English(EN) Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate Model

AI模型加速铁电NAND保持分析，速度比TCAD快10000倍以上

作者 PulseAugur 编辑部 · [1 个来源] · 2026-04-28 04:00

研究人员开发了一种新颖的物理信息神经网络算子（PINO）模型，以加速铁电垂直NAND（Fe-VNAND）闪存中的数据保持分析。该AI代理模型整合了基本物理原理，与传统的工艺计算机辅助设计（TCAD）模拟相比，实现了超过10,000倍的速度提升。PINO框架能够准确预测阈值电压漂移和保持行为，为优化器件设计和实现可靠性感知模拟提供了重大进展。 AI

影响加速存储器器件的硬件仿真，实现更快的设计周期和优化。

排序理由这是一篇详细介绍用于硬件仿真的新AI模型的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Gyujun Jeong (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Sungwon Cho (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Minji Shon (School of Electrical and Computer En · 2026-04-28 04:00

Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate Model

arXiv:2603.06881v3 Announce Type: replace Abstract: Ferroelectric field-effect transistors (FeFET)-based vertical NAND (Fe-VNAND) has emerged as a promising candidate to overcome z-scaling limitations with lower programming voltages. However, the data retention of 3D Fe-VNAND is …

报道来源 [1]

Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate Model

相关实体

相关话题