered to be two competitive candidates for unconventional computing, due to their extraordinary potential for energy-efficient and high-performance computing. Although conventional electronic devices can mimic the topology of the human brain, these require high power consumption and large area. Spintronic devices represented by magnetic tunnel junctions (MTJs) exhibit remarkable high-energy efficiency, non-volatility, and similarity to biological nervous systems, making them one of the promising candidates for unconventional computing. In this work, we review the fundamentals of MTJs as well as the development of MTJ-based neurons, synapses, and probabilistic-bit. In the section on neuromorphic computing, we review a variety of neural networks composed of MTJ-based neurons and synapses, including multilayer perceptrons, convolutional neural networks, recurrent neural networks, and spiking neural networks, which are the closest to the biological neural system. In the section on stochastic computing, we review the applications of MTJ-based p-bits, including Boltzmann machines, Ising machines, and Bayesian networks. Furthermore, the challenges to developing these novel technologies are briefly discussed at the end of each section.

Direct design of ground-state probabilistic logic using many-body interactions for probabilistic computing

“…The advent of tunably stochastic nanodevices, colloquially known as probabilistic bits (p-bits), has injected new vitality into the development of this field. These p-bit devices, represented by stochastic magnetic tunnel junctions 5 – 11 , are characterized by their intrinsic stochasticity and the capability for rapid fluctuations on sub-nanosecond timescales 12 , 13 . These unique properties make p-bits ideally suited to serve as the fundamental building blocks for probabilistic logic networks, enabling the efficient exploration of vast solution spaces and the solving of hard computational problems.…”

Artificial Neuron Based on the Bloch-Point Domain Wall in Ferromagnetic Nanowires

“…While joule heating, speed, and scalability are among the main challenges for neuromorphic elements based on resistive switching [4], spin-based data processing could offer scalability, sub-nanosecond speeds, and low dissipation if the operation is mediated by spin waves. Systems utilizing spintronics nanostructures for non-conventional computing currently include magnetic tunnel junctions for neuromorphic [5] or stochastic [6] computing (see [7] for a recent review), spin wave logics [8,9] and lithographically patterned nanowires [10]. In magnetic nanostructures, information can be encoded and processed by using magnetic signals detected through electromagnetic induction or tunneling magnetoresistance and manipulated using spin torque [10].…”

Weighted spin torque nano-oscillator system for neuromorphic computing

“…Different types of devices can be used to implement synapses and neurons 29 , 30 . More specifically, neurons have been implemented using a wide range of MTJ micropillars and nanopillars: Using MTJs nanopillars with footprints as low as 0.008 µm 2 as rectifiers requires modest RF inputs of 32 µW and results in small DC outputs of 0.2 nW 22 .…”