摘要
由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-人工智能的新数据在一份新的报告中呈现。根据NewsRx编辑对新加坡国立大学的新闻报道，研究表明：“晶体管进步成功的关键在于准确地使用失效分析(FA)，它适用于制造工艺的微调和优化。然而，随着器件尺寸、结构和材料复杂性的急剧扩大，芯片制造商面临着几个FA挑战。”新闻记者从新加坡国立大学的研究中得到一句话：“为了保持可制造性，我们可以在芯片加工和设计的所有步骤中加速缺陷识别。另一方面，随着技术规模在纳米节点以下，器件对无法避免的工艺诱导的变异性更加敏感。因此，金属缺陷和工艺诱导的D变异需要在芯片缩放的背景下同时处理，因此应该开发出将这些影响解耦的故障诊断方法。摘要:针对一个6t-sram位元单元,利用SPICE电路仿真和基于机器学习的物理建模相结合的方法,设计了一个基于SPICE电路仿真的电路桥缺陷自动识别系统。对于模型的特征描述符，电路的对称性和基本材料特性被利用：金属S（半导体）在一定电压范围内具有正（负）电阻温度系数。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on artificial intelligence are presented in a new report. According to news reporting out of National Unive rsity of Singapore by NewsRx editors, research stated, “Integral to the success of transistor advancements is the accurate use of failure analysis (FA) which be nefits in fine-tuning and optimization of the fabrication processes. However, th e chip makers face several FA challenges as device sizes, structure, and materia l complexities scale dramatically.” The news journalists obtained a quote from the research from National University of Singapore: “To sustain manufacturability, one can accelerate defect identifi cation at all steps of the chip processing and design. On the other hand, as tec hnologies scale below the nanometer nodes, devices are more sensitive to unavoid able process-induced variability. Therefore, metallic defects and process-induce d variability need to be treated concurrently in the context of chip scaling, wh ile failure diagnostic methods to decouple the effects should be developed. Inde ed, the locating a defective component from thousands of circuits in a microchip in the presence of variability is a tedious task. This work shows how the SPICE circuit simulations coupled with machine learning based-physical modeling shoul d be effectively used to tackle such a problem for a 6T-SRAM bit cell. An automa tic bridge defect recognition system for such a circuit is devised by training a predictive model on simulation data. For feature descriptors of the model, the symmetry of the circuit and a fundamental material property are leveraged: metal s (semiconductors) have a positive (negative) temperature coefficient of resista nce up to a certain voltage range.”
NETL
NSTL