1. Ferroelectrically-enhanced Schottky barrier transistors for Logic-in-Memory applications
- Author
-
Nazzari, Daniele, Wind, Lukas, Sistani, Masiar, Mayr, Dominik, Kim, Kihye, and Weber, Walter M.
- Subjects
Physics - Applied Physics ,Computer Science - Emerging Technologies - Abstract
Artificial neural networks (ANNs) have had an enormous impact on a multitude of sectors, from research to industry, generating an unprecedented demand for tailor-suited hardware platforms. Their training and execution is highly memory-intensive, clearly evidencing the limitations affecting the currently available hardware based on the von Neumann architecture, which requires frequent data shuttling due to the physical separation of logic and memory units. This does not only limit the achievable performances but also greatly increases the energy consumption, hindering the integration of ANNs into low-power platforms. New Logic in Memory (LiM) architectures, able to unify memory and logic functionalities into a single component, are highly promising for overcoming these limitations, by drastically reducing the need of data transfers. Recently, it has been shown that a very flexible platform for logic applications can be realized recurring to a multi-gated Schottky-Barrier Field Effect Transistor (SBFET). If equipped with memory capabilities, this architecture could represent an ideal building block for versatile LiM hardware. To reach this goal, here we investigate the integration of a ferroelectric Hf$_{0.5}$Zr$_{0.5}$O$_2$ (HZO) layer onto Dual Top Gated SBFETs. We demonstrate that HZO polarization charges can be successfully employed to tune the height of the two Schottky barriers, influencing the injection behavior, thus defining the transistor mode, switching it between n and p-type transport. The modulation strength is strongly dependent on the polarization pulse height, allowing for the selection of multiple current levels. All these achievable states can be well retained over time, thanks to the HZO stability. The presented result show how ferroelectric-enhanced SBFETs are promising for the realization of novel LiM hardware, enabling low-power circuits for ANNs execution.
- Published
- 2024