請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/58960
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 張耀文(Yao-Wen Chang) | |
dc.contributor.author | Ping-Wei Huang | en |
dc.contributor.author | 黃平瑋 | zh_TW |
dc.date.accessioned | 2021-06-16T08:41:13Z | - |
dc.date.available | 2026-02-02 | |
dc.date.copyright | 2021-02-23 | |
dc.date.issued | 2021 | |
dc.date.submitted | 2021-02-05 | |
dc.identifier.citation | [1] ANSYS. RedHawk user manual. Accessed: 2020-11-23. [Online]. Available: http://www.ansys.com/ [2] W.-H. Chang, M. C.-T. Chao, and S.-H. Chen, Practical routability-driven design flow for multilayer power networks using aluminum-pad layer,' IEEE Transactions on Very Large Scale Integration VLSI Systems, vol. 22, no. 5, pp. 1069-1081, June 2013. [3] W.-H. Chang, C.-H. Lin, S.-P. Mu, L.-D. Chen, C.-H. Tsai, Y.-C. Chiu, and M. C.-T. Chao, Generating routing-driven power distribution networks with machine-learning technique,' IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 36, no. 8, pp. 1237-1250, January 2017. [4] T. Chen and C. Guestrin, XGBoost: A scalable tree boosting system,' in Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data mining, pp. 785-794, August 2016. [5] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, ImageNet: A large-scale hierarchical image database,' in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255, Miami, FL, June 2009. [6] Y.-C. Fang, H.-Y. Lin, M.-Y. Su, C.-M. Li, and E. J.-W. Fang, Machine learning-based dynamic IR drop prediction for ECO,' in Proceedings of IEEE/ACM International Conference on Computer-Aided Design, San Diego, CA, November 2018. [7] C.-T. Ho and A. B. Kahng, IncPIRd: Fast learning-based prediction of incremental IR drop,' in Proceedings of IEEE/ACM International Conference on Computer-Aided Design, Westminster, CO, November 2019. [8] X.-X. Huang, H.-C. Chen, S.-W. Wang, I. H.-R. Jiang, Y.-C. Chou, and C.-H. Tsai, Dynamic IR-drop ECO optimization by cell movement with current waveform staggering and machine learning guidance,' in Proceedings of IEEE/ACM International Conference on Computer-Aided Design, San Diego, CA, November 2020. [9] A. Krizhevsky, I. Sutskever, and G. Hinton, ImageNet classification with deep convolutional neural networks,' in Proceedings of ACM International Conference on Neural Information Processing Systems, pp. 1097-1105, Lake Tahoe, NV, December 2012. [10] S. Kose and E. G. Friedman, Fast algorithms for IR voltage drop analysis exploiting locality,' in Proceedings of ACM/IEEE Design Automation Conference, pp. 996-1001, San Diego, CA, June 2011. [11] J. Lin, J. Syu, and I. Chen, Macro-aware row-style power delivery network design for better routability,' in Proceedings of IEEE/ACM International Conference on Computer-Aided Design, San Diego, CA, November 2018. [12] S. Lin and N. Chang, Challenges in power-ground integrity,' in Proceedings of IEEE/ACM International Conference on Computer-Aided Design, pp. 651-654, San Jose, CA, November 2001. [13] C. Liu and Y. Chang, Power/ground network and floorplan cosynthesis for fast design convergence,' IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 26, no. 4, pp. 693-704, March 2007. [14] S. K. Nithin, G. Shanmugam, and S. Chandrasekar, Dynamic voltage IR drop analysis and design closure: Issues and challenges,' in Proceedings of IEEE International Symposium on Quality Electronic Design, pp. 611-617, San Jose, CA, March 2010. [15] S. J. Pan and Q. Yang, A survey on transfer learning,' IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, October 2010. [16] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, Scikit-learn: Machine learning in Python,' Journal of Machine Learning Research, vol. 12, pp. 2825-2830, November 2011. [17] S. Ruder, An overview of multi-task learning in deep neural networks,' arXiv preprint arXiv:1706.05098, August 2017. [18] Synopsys. IC Compiler II user manual. Accessed: 2020-11-23. [Online]. Available: https://www.synopsys.com/ [19] M. Tan and Q. V. Le, EfficientNet: Rethinking model scaling for convolutional neural networks,' arXiv preprint arXiv:1905.11946, September 2019. [20] S. Wang, G. Liou, Y. Su, and M. P. Lin, IR-aware power net routing for multi-voltage mixed-signal design,' in Proceedings of ACM/IEEE Design, Automation and Test in Europe, pp. 72-77, Florence, Italy, March 2019. [21] Z. Xie, Y.