Skip to search formSkip to main contentSkip to account menu
DOI:10.1109/ICCAD51958.2021.9643458 - Corpus ID: 245129585
@article{Chen2021AUF, title={A Unified Framework for Layout Pattern Analysis with Deep Causal Estimation}, author={Ran Chen and Shoubo Hu and Zhitang Chen and Shengyu Zhu and Bei Yu and Pengyun Li and Cheng Chen and Yu Huang and Jianye Hao}, journal={2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)}, year={2021}, pages={1-9}, url={https://api.semanticscholar.org/CorpusID:245129585}}
- Ran Chen, Shoubo Hu, Jianye Hao
- Published in IEEE/ACM International… 1 November 2021
- Computer Science, Engineering
- 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)
A novel layout-aware diagnosis-based layout pattern analysis framework is proposed to identify the root cause efficiently and outperforms a commercial tool with higher accuracies and around x8.4 speedup on average.
6 Citations
3
1
Figures and Tables from this paper
- figure 1
- figure 10
- figure 11
- figure 2
- figure 3
- figure 4
- figure 5
- figure 6
- figure 7
- figure 8
- figure 9
- table I
- table II
- table III
- table IV
- table V
- table VI
Topics
Average Causal Effect (opens in a new tab)Layout Patterns (opens in a new tab)Systematic Defects (opens in a new tab)Speedup (opens in a new tab)Contrastive Learning (opens in a new tab)Structural Causal Model (opens in a new tab)Encoder Network (opens in a new tab)Clusters (opens in a new tab)
6 Citations
- Ran ChenShoubo Hu Jianye Hao
- 2023
Computer Science, Engineering
IEEE Transactions on Computer-Aided Design of…
A novel layout-aware diagnosis-based layout pattern analysis framework is proposed to identify the root cause efficiently and outperforms a commercial tool with higher accuracies and around $\times 8.4$ speedup on average.
- 2
- Highly Influenced
- PDF
- Hao GengHaoyu YangLu ZhangFan YangXuan ZengBei Yu
- 2022
Computer Science, Engineering
IEEE Transactions on Computer-Aided Design of…
This article develops a new end-to-end hotspot detection flow where layout feature embedding and hotspots detection are jointly performed and an attention mechanism-based deep convolutional neural network is exploited as the backbone to learn embeddings for layout features and classify the hotspots simultaneously.
- PDF
- Xiaopeng ZhangShoubo Hu Jianye Hao
- 2022
Engineering, Computer Science
2022 IEEE International Test Conference (ITC)
RCANet is developed, an end-to-end unsupervised learning-based RCA framework, which analyses diagnosis reports of failing dies within a wafer and identifies both layout-aware and cell-internal root causes efficiently.
- Zehua PeiWenqian ZhaoZhuolun HeBei Yu
- 2023
Computer Science, Engineering
2023 International Symposium of Electronics…
This paper proposes several quantization algorithms specifically designed for a classic neural network based hotspot detector while taking into account the feature distribution of the dataset used, and shows that they can achieve competitive results compared with full-precision models while significantly reducing inference runtime at the same time.
- PDF
- Hao GengQi SunTinghuan ChenQi XuTsung-Yi HoBei Yu
- 2023
Engineering, Computer Science
2023 28th Asia and South Pacific Design…
This paper will survey the recent pace of progress on advanced methodologies for wafer failure pattern recognition, especially for mixed-type one, and hopes this literature review can highlight the future directions and promote the advancement of the waferFailure pattern recognition.
- 1
- PDF
- Hao GengTinghuan ChenQi SunBei Yu
- 2022
Engineering, Computer Science
2022 27th Asia and South Pacific Design…
This paper will survey the recent pace of progress on advanced parameter auto-tuning flows of physical synthesis tools to reduce human cost and tool evaluation cost and hopes this survey can enlighten the future development of parameterAuto- Tuning methodologies.
- 4
- PDF
30 References
- Haoyu YangJing SuY. ZouBei YuEvangeline F. Y. Young
- 2017
Computer Science, Engineering
2017 54th ACM/EDAC/IEEE Design Automation…
A deep learning framework for high performance and large scale hotspot detection is developed and a biased learning algorithm is proposed to train the convolutional neural network to further improve detection accuracy with small false alarm penalties.
- 107
- PDF
- Wu-Tung ChengR. Klingenberg Atul Chittora
- 2017
Computer Science, Engineering
2017 IEEE 26th Asian Test Symposium (ATS)
in many cases, the main cause of yield loss is a specific layout pattern that is difficult to manufacture and is prone to causing an open or short defect. This situation is getting worse with…
- 9
- Wei YeYibo LinMeng LiQiang LiuD. Pan
- 2019
Computer Science, Engineering
2019 24th Asia and South Pacific Design…
This work proposes the use of the area under the ROC curve (AUC), which provides a more holistic measure for im-balanced datasets compared with the previous methods, and proposes the surrogate loss functions for direct AUC maximization as a substitute for the conventional crossentropy loss.
- 23
- PDF
- Ran ChenWei ZhongHaoyu YangHao GengXuan ZengBei Yu
- 2019
Computer Science, Engineering
2019 56th ACM/IEEE Design Automation Conference…
A new end-to-end framework that can detect multiple hotspots in a large region at a time and promise a better hotspot detection performance is developed and Experimental results show that this framework enables a significant speed improvement over existing methods with higher accuracy and fewer false alarms.
- 46
- PDF
- W. TamR. D. Blanton
- 2015
Computer Science, Engineering
IEEE Transactions on Computer-Aided Design of…
By clustering images of the layout locations that correspond to diagnosed sites for a statistically large number of IC failures, LASIC uncovers the common layout features and is found to be effective.
- 21
- PDF
- W. TamO. PokuShawn Blanton
- 2010
Computer Science, Engineering
2010 IEEE International Test Conference
A method that uses diagnosis to identify layout features that do not yield as expected and clustering techniques are applied to layout snippets of diagnosis-implicated regions from (ideally) a statistically-significant number of IC failures for identifying feature commonalties.
- 40
- PDF
- B. BenwareC. SchuermyerManish SharmaT. Herrmann
- 2012
Computer Science, Engineering
This work focuses on significantly increasing the value of test data and the yield learning rate, which is a critical factor in the success of an IC in the market place.
- 50
- Xinlei ChenKaiming He
- 2021
Computer Science
2021 IEEE/CVF Conference on Computer Vision and…
Surprising empirical results are reported that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders.
- 3,046 [PDF]
- Wu-Tung ChengYue TianS. Reddy
- 2017
Computer Science, Engineering
2017 22nd IEEE European Test Symposium (ETS)
Volume diagnosis data mining for root cause identification based on statistical methods is used to reduce turnaround time and cost to speed up the process of systematic defect identification.
- 8
- Adam PaszkeSam Gross Soumith Chintala
- 2019
Computer Science
NeurIPS
This paper details the principles that drove the implementation of PyTorch and how they are reflected in its architecture, and explains how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance.
- 32,939 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers
TABLE II Layout Design Information.
Published in 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD) 2021
A Unified Framework for Layout Pattern Analysis with Deep Causal Estimation
Ran ChenShoubo Hu Jianye Hao
Figure 13 of 17