Computing with injection-locked spintronic diodes
arXiv:2201.04724 · doi:10.1103/PhysRevApplied.17.014045
Abstract
Spintronic diodes (STDs) are emerging as a technology for the realization of high-performance microwave detectors. The key advantages of such devices are their high sensitivity, capability to work at low input power, and compactness. In this work, we show a possible use of STDs for neuromorphic computing expanding the realm of their functionalities to implement analog multiplication, which is a key operation in convolutional neural networks (CNN). In particular, we introduce the concept of degree of rectification (DOR) in injection-locked STDs. Micromagnetic simulations are used to design and identify the working range of the STDs for the implementation of the DOR. Previous experimental data confirm the applicability of the proposed solution, which is tested in image processing and in a CNN that recognizes handwritten digits.
arXiv comment21 pages, 6 figures, supplemental material includes 4 figures
References in corpus (12)
- Parallel convolution processing using an integrated photonic tensor core
- Currents, Torques, and Polarization Factors in Magnetic Tunnel Junctions
- Ultralow-current-density and bias-field-free spin-transfer nano-oscillator
- Giant spin-torque diode sensitivity at low input power in the absence of bias magnetic field
- Spin torque resonant vortex core expulsion for an efficient radio-frequency detection scheme
- Micromagnetic modeling of Terahertz oscillations in an antiferromagnetic material driven by spin-Hall effect
- Oscillatory transient regime in the forced dynamics of a spin torque nano-oscillator
- Perspectives on spintronic diodes
- Electrically tunable detector of THz-frequency signals based on an antiferromagnet
- Radio-Frequency Multiply-And-Accumulate Operations with Spintronic Synapses
- Low Power Microwave Signal Detection With a Spin-Torque Nano-Oscillator in the Active Self-Oscillating Regime
- Reliability of Neural Networks Based on Spintronic Neurons