-H. Huang, G.-Q. Fang, H. Ren, S.-Y. Fang, Y. Chen, and J. Hu, RouteNet: Routability prediction for mixed-size designs using convolutional neural network,' in Proceedings of IEEE/ACM International Conference on Computer-Aided Design, San Diego, CA, November 2018. [22] Z. Xie, H. Li, X. Xu, J. Hu, and Y. Chen, Fast IR drop estimation with machine learning,' in Proceedings of IEEE/ACM International Conference on Computer-Aided Design, San Diego, CA, November 2020. [23] Z. Xie, H. Ren, B. Khailany, Y. Sheng, S. Santosh, J. Hu, and Y. Chen, PowerNet: Transferable dynamic IR drop estimation via maximum convolutional neural network,' in Proceedings of IEEE/ACM International Conference on Computer-Aided Design, pp. 13-18, Beijing, China, January 2020. [24] Y. Yamato, T. Yoneda, K. Hatayama, and M. Inoue, A fast and accurate per-cell dynamic IR-drop estimation method for at-speed scan test pattern validation,' in Proceedings of IEEE International Test Conference, Anaheim, CA, November 2012. [25] F. Ye, F. Firouzi, Y. Yang, K. Chakrabarty, and M. B. Tahoori, On-chip voltage-droop prediction using support-vector machines,' in Proceedings of IEEE VLSI Test Symposium, Napa, CA, April 2014. [26] J.-S. Yim, S.-O. Bae, and C.-M. Kyung, A floorplan-based planning methodology for power and clock distribution in ASICs,' in Proceedings of ACM/IEEE Design Automation Conference, pp. 766-771, New Orleans, LA, June 1999. [27] Y. Zhang and Q. Yang, A survey on multi-task learning,' arXiv preprint arXiv:1707.08114, June 2018. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/58960 | - |
dc.description.abstract | 在現代電路設計中,電源網路 (power/ground network) 是其中相當重要的部分,因為電源網路的配置將密切影響可靠性問題,如電壓降 (IR drop)、電遷移 (electromigration),以及面積成本如金屬面積、訊號線繞線率 (signal net routability)。電源網路中的動態壓降 (dynamic IR drop) 是先進技術節點中最關鍵的問題之一。過度的動態壓降會降低電路性能,並導致潛在的功能性錯誤,但使用商用軟體模擬分析動態壓降值卻非常耗時。對於動態壓降的限制,大多業界作法都傾向於超規格設計 (overdesign) 電源網絡,但此做法卻會減少繞線資源 (routing resources) 並引起了繞線擁擠 (routing congestion)。而現有的基於機器學習 (machine learning) 的方法僅針對動態壓降預測,而沒有考慮受到電源網路影響的訊號線繞線率。 在本篇論文中,我們開發了一個兩階段的演算法流程,該流程包括用於訓練機器學習模型的數據預處理 (data preprocessing) 和多目標優化 (multi-objective optmization) 方案。在數據預處理階段,我們提出了一種有效提取周圍環境特徵的特徵工程 (feature engineering) 方法,這些特徵可用於同時預測動態壓降和繞線擁擠。在多目標優化方案中,我們採用前一階段的機器學習模型,並解決動態壓降與繞線資源之間的權衡問題。 實驗結果顯示,該演算法在模型精度和繞線資源優化方面均十分有效。我們的模型可以通過採用多任務學習 (multi-task learning) 以準確預測動態壓降和訊號線擁擠,從而獲得高達0.996的相關係數。實驗結果也顯示,通過採用的機器學習模型,該演算法能節省約10%的繞線資源,而不會顯著增加動態壓降峰值。與業界領先的商用軟體的模擬分析相比,我們的演算法還可實現高達48倍的顯著加速。 | zh_TW |
dc.description.abstract | The power/ground (PG) network is an essential component in modern circuit designs, as the configuration of a PG network is closely related to the reliability issues (IR drop, electromigration) and area cost (metal area, signal net routability). The dynamic IR drop of a PG network is one of the most critical problems in an advanced technology node. Excessive IR drop slows down circuit performance and causes potential functional failures while obtaining the exact IR drop value is time-consuming by the simulation-based commercial tool. For the dynamic IR drop constraints, most industrial practices tend to over-design the PG network, reducing routing resources and incurring routing congestion. Existing machine-learning-based approaches target only dynamic IR drop prediction without considering the routability affected by the PG network.
