請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97806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 | 王濰紳 | zh_TW |
| dc.contributor.author | Wei-Shen Wang | en |
| dc.date.accessioned | 2025-07-17T16:05:15Z | - |
| dc.date.available | 2025-07-18 | - |
| dc.date.copyright | 2025-07-17 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-07-14 | - |
| dc.identifier.citation | S. H. Pan, N. Chang, and T. Hitomi, “3d-ic dynamic thermal analysis with hierarchical and configurable chip thermal model,” in 2013 IEEE International 3D Systems Integration Conference (3DIC), pp. 1–8, 2013.
W. Huang, S. Ghosh, S. Velusamy, K. Sankaranarayanan, K. Skadron, and M. R. Stan, “Hotspot: A compact thermal modeling methodology for early-stage vlsi design,” IEEE Transactions on very large scale integration (VLSI) systems, vol. 14, no. 5, pp. 501–513, 2006. A. Ziabari, J.-H. Park, E. K. Ardestani, J. Renau, S.-M. Kang, and A. Shakouri, “Power blurring: Fast static and transient thermal analysis method for packaged integrated circuits and power devices,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 22, no. 11, pp. 2366–2379, 2014. V. A. Chhabria, V. Ahuja, A. Prabhu, N. Patil, P. Jain, and S. S. Sapatnekar, “Thermal and ir drop analysis using convolutional encoder-decoder networks,” in Proceedings 47 of the 26th Asia and South Pacific Design Automation Conference, pp. 690–696, 2021. Z.-J. Liang, Y.-T. Wu, Y.-F. Yang, J. C.-M. Li, N. Chang, A. Kumar, and Y.-S. Li, “High-speed, low-storage power and thermal predictions for atpg test patterns,” in 2023 IEEE International Test Conference (ITC), pp. 206–215, 2023. Z. Liu, Y. Li, J. Hu, X. Yu, S. Shiau, X. Ai, Z. Zeng, and Z. Zhang, “Deepoheat: Operator learning-based ultra-fast thermal simulation in 3d-ic design,” in 2023 60th ACM/IEEE Design Automation Conference (DAC), pp. 1–6, 2023. L. Lu, P. Jin, G. Pang, Z. Zhang, and G. E. Karniadakis, “Learning nonlinear operators via deeponet based on the universal approximation theorem of operators,” Nature machine intelligence, vol. 3, no. 3, pp. 218–229, 2021. R. Ranade, H. He, J. Pathak, N. Chang, A. Kumar, and J. Wen, “A thermal machine learning solver for chip simulation,” in 2022 ACM/IEEE 4th Workshop on Machine Learning for CAD (MLCAD), pp. 111–117, 2022. A. Kumar, N. Chang, D. Geb, H. He, S. Pan, J. Wen, S. Asgari, M. Abarham, and C. Ortiz, “Ml-based fast on-chip transient thermal simulation for heterogeneous 2.5d/3d ic designs,” in 2022 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), pp. 1–8, IEEE, 2022. K. Asanovic, R. Avizienis, J. Bachrach, S. Beamer, D. Biancolin, C. Celio, H. Cook, D. Dabbelt, J. Hauser, A. Izraelevitz, et al., “The rocket chip generator,” EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2016-17, vol. 4, pp. 6–2, 2016. M. Pedram and S. Nazarian, “Thermal modeling, analysis, and management in vlsi circuits: Principles and methods,” Proceedings of the IEEE, vol. 94, no. 8, pp. 1487–1501, 2006. H. Sultan, A. Chauhan, and S. R. Sarangi, “A survey of chip-level thermal simulators,” ACM Comput. Surv., vol. 52, Apr. 2019. M. Miller, “Next generation burn-in and test systems for athlon microprocessors: hybrid burn-in,” in Burn-in and Test Socket Workshop, vol. 7, pp. 36–7, 2001. Intel, “Too hot to test workshop,” 2021. W.-S. Wang, Z.-J. Liang, J. C.-M. Li, N. Chang, A. Kumar, and Y.-S. Li, “Thermalaware test frequency optimization,” in 2024 IEEE International Test Conference in Asia (ITC-Asia), pp. 1–5, 2024. A. Inc., RedHawk-SC-Electrothermal User Manual. 2024. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical image computing and computerassisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pp. 234–241, Springer, 2015. J. Cong, J. Wei, and Y. Zhang, “A thermal-driven floorplanning algorithm for 3d ics,” in IEEE/ACM International Conference on Computer Aided Design, 2004. ICCAD2004., pp. 306–313, 2004. H. He, N. Chang, J. Yang, A. Kumar, W. Xia, L. Lin, and R. Ranade, “Invited paper: Solving fine-grained static 3dic thermal with ml thermal solver enhanced with decay curve characterization,” in 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD), pp. 1–7, 2023. R. Ranade, C. Hill, H. He, A. Maleki, N. Chang, and J. Pathak, “A composable autoencoder-based iterative algorithm for accelerating numerical simulations,” arXiv preprint arXiv:2110.03780, 2021. K. Srinivasan, P. Gupta, W. Xia, Z. Feng, S. Pan, P. Traynar, and N. Chang, “An early system-level thermal analysis methodology for advanced electronic subsystems,” in 2018 34th Thermal Measurement, Modeling & Management Symposium (SEMI-THERM), pp. 92–97, 2018. K. Srinivasan, S. Pan, Z. Feng, N. Chang, and T. Pawlak, “An efficient transient thermal simulation methodology for power management ic designs,” in 2017 33rd Thermal Measurement, Modeling & Management Symposium (SEMI-THERM), pp. 57–62, 2017. Y.-F. Yang, W.-S. Wang, Y.-J. Lee, J. C.-M. Li, N. Chang, A. Kumar, Y.-S. Li, J