Invited Paper: Ultra-Efficient Edge AI Using FeFET-based Monolithic 3D Integration

Monolithic three-dimensional (M3D) integration signifies a notable technological leap by providing solutions of high density and energy efficiency, particularly for ultra-efficient edge AI solutions. Among emerging technologies, ferroelectric thin-film transistors (FeTFTs) have attracted substantial interest due to their potential in neuromorphic computing and their compatibility with back-end-of-the-line (BEOL) fabrication processes. Nevertheless, the challenge of M3D integrated circuits lies in elevated temperatures resulting from limited heat dissipation across various stacked tiers, subsequently exerting adverse effects on system reliability. In this work, we explore how compute-in-memory (CIM) architectures can be realized using BEOL FeTFT to accelerate deep learning applications. We demonstrate how generated temperature impacts the reliability and ultimately degrade the inference accuracy. To achieve that, we have modified the open-source “3D+NeuroSim” framework to introduce FeTFT and then employed it to estimate the key figures of merit, such as throughput, power density, area, etc. Then, we perform a comprehensive thermal analysis for the simulated M3D architecture to explore how the DNN accuracy will be impacted due to the generated heat. We also demonstrate how FeTFT devices can be accurately modeled using TCAD simulations and how run-time variability (due to temperature effects) and design-time variability (due to process variation) impact the reliability of FeTFT transistors.