In this thesis, we develop a two-stage algorithm flow consisting of the data preprocessing for model training and the multi-objective optimization scheme. In the data preprocessing stage, we propose a feature engineering method that effectively extracts features containing neighboring information. These features can be used to predict dynamic IR drop and routing congestion simultaneously. In the multi-objective optimization scheme, we adopt the machine-learning model from the previous stage and solve the trade-off between dynamic IR drop and routing resources. Experimental results show that our algorithm is effective in both model accuracy and routing resources optimization. Our model can accurately predict dynamic IR drop and signal net congestion by adopting a multi-task learning scheme, achieving 0.996 high correlation coefficient. The experimental results also show that our algorithm can save about 10\% routing resources without worsening dynamic IR drop peak value by adopting the machine learning model. Our algorithm also achieves significant speedups of up to 48X, compared to the time-consuming dynamic IR drop simulation by a leading commercial tool. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T08:41:13Z (GMT). No. of bitstreams: 1 U0001-0302202122031800.pdf: 4281041 bytes, checksum: 04712d86de2afb97c4df1aba4ea89667 (MD5) Previous issue date: 2021 | en |
dc.description.tableofcontents | Acknowledgements iii Abstract (Chinese) iv Abstract vi List of Tables xi List of Figures xii Chapter 1. Introduction 1 1.1 Introduction to the Power/Ground Network . . . . . . . . . . . . . . . . 1 1.1.1 Configuration of the Power/Ground Network . . . . . . . . . . . . 2 1.1.2 Issues Related to the Power/Ground Network . . . . . . . . . . . . 4 1.2 Previous Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.2.1 IR-Drop-Aware Optimization . . . . . . . . . . . . . . . . . . . . . 7 1.2.2 Routability-Aware Optimization . . . . . . . . . . . . . . . . . . . 9 1.3 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 1.4 Our Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 1.5 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 Chapter 2. Preliminaries 15 2.1 Introduction to IR Drop . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 2.1.1 Static IR Drop . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 2.1.2 Dynamic IR Drop . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 2.2 Machine Learning Techniques . . . . . . . . . . . . . . . . . . . . . . . . 18 2.2.1 Machine Learning Models . . . . . . . . . . . . . . . . . . . . . . . 18 2.2.2 Multi-Task Learning . . . . . . . . . . . . . . . . . . . . . . . . . . 20 2.2.3 Transfer Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 2.3 Terminologies and Notations . . . . . . . . . . . . . . . . . . . . . . . . . 22 2.4 Problem Formulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 Chapter 3. Our Proposed Algorithm 24 3.1 Algorithm Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 3.2 IR Drop and Routing Congestion Estimation . . . . . . . . . . . . . . . . 26 3.2.1 Golden IR drop . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 3.2.2 Golden Congestion Score . . . . . . . . . . . . . . . . . . . . . . . 26 3.3 Data Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 3.3.1 Training Data Generation . . . . . . . . . . . . . . . . . . . . . . . 28 3.3.2 Feature Engineering . . . . . . . . . . . . . . . . . . . . . . . . . . 31 3.3.2.1 Cell-Based Features . . . . . . . . . . . . . . . . . . . . . . 31 3.3.2.2 Pin-Based Features . . . . . . . . . . . . . . . . . . . . . . 32 3.3.2.3 Local Features . . . . . . . . . . . . . . . . . . . . . . . . 32 3.3.2.4 Global Features . . . . . . . . . . . . . . . . . . . . . . . . 34 3.3.3 Neighboring Image Generation . . . . . . . . . . . . . . . . . . . . 36 3.4 Machine-Learning-Based Optimization . . . . . . . . . . . . . . . . . . . 38 3.4.1 Multi-Objective Model Training . . . . . . . . . . . . . . . . . . . 39 3.4.2 PG Vias Removal . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 3.4.3 PG Wires Modification . . . . . . . . . . . . . . . . . . . . . . . . 44 Chapter 4. Experimental Results 45 4.1 Experimental Settings Benchmarks . . . . . . . . . . . . . . . . . . . . 45 4.2 Accuracy of the Proposed Model . . . . . . . . . . . . . . . . . . . . . . . 47 4.2.1 Model Accuracy Before Modification. . . . . . . . . . . . . . . . 47 4.2.2 Comparison with Other Methods . . . . . . . . . . . 48 4.2.3 Model Accuracy After Modification . . . . . . . . . . . . . . . . . 52 4.3 Effectiveness of the Proposed Algorithm . . . . . . . . . . . . . . . . . . 54 4.4 Scalability of the Proposed Algorithm . . . . . . . . . . . . . . . . . . . 56 Chapter 5. Conclusions and Future Work 58 5.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 Bibliography 62 | |
dc.language.iso | en | |
dc.title | 基於機器學習與考量動態壓降之電源網路可繞度最佳化 | zh_TW |
dc.title | Machine-learning-based Routability-driven Power/Ground Network Optimization Considering Dynamic IR Drop | en |
dc.type | Thesis | |
dc.date.schoolyear | 109-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 陳東傑(Tung-Chieh Chen),黃婷婷(Ting-Ting Hwang),方劭云(Shao-Yun Fang) | |
dc.subject.keyword | 實體設計,機器學習,電源網路,動態壓降, | zh_TW |
dc.subject.keyword | Phyiscal design,Machine learning,Power/ground network,Dyanmic IR drop, | en |
dc.relation.page | 65 | |
dc.identifier.doi | 10.6342/NTU202100475 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2021-02-08 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
顯示於系所單位: | 電機工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-0302202122031800.pdf 目前未授權公開取用 | 4.18 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。