EPIC: Efficient prediction of IC manufacturing hotspots with a unified meta-classification formulation
Design Automation Conference（2014）
摘要
In this paper we present EPIC, an efficient and effective predictor for IC manufacturing hotspots in deep sub-wavelength lithography. EPIC proposes a unified framework to combine different hotspot detection methods together, such as machine learning and pattern matching, using mathematical programming/optimization. EPIC algorithm has been tested on a number of industry benchmarks under advanced manufacturing conditions. It demonstrates so far the best capability in selectively combining the desirable features of various hotspot detection methods (3.5-8.2% accuracy improvement) as well as significant suppression of the detection noise (e.g., 80% false-alarm reduction). These characteristics make EPIC very suitable for conducting high performance physical verification and guiding efficient manufacturability friendly physical design.
更多查看译文
关键词
detection noise suppression,unified meta-classification formulation,lithography hotspots,integrated circuit manufacture,design for manufacturability,photolithography,mathematical programming,pattern matching,pattern classification,circuit optimisation,meta classification,machine learning,hotspot detection methods,deep sub-wavelength lithography,epic effective predictor algorithm,mathematical programming-optimization,integrated circuit design,ic manufacturing hotspots,electronic engineering computing,design for manufacture,lithography,layout,calibration,physical design,accuracy
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要