請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92588
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 李建模 | zh_TW |
dc.contributor.advisor | James Chien-Mo Li | en |
dc.contributor.author | 謝兆和 | zh_TW |
dc.contributor.author | Chao-Ho Hsieh | en |
dc.date.accessioned | 2024-05-02T16:04:54Z | - |
dc.date.available | 2024-05-03 | - |
dc.date.copyright | 2024-04-29 | - |
dc.date.issued | 2024 | - |
dc.date.submitted | 2024-04-23 | - |
dc.identifier.citation | [Shepard 96] K. L. Shepard et al., “Noise in deep submicron digital design,” Proceedings of International Conference on Computer Aided Design, 1996, pp. 524-531
[Calhoun 08] B. H. Calhoun et al., "Digital Circuit Design Challenges and Opportunities in the Era of Nanoscale CMOS," in Proceedings of the IEEE, vol. 96, no. 2, pp. 343-365, Feb. 2008 [Tehranipoor 10] M. Tehranipoor et al., “Power Supply Noise: A Survey on Effects and Research,” IEEE Design & Test of Computers, vol. 27, no. 2, pp. 51-67, March-April 2010 [Chen 16] T. Chen et al., “XGBoost: A Scalable Tree Boosting System,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ''16), Association for Computing Machinery, 2016, pp. 785-794 [McCulloch 43] Warren S. McCulloch et al., "A logical calculus of the ideas immanent in nervous activity." The bulletin of mathematical biophysics 5.4 (1943): pp. 115-133. [Fang 18] Y. -C. Fang et al., “Machine-learning-based Dynamic IR Drop Prediction for ECO,” 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2018, pp. 1-7 [Krizhevsky 12] A. Krizhevsky et al., “Imagenet classification with deep convolutional neural networks,” Proc. Advances in neural information processing systems. 2012. pp. 1097-1105. [Huang 20] X. -X. Huang et al., “Dynamic IR-Drop ECO Optimization by Cell Movement with Current Waveform Staggering and Machine Learning Guidance,” 2020 IEEE/ACM International Conference On Computer Aided Design (ICCAD), 2020, pp. 1-9. [Xie 20] Z. Xie et al., “PowerNet: Transferable Dynamic IR Drop Estimation via Maximum Convolutional Neural Network,” 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC), 2020, pp. 13-18 [Nieh 05] Y. -T. Nieh et al., “Minimizing peak current via opposite-phase clock tree,” Proceedings. 42nd Design Automation Conference, 2005., 2005, pp. 182-185 [Ahmed 07] N. Ahmed et al., “Supply Voltage Noise Aware ATPG for Transition Delay Faults,” 25th IEEE VLSI Test Symposium (VTS''07), 2007, pp. 179-186 [Chen 22] J. -X. Chen et al., “Vector-based Dynamic IR-drop Prediction Using Machine Learning,” 2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC), 2022, pp. 202-207 [Wu 23] Y. -T. Wu, “Dynamic IR-drop Prediction of At-speed Two-vector Test Using Machine Learning”, Masters Thesis, Graduate Institute of Electronics Engineering, National Taiwan University, 2023 [Lin 01] S. Lin et al., “Challenges in power-ground integrity,” IEEE/ACM International Conference on Computer Aided Design. ICCAD 2001. IEEE/ACM Digest of Technical Papers (Cat. No.01CH37281), 2001, pp. 651-654 [Nithin 10] S. K. Nithin et al., “Dynamic voltage (IR) drop analysis and design closure: Issues and challenges,” 2010 11th International Symposium on Quality Electronic Design (ISQED), 2010, pp. 611-617 [Najm 10] Farid N. Najm, Circuit Simulation, John Wiley & Sons, 2010, pp. 42-45 [Ye 14] F. Ye et al., “On-chip voltage-droop prediction using support-vector machines,” 2014 IEEE 32nd VLSI Test Symposium (VTS), 2014, pp. 1-6 [Lin 18] S. -Y. Lin et al., “IR drop prediction of ECO-revised circuits using machine learning,” 2018 IEEE 36th VLSI Test Symposium (VTS), 2018, pp. 1-6 [Bhamidipati 17] L. Bhamidipati et al., “A Power Delivery Network and Cell Placement Aware IR-Drop Mitigation Technique: Harvesting Unused Timing Slacks to Schedule Useful Skews,” 2017 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 2017, pp. 272-277 [Aresh 21] S. Aresh et al., “A Reinforced Learning Solution for Clock Skew Engineering to Reduce Peak Current and IR Drop”, Proceedings of the 2021 on Great Lakes Symposium on VLSI (GLSVLSI ''21), pp. 181-187. [Friedman 02] J. Friedman. Stochastic gradient boosting. Computational Statistics & Data Analysis, vol. 38, no. 4, pp. 367-378, 2002. [NanGate 08] NanGate Inc., “NanGate FreePDK45 Open