Nonlinearity Modulation of Auto-oscillations in Three-terminal Magnetic Tunnel Junctions

TL;DR

This paper investigates how various factors such as magnetic field, layer thickness, and spin torques influence the nonlinearity in three-terminal magnetic tunnel junction spin torque nano-oscillators, aiming to optimize their microwave and neuromorphic applications.

Contribution

It provides a comprehensive analysis of nonlinearity modulation in MTJ-STNOs, including a new model incorporating spin-orbit torque effects for better control and miniaturization.

Findings

Nonlinearity can be tuned by magnetic field direction and CoFeB layer thickness.

Zero nonlinearity achieved at 1.1 nm CoFeB thickness.

Electrical modulation of nonlinearity via spin-transfer and spin-orbit torques.

Abstract

Spin torque nano-oscillators (STNOs) hold encouraging promise for nanoscale microwave generators, modulators, and new types of intelligent computing. The nonlinearity, describing the current-induced tunability of oscillating frequency, is a distinctive feature of STNOs, which plays important roles in efficient manipulation of microwave frequencies, rapid spec-trum analysis, and the design of neuromorphic devices. However, experimental research on its efficient modulation remains limited. Here, we comprehensively studied the impact of several factors on nonlinearity in nanoscale three-terminal MTJ-STNOs, including the external magnetic field, the thickness of CoFeB free layer, and the combination of spin-transfer torque (STT) and spin-orbit torque (SOT). Among these factors, nonlinearity can be significantly tuned by the direction of magnetic field as well as the thickness of CoFeB free layer. Notably, it reaches zero in 1.1 nm CoFeB, where the oscillation frequency is not affected by the drive current. Such property provides a more intrinsic and robust approach to achieve zero nonlinearity in STNOs, which is advantageous for high-quality microwave generators. More importantly, we found that nonlinearity can also be electrically modulated by both STT and SOT currents, and develop a refined model that accounts for the additional contribution of the SOT current to explain the mechanism. This electrical approach is more convenient, energy-efficient, and well-suited for miniaturization. Our findings offer a comprehensive understanding and open up a new dimension for the current tunability of nonlinearity in MTJ-STNOs, benefiting further optimization in nanoscale STNO-based microwave generators and neuromorphic computing devices.