TY - GEN
T1 - Hotspot Detection via Multi-task Learning and Transformer Encoder
AU - Zhu, Binwu
AU - Chen, Ran
AU - Zhang, Xinyun
AU - Yang, Fan
AU - Zeng, Xuan
AU - Yu, Bei
AU - Wong, Martin D.F.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - With the rapid development of semiconductors and the continuous scaling-down of circuit feature size, hotspot detection has become much more challenging and crucial as a critical step in the physical verification flow. In recent years, advanced deep learning techniques have spawned many frameworks for hotspot detection. However, most existing hotspot detectors can only detect defects arising in the central region of small clips, making the whole detection process time-consuming on large layouts. Some advanced hotspot detectors can detect multiple hotspots in a large area but need to propose potential defect regions, and a refinement step is required to locate the hotspot precisely. To simplify the procedure of multi-stage detectors, an end-to-end single-stage hotspot detector is proposed to identify hotspots on large scales without refining potential regions. Besides, multiple tasks are developed to learn various pattern topological features. Also, a feature aggregation module based on Transformer Encoder is designed to globally capture the relationship between different features, further enhancing the feature representation ability. Experimental results show that our proposed framework achieves higher accuracy over prior methods with faster inference speed.
AB - With the rapid development of semiconductors and the continuous scaling-down of circuit feature size, hotspot detection has become much more challenging and crucial as a critical step in the physical verification flow. In recent years, advanced deep learning techniques have spawned many frameworks for hotspot detection. However, most existing hotspot detectors can only detect defects arising in the central region of small clips, making the whole detection process time-consuming on large layouts. Some advanced hotspot detectors can detect multiple hotspots in a large area but need to propose potential defect regions, and a refinement step is required to locate the hotspot precisely. To simplify the procedure of multi-stage detectors, an end-to-end single-stage hotspot detector is proposed to identify hotspots on large scales without refining potential regions. Besides, multiple tasks are developed to learn various pattern topological features. Also, a feature aggregation module based on Transformer Encoder is designed to globally capture the relationship between different features, further enhancing the feature representation ability. Experimental results show that our proposed framework achieves higher accuracy over prior methods with faster inference speed.
UR - http://www.scopus.com/inward/record.url?scp=85124160091&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124160091&partnerID=8YFLogxK
U2 - 10.1109/ICCAD51958.2021.9643590
DO - 10.1109/ICCAD51958.2021.9643590
M3 - Conference contribution
AN - SCOPUS:85124160091
T3 - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
BT - 2021 40th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 40th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2021
Y2 - 1 November 2021 through 4 November 2021
ER -