Machine Learning-Based Hotspot Detection: Fallacies, Pitfalls and Marching Orders

Extensive technology scaling has not only increased the complexity of Integrated Circuit (IC) fabrication but also multiplied the challenges in the Design For Manufacturability (DFM) space. Among these challenges, detection of design weak-points, popularly known as Lithographic Hotspots, has attracted substantial attention. Hotspots are certain patterns which exhibit a higher probability of causing defects due to complex design-process interactions. Identifying such patterns and fixing them in the design stage itself is imperative towards ensuring high yield. In the early days of hotspot detection, Pattern Matching (PM) based methods were proposed. While effective in identifying previously known patterns, these methods failed to identify Never-Seen-Before (NSB) hotspots. To address this drawback, Machine Learning (ML) based solutions were introduced. Over the last decade, we have witnessed a plethora of ML-based hotspot detection methods being developed, each slightly outperforming its predecessors in accuracy and false-alarm rates. In this work, we critically analyze the ML-based hotspot detection literature and we highlight common fallacies which are found therein. We pinpoint the pitfalls in the ICCAD-2012 benchmarks that have led to these fallacies. We propose an enhanced version of this benchmark dataset, titled ICCAD-2019 benchmarks, which we deem more appropriate for accurately assessing hotspot detection methods. We offer our best recommendations /marching orders to improve the effectiveness of ML-based hotspot detection methods and experimentally demonstrate the effectiveness of the proposed methods in comparison to the stateof-the-art. Furthermore, we perform the first ever silicon validation of hotspots, wherein, we fabricate several hotspot patterns on silicon, study their electrical characteristics and propose a methodology to rank them. Through Early Design Space Exploration (EDSE), we also perform the first quantitative demonstration of early hotspot detection and TrulyNever-Seen-Before (TNSB) hotspot detection.