4.6 Article

Antiferromagnetic Skyrmion Based Energy-Efficient Integrate-Fire Neuron Device

Journal

IEEE TRANSACTIONS ON ELECTRON DEVICES
Volume -, Issue -, Pages -

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TED.2023.3332700

Keywords

Micromagnetics; Neurons; Force; Nanoscale devices; Current density; Nanobioscience; Energy efficiency; Antiferromagnets; diode; integrate-fire (IF); interskyrmion repulsion; neuron; spin-orbit torque (SOT)

Ask authors/readers for more resources

Antiferromagnetic (AFM) skyrmion technology is considered a promising direction for the development of the next-generation spintronics-based neuromorphic computing due to its unique features. In this study, a neuron device based on AFM skyrmion is proposed, which demonstrates integrate fire functionality and generates an output signal on a nanotrack. The proposed device offers a 68% reduction in energy dissipation when the number of skyrmions on the nanotrack is increased from 1 to 3.
Antiferromagnetic (AFM) skyrmion technology holds great promise for the development of the next-generation spintronics-based neuromorphic computing due to its unique features. They offer negligible stray fields, resilience to external magnetic fields, ultra fast dynamics, and no skyrmion Hall effect (SkHE) due to zero net topological charge. These advantages make AFM skyrmions a more viable alternative for future spintronic applications compared to ferromagnetic (FM) skyrmions. In this study, a neuron device based on AFM skyrmion is proposed, which demonstrates the integrate fire (IF) functionality by utilizing a previously proposed AFM skyrmion-based diode device and the interskyrmion repulsion effect on the nanotrack. The threshold of the device, which is determined by the maximum number of skyrmions pinned near the device window, can be adjusted by manipulating the applied current density. The device generates an output signal when the primary skyrmion overcomes the device window and reaches the detection region. By increasing the threshold, the device's operating current density can be reduced, leading to improved energy efficiency. It is observed that the threshold current density is 4.6 GAm(-2), 2.3 GAm(-2), and 1.5 GAm(-2) for one, two, and three skyrmions, respectively, on a nanotrack. The minimum overall energy dissipation is estimated at 6.285 fJ. The proposed neuron device offers a 68% reduction in the energy dissipation when the number of skyrmions on a nanotrack is increased from 1 to 3, thus indicating the potential for developing energy-efficient devices in AFM spintronics for neuromorphic computing.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available