Retargeting-aware design for manufacturability (DFM) checks using machine learning

Geometrical positioning surveying-based features for BEOL line-end-pull-back modeling using regression-based machine-learning

“…Design-formanufacturability (DFM) checks are part of IC physical verification and can be defined as conservative rules checks beyond DRC that provide additional fabrication process margin to IC designers. Wang et al 9 incorporated 17 localized geometrical features for metal-via LE patterns with multi-layer perceptron (MLP) neural network (NN) architecture to check for metal-via enclosure DFM violations. The aim of this model is to aid the IC design process and fix potential DFM violations before manufacturing.…”

“…Although Ref. 9 presented a mixture of density features and localized extracted geometrical features to represent layout patterns, the list of extracted features still ignores several descriptive details about the contextual patterns, such as corners and internal and external spacings. To address this problem, we present a novel edge-based approach named geometrical positioning surveying (GPS) 30 to represent the layout POIs and their surrounding context of patterns.…”