Search

Nanoelectromechanical (NEM) switches offer the advantages of zero OFF-state leakage current, abrupt switching characteristics, nonvolatile (NV) operation, and relatively low ON-state resistance as compared with CMOS transistors predominantly used for digital computing today. NEM switches can be implemented using metallic interconnect layers formed in the back-end-of-line (BEOL) steps of a standard CMOS IC manufacturing process, in order to enable compact implementation of hybrid CMOS-NEM circuits. In this article, a release-etch method is developed for realizing BEOL NV-NEM switches with $\leq 100$ -nm contact gaps. A functional array of BEOL NV-NEM switches is used to implement a hybrid CMOS-NEM IC for data search applications. NV-NEM switch design optimization to minimize the programming voltage and accelerate switching speed is discussed. A scaled NV-NEM technology is projected to be advantageous for high-speed, low-power reconfigurable computing applications. This projection is validated with experimental data for a BEOL NV-NEM switch implemented with a conventional 16-nm CMOS IC manufacturing process. [ABSTRACT FROM AUTHOR]

The current-induced perpendicular magnetic anisotropy magnetic tunnel junctions (p-MTJs) offer a number of advantages, such as high density and high speed. As p-MTJs downscale to $\sim 40$ nm, further performance enhancements can be realized thanks to high spin-torque efficiency, i.e., lower critical current density and higher thermal stability. In this paper, we investigate the origin of high spin-torque efficiency and give a phenomenological theory to describe the critical current reduction due to the subvolume activation. Based on various physical theories and structural parameters, a compact model of nanoscale MTJ is developed and demonstrates a satisfactory agreement with experimental results. Dynamic, static, and stochastic switching behaviors have been addressed and validated. Then, we perform mixed simulations for hybrid MTJ/CMOS read/write circuits, magnetic random access memory, and magnetic flip-flop to evaluate their performance. Analyses of energy consumption are given to show the prospect of MTJ technology node miniaturization. [ABSTRACT FROM AUTHOR]