In neuromorphic computing, artificial synapses provide a multi‐weight (MW) conductance state that is set based on inputs from neurons, analogous to the brain. Herein, artificial synapses based on magnetic materials that use a magnetic tunnel junction (MTJ) and a magnetic domain wall (DW) are explored. By fabricating lithographic notches in a DW track underneath a single MTJ, 3–5 stable resistance states that can be repeatably controlled electrically using spin‐orbit torque are achieved. The effect of geometry on the synapse behavior is explored, showing that a trapezoidal device has asymmetric weight updates with high controllability, while a rectangular device has higher stochasticity, but with stable resistance levels. The device data is input into neuromorphic computing simulators to show the usefulness of application‐specific synaptic functions. Implementing an artificial neural network (NN) applied to streamed Fashion‐MNIST data, the trapezoidal magnetic synapse can be used as a metaplastic function for efficient online learning. Implementing a convolutional NN for CIFAR‐100 image recognition, the rectangular magnetic synapse achieves near‐ideal inference accuracy, due to the stability of its resistance levels. This work shows MW magnetic synapses are a feasible technology for neuromorphic computing and provides design guidelines for emerging artificial synapse technologies.

There are pressing problems with traditional computing, especially for accomplishing data-intensive and real-time tasks, that motivate the development of in-memory computing devices to both store information and perform computation 1 . Magnetic tunnel junction (MTJ) memory elements can be used for computation by manipulating a domain wall (DW), a transition region between magnetic domains. Three leading device types that use MTJs and DWs for in-memory computing are majority logic 2-4 , mLogic 5-9 , and DW-MTJs 10-14 . But, these devices have suffered from challenges: spin transfer torque (STT) switching of a DW requires high current, and the multiple etch steps needed to create an MTJ pillar on top of a DW track has led to reduced tunnel magnetoresistance (TMR) 15-16 . These issues have limited experimental study of devices and circuits. Here, we study prototypes of three-terminal domain wall-magnetic tunnel junction (DW-MTJ) in-memory computing devices that can address data processing bottlenecks and resolve these challenges by using perpendicular magnetic anisotropy (PMA), spin-orbit torque (SOT) switching, and an optimized lithography process to produce average device tunnel magnetoresistance TMR = 164%, resistance-area product RA = 31 𝛀 − 𝝁𝒎 𝟐 , close to the RA of the unpatterned film, and lower switching current density compared to using spin transfer torque. A two-device circuit shows bit propagation between devices. Device initialization variation in switching voltage is shown to be curtailed to 7% by controlling the DW initial position, which we show corresponds to 96% accuracy in a DW-MTJ full adder simulation. These results make strides in using MTJs and DWs for in-memory and neuromorphic computing applications.Computing today faces walls when processing data-intensive and unstructured tasks. Memory access in modern computers can dominate as much as 96% of computing time 17 . SRAM idle leakage can consume over 20% of the total power of a computation 18,19 . For internet of things

In neuromorphic computing, artificial synapses provide a multi-weight conductance state that is set based on inputs from neurons, analogous to the brain. Additional properties of the synapse beyond multiple weights can be needed, and can depend on the application, requiring the need for generating different synapse behaviors from the same materials. Here, we measure artificial synapses based on magnetic materials that use a magnetic tunnel junction and a magnetic domain wall. By fabricating lithographic notches in a domain wall track underneath a single magnetic tunnel junction, we achieve 4-5 stable resistance states that can be repeatably controlled electrically using spin orbit torque. We analyze the effect of geometry on the synapse behavior, showing that a trapezoidal device has asymmetric weight updates with high controllability, while a straight device has higher stochasticity, but with stable resistance levels. The device data is input into neuromorphic computing simulators to show the usefulness of application-specific synaptic functions. Implementing an artificial neural network applied on streamed Fashion-MNIST data, we show that the trapezoidal magnetic synapse can be used as a metaplastic function for efficient online learning. Implementing a convolutional neural network for CIFAR-100 image recognition, we show that the straight magnetic synapse achieves near-ideal inference accuracy, due to the stability of its resistance levels. This work shows multi-weight magnetic synapses are a feasible technology for neuromorphic computing and provides design guidelines for emerging artificial synapse technologies.

No abstract

No abstract