D
David Z. Pan
Researcher at University of Texas at Austin
Publications - 557
Citations - 12677
David Z. Pan is an academic researcher from University of Texas at Austin. The author has contributed to research in topics: Computer science & Routing (electronic design automation). The author has an hindex of 50, co-authored 496 publications receiving 10182 citations. Previous affiliations of David Z. Pan include University of California, Los Angeles & Fudan University.
Papers
More filters
Journal ArticleDOI
Methodology for Standard Cell Compliance and Detailed Placement for Triple Patterning Lithography
TL;DR: This paper proposes a coherent framework, including standard cell compliance and detailed placement to enable TPL friendly design, and shows that, with negligible impact on critical path delay, this framework can resolve the conflicts much more easily, compared with the traditional physical design flow and followed layout decomposition.
Proceedings ArticleDOI
Design for manufacturability and reliability for TSV-based 3D ICs
David Z. Pan,Sung Kyu Lim,Krit Athikulwongse,Moongon Jung,Joydeep Mitra,Jiwoo Pak,Mohit Pathak,Jae-Seok Yang +7 more
TL;DR: Some key design for manufacturability and reliability challenges and possible solutions for TSV-based 3D IC integration, as well as future research directions are discussed.
Proceedings ArticleDOI
LithoROC: lithography hotspot detection with explicit ROC optimization
TL;DR: This work proposes the use of the area under the ROC curve (AUC), which provides a more holistic measure for imbalanced datasets compared with the previous methods, and proposes the surrogate loss functions for direct AUC maximization as a substitute for the conventional cross-entropy loss.
Proceedings ArticleDOI
Wafer Map Defect Patterns Classification using Deep Selective Learning
TL;DR: This paper proposes a novel methodology for wafer map defect pattern classification using deep selective learning that features an integrated reject option where the model chooses to abstain from predicting a class label when misclassification risk is high, providing a trade-off between prediction coverage and mis classification risk.
Proceedings ArticleDOI
Hardware-software co-design of slimmed optical neural networks
Zheng Zhao,Derong Liu,Meng Li,Zhoufeng Ying,Lu Zhang,Biying Xu,Bei Yu,Ray T. Chen,David Z. Pan +8 more
TL;DR: This work designs a novel slimmed architecture for realizing optical neural network considering both its software and hardware implementations and shows a more area-efficient architecture which uses a sparse tree network block, a single unitary block and a diagonal block for each neural network layer.