Current control of time-averaged magnetization in superparamagnetic tunnel junctions

Bapna, Mukund; Majetich, Sara A.

doi:10.1063/1.5012091

Cited by 32 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Asynchronous measurements are typically obtained for thermally unstable MTJs with < 20, where thermal fluctuations drive random switching between states, as illustrated in Fig. 2(d) [54], [55], [56], [57], [58]. These devices typically show random fluctuations near the switching fields, as illustrated in Fig.…”

Section: Tunable Stochasticity In Mtjsmentioning

confidence: 96%

Review of Magnetic Tunnel Junctions for Stochastic Computing

Zink

Wang

2022

IEEE J. Explor. Solid-State Comput. Devices Circuits

View full text Add to dashboard Cite

Modern computing schemes require large circuit areas and large energy consumption for neuromorphic computing applications, such as recognition, classification, and prediction. This is because these tasks require parallel processing on large datasets. Stochastic computing (SC) is a promising alternative to conventional binary computing schemes due to its low area cost, low processing power, and robustness to noise. However, the large area and energy costs for random number generation with CMOS-based circuits make SC impractical for most hardware implementations. For this reason, beyond-CMOS approaches to random number generation have been investigated in recent years. Spintronics is one of the most promising approaches due to the intrinsic stochasticity of the magnetic tunnel junction (MTJ). In this review article, we provide an overview of the literature published in recent years investigating the tunable, intrinsic stochasticity of MTJs and proposing practical methods for random number generation using spintronic hardware.INDEX TERMS Magnetic tunnel junctions (MTJs), random number generators (RNGs), spintronic devices, stochastic-bit generators (SBGs), stochastic computing (SC).

show abstract

Section: Tunable Stochasticity In Mtjsmentioning

confidence: 96%

Review of Magnetic Tunnel Junctions for Stochastic Computing

Zink

Wang

2022

IEEE J. Explor. Solid-State Comput. Devices Circuits

View full text Add to dashboard Cite

show abstract

“…The first modification is to replace the stable free layer with a low-barrier nanomagnet (E B ≪ 40kT ) that can be achieved by either reducing the total number of spins in the nanomagnet (by reducing M s Vol., where M s is the saturation magnetization and Vol. is the volume [Bapna and Majetich 2017]) or by using circular disk magnets that have no preferential easy-axis…”

Section: Embedded Mram Based Neuron As a Building Block For Rbmsmentioning

confidence: 99%

Composable Probabilistic Inference Networks Using MRAM-based Stochastic Neurons

Zand

Datta

DeMara

2019

J. Emerg. Technol. Comput. Syst.

View full text Add to dashboard Cite

Magnetoresistive random access memory (MRAM) technologies with thermally unstable nanomagnets are leveraged to develop an intrinsic stochastic neuron as a building block for restricted Boltzmann machines (RBMs) to form deep belief networks (DBNs). The embedded MRAM-based neuron is modeled using precise physics equations. The simulation results exhibit the desired sigmoidal relation between the input voltages and probability of the output state. A probabilistic inference network simulator (PIN-Sim) is developed to realize a circuit-level model of an RBM utilizing resistive crossbar arrays along with differential amplifiers to implement the positive and negative weight values. The PIN-Sim is composed of five main blocks to train a DBN, evaluate its accuracy, and measure its power consumption. The MNIST dataset is leveraged to investigate the energy and accuracy tradeoffs of seven distinct network topologies in SPICE using the 14nm HP-FinFET technology library with the nominal voltage of 0.8V, in which an MRAM-based neuron is used as the activation function. The software and hardware level simulations indicate that a 784 × 200 × 10 topology can achieve less than 5% error rates with ∼ 400p J energy consumption. The error rates can be reduced to 2.5% by using a 784 × 500 × 500 × 500 × 10 DBN at the cost of ∼ 10× higher energy consumption and significant area overhead. Finally, the effects of specific hardware-level parameters on power dissipation and accuracy tradeoffs are identified via the developed PIN-Sim framework.Additional Key Words and Phrases: Deep belief network (DBN), restricted Boltzmann machine (RBM), magnetoresistive random access memory (MRAM), stochastic binary neuron, resistive crossbar array

show abstract

“…Emerging spintronic devices have recently attracted attention for efficient implementation of more-than-Boolean computational systems such as neural networks 1 , Bayesian networks 2 – 4 , Ising networks 4 – 6 , and invertible logic 7 . Key to the implementation of such systems is the stochastic nature of the network building blocks 8 – 10 - nano-magnets in this demonstration – in response to an external stimulation. The desired output characteristics display a sigmoidal probability to find the nano-magnet in one or the other magnetization state – here as a function of an input current.…”

Section: Introductionmentioning

confidence: 99%

Spin-torque devices with hard axis initialization as Stochastic Binary Neurons

Ostwal

Debashis

Faria

et al. 2018

Sci Rep

View full text Add to dashboard Cite

Employing the probabilistic nature of unstable nano-magnet switching has recently emerged as a path towards unconventional computational systems such as neuromorphic or Bayesian networks. In this letter, we demonstrate proof-of-concept stochastic binary operation using hard axis initialization of nano-magnets and control of their output state probability (activation function) by means of input currents. Our method provides a natural path towards addition of weighted inputs from various sources, mimicking the integration function of neurons. In our experiment, spin orbit torque (SOT) is employed to “drive” nano-magnets with perpendicular magnetic anisotropy (PMA) -to their metastable state, i.e. in-plane hard axis. Next, the probability of relaxing into one magnetization state (+mi) or the other (−mi) is controlled using an Oersted field generated by an electrically isolated current loop, which acts as a “charge” input to the device. The final state of the magnet is read out by the anomalous Hall effect (AHE), demonstrating that the magnetization can be probabilistically manipulated and output through charge currents, closing the loop from charge-to-spin and spin-to-charge conversion. Based on these building blocks, a two-node directed network is successfully demonstrated where the status of the second node is determined by the probabilistic output of the previous node and a weighted connection between them. We have also studied the effects of various magnetic properties, such as magnet size and anisotropic field on the stochastic operation of individual devices through Monte Carlo simulations of Landau Lifshitz Gilbert (LLG) equation. The three-terminal stochastic devices demonstrated here are a critical step towards building energy efficient spin based neural networks and show the potential for a new application space.

show abstract

Current control of time-averaged magnetization in superparamagnetic tunnel junctions

Cited by 32 publications

References 18 publications

Review of Magnetic Tunnel Junctions for Stochastic Computing

Review of Magnetic Tunnel Junctions for Stochastic Computing

Composable Probabilistic Inference Networks Using MRAM-based Stochastic Neurons

Spin-torque devices with hard axis initialization as Stochastic Binary Neurons

Contact Info

Product

Resources

About