Cell Library,” 2008 [Gaisler 04] Gaisler home page, 2004, [Online]. Available: https://www.gaisler.com/index.php [Synopsys 16] Synopsys Inc., “PrimeTime User Guide,” 2016 [Ansys 21] Ansys Inc., “RedHawk-SC User Manual,” 2021 [Liu 22] S. -T. Liu et al., “Low-IR-Drop Test Pattern Regeneration Using A Fast Predictor,” 2022 23rd International Symposium on Quality Electronic Design (ISQED), 2022, pp. 27-32 [Hung 10] J. -H. Hung et al., “Technology remapping for engineering change with wirelength consideration,” Proceedings of 2010 IEEE International Symposium on Circuits and Systems, 2010, pp. 2602-2605 [Yang 22] T. Yang et al., A. Han and G. Liu, “Automatic Timing ECO Using Stage-based Path Delay Prediction,” 2022 20th IEEE Interregional NEWCAS Conference (NEWCAS), 2022, pp. 455-459 | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92588 | - |
dc.description.abstract | 時序(timing)工程修改命令 (engineering change order, ECO)可能導致新的電壓降(IR-drop)熱點(hotspot),這些熱點需要在簽發(signoff)前通過額外的電壓降工程修改命令進行修復。在這篇論文中,我們提出了一種基於機器學習的做法,能預測時脈樹(clock tree)工程修改命令後,電路中每個單元(cell)的動態電壓降,以便讓我們找出時脈樹工程修改命令導致的新電壓降熱點。在機器學習模型訓練這方面,我們結合了時脈樹工程修改命令前後設計的特徵,並提出了四種新特徵:目標單元差異特徵、鄰近單元框形平均特徵、鄰近單元框形分佈特徵,和鄰近單元暫態功率特徵。我們的實驗結果顯示,相比於運用坊間軟體進行電壓降分析,我們的作法加速了至少九倍。預測結果的平均絕對百分比誤差也小於3%。我們的方法還可以在大多數情況下,有效找出時脈樹工程修改命令後的電壓降熱點。 | zh_TW |
dc.description.abstract | Timing engineering change order (ECO) may result in new IR-drop hotspots, which are required to be fixed by additional efforts in IR-drop ECO before signoff. In this thesis, we proposed a machine-learning-based method to predict the dynamic IR-drop of every cell in a clock tree ECO revised design so that we can determine the new IR-drop hotspots resulting from the clock tree ECO. To train the machine learning model, we combine the features of a design before and after clock tree ECO, as well as propose four types of new features: target cell delta features, neighbor cell frame averaged features, neighbor cell frame distribution features, and neighbor cell transient power features. Our experimental results show that we achieved at least a 9x speed-up ratio compared to IR-drop analysis by commercial tools, with mean absolute percentage errors less than 3%. Our method can also improve the effectiveness of IR-drop hotspot identification after clock tree ECO in most cases. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-05-02T16:04:54Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2024-05-02T16:04:54Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 致謝 ii
摘要 iv Abstract v Contents vi List of Figures vii List of Tables ix Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Proposed Techniques 3 1.3 Contributions 6 1.4 Organization 7 Chapter 2 Background 8 2.1 Background of IR-drop in VLSI Design 8 2.2 Past Research on Machine-learning-based IR-drop Prediction 10 2.3 Past Research on Clock Tree ECO and IR-drop 18 Chapter 3 Proposed Techniques 22 3.1 Overall Flow 22 3.2 Target Cell Feature Extraction 23 3.3 Neighbor Cell Feature Creation 27 3.4 ML Model Training 33 Chapter 4 Experimental Results 36 4.1 Experimental Setup & Evaluation Metric 36 4.2 IR-drop Prediction Results of Designs After Clock Tree ECO 41 4.3 IR-drop Hotspot Identification for Designs After Clock Tree ECO 50 4.4 Runtime Comparison 52 Chapter 5 Discussion and Future Works 54 5.1 Discussion 54 5.2 Future Works 58 Chapter 6 Conclusion 60 References 61 | - |
dc.language.iso | en | - |
dc.title | 針對時序工程修改命令的快速準確動態電壓降預測 | zh_TW |
dc.title | Fast and Accurate Dynamic IR-drop Prediction For Timing ECO | en |
dc.type | Thesis | - |
dc.date.schoolyear | 112-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 江蕙如;張鴻嘉 | zh_TW |
dc.contributor.oralexamcommittee | Iris Hui-Ru Jiang;Norman Chang | en |
dc.subject.keyword | 電壓降預測,時序ECO,時脈樹,機器學習, | zh_TW |
dc.subject.keyword | IR-drop prediction,timing ECO,clock tree,machine learning, | en |
dc.relation.page | 65 | - |
dc.identifier.doi | 10.6342/NTU202400880 | - |
dc.rights.note | 同意授權(全球公開) | - |
dc.date.accepted | 2024-04-24 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 電子工程學研究所 | - |
顯示於系所單位: | 電子工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-112-2.pdf | 4.87 MB | Adobe PDF | 檢視/開啟 |
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。