Accelerated Atomistic Modeling of Phase Change Memory Using Deep Neural Network and Specialized Hardware

ZY Zhao and JH Li and PH Mo and X Zhang and J Liu, IEEE JOURNAL OF THE ELECTRON DEVICES SOCIETY, 13, 1026-1030 (2025).

DOI: 10.1109/JEDS.2025.3604839

Atomistic simulations offer valuable insights into phase change memory (PCM) device research and development. Current methods, such as density functional theory (DFT) and machine learning interatomic potential (ML- IAP), face limitations in device-scale modeling. DFT achieves a time-to- solution (eta(t))approximate to 10(-2) s/step/atom and an energy-to- solution (eta(p))approximate to 10(1) J/step/atom. State-of-the-art ML- IAPs, accelerated by GPUs, achieve eta(t)approximate to 10(-6) s/step/atom and eta(p)approximate to 10(-3) J/step/atom. We present a more efficient method that integrates deep neural network (DNN) with a special-purpose hardware accelerator, achieving eta(t)approximate to 10(-7) s/step/atom and eta(p)approximate to 10(-5) J/step/atom. Our method offers a powerful tool for high-throughput screening of PCM design possibilities (e.g., doping, interfaces), within practical time and energy consumption.

Return to Publications page