4.8 Article

Ultralow Energy Domain Wall Device for Spin- Based Neuromorphic Computing

Journal

ACS NANO
Volume -, Issue -, Pages -

Publisher

AMER CHEMICAL SOC
DOI: 10.1021/acsnano.2c09744

Keywords

artificial intelligence; neuromorphic computing; spin-orbit torque; dual W; pinning field; domain wall motion

Ask authors/readers for more resources

Neuromorphic computing is a potential technology for low power intelligent devices. Spintronics-based neurons and synapses have higher endurance. By engineering the beta-W spin-orbit coupling material, we achieved low energy domain wall motion. The energy consumption for moving the domain wall is 27 aJ/bit, showing the potential for ultralow energy spin-based neuromorphic elements.
Neuromorphic computing (NC) is gaining wide acceptance as a potential technology to achieve low power intelligent devices. To realize NC, researchers investigate various types of synthetic neurons and synaptic devices, such as memristors and spintronic devices. In comparison, spintronics-based neurons and synapses have potentially higher endurance. However, for realizing low-power devices, domain wall (DW) devices that show DW motion at low energies -typically below pJ/bit-are favored. Here, we demonstrate DW motion at current densities as low as 106 A/m2 by engineering the beta-W spin-orbit coupling (SOC) material. With our design, we achieve ultralow pinning fields and current density reduction by a factor of 104. The energy required to move the DW by a distance of about 18.6 mu m is 0.4 fJ, which translates into the energy consumption of 27 aJ/bit for a bit-length of 1 mu m. With a meander DW device configuration, we have established a controlled DW motion for synapse applications and have shown the direction to make ultralow energy spin-based neuromorphic elements.

Authors

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

Reviews

Primary Rating

4.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available