Multi-state MRAM cells for hardware neuromorphic computing.

Magnetic tunnel junctions (MTJ) have been successfully applied in various sensing application and digital information storage technologies. Currently, a number of new potential applications of MTJs are being actively studied, including high-frequency electronics, energy harvesting or random number generators. Recently, MTJs have been also proposed in designs of new platforms for unconventional or bio-inspired computing. In the current work, we present a complete hardware implementation design of a neural computing device that incorporates serially connected MTJs forming a multi-state memory cell can be used in a hardware implementation of a neural computing device. The main purpose of the multi-cell is the formation of quantized weights in the network, which can be programmed using the proposed electronic circuit. Multi-cells are connected to a CMOS-based summing amplifier and a sigmoid function generator, forming an artificial neuron. The operation of the designed network is tested using a recognition of hand-written digits in 20 [Formula: see text] 20 pixels matrix and shows detection ratio comparable to the software algorithm, using weights stored in a multi-cell consisting of four MTJs or more. Moreover, the presented solution has better energy efficiency in terms of energy consumed per single image processing, as compared to a similar design.

Understanding stability diagram of perpendicular magnetic tunnel junctions.

Perpendicular magnetic tunnel junctions (MTJ) with a bottom pinned reference layer and a composite free layer (FL) are investigated. Different thicknesses of the FL were tested to obtain an optimal balance between tunneling magnetoresistance (TMR) ratio and perpendicular magnetic anisotropy. After annealing at 400 °C, the TMR ratio for 1.5 nm thick CoFeB sublayer reached 180% at room temperature and 280% at 20 K with an MgO tunnel barrier thickness corresponding to the resistance area product RA = 10 Ohmµm2. The voltage vs. magnetic field stability diagrams measured in pillar-shaped MTJs with 130 nm diameter indicate the competition between spin transfer torque (STT), voltage controlled magnetic anisotropy (VCMA) and temperature effects in the switching process. An extended stability phase diagram model that takes into account all three effects and the effective damping measured independently using broadband ferromagnetic resonance technique enabled the determination of both STT and VCMA coefficients that are responsible for the FL magnetization switching.