A new technical titled “Impact of Random Phase Distribution on Ferroelectric Tunnel Field-Effect Transistors With Mitigation Strategies for Compute-in-Memory Applications” was published by researchers at Seoul National University.
Abstract
“This work presents, for the first time, an investigation of the impact of random phase distribution on ferroelectric (FE) tunnel field-effect transistors (FeTFETs). Due to localized band-to-band tunneling, FeTFETs exhibit severe device-to-device variation in memory window, subthreshold swing, and on-current. To mitigate this variability, we propose a metal–FE–metal–insulator–semiconductor (MFMIS) structure, which employs a floating gate to equalize the channel potential and ensure uniform electrical characteristics. System-level simulations demonstrate that a single MFMIS FeTFET configuration achieves binary neural network accuracy comparable to that of dual-FeFETs, while providing superior energy and area efficiency. Thus, MFMIS FeTFETs offer a scalable and energy-efficient solution for compute-in-memory hardware.”
Find the technical paper here. Published January 2026.
J. Park, J. Yeom, J. W. Lee, M. Ryu, C. Park and W. Y. Choi, “Impact of Random Phase Distribution on Ferroelectric Tunnel Field-Effect Transistors With Mitigation Strategies for Compute-in-Memory Applications,” in IEEE Access, vol. 14, pp. 8610-8617, 2026, doi: 10.1109/ACCESS.2026.3653121.
Leave a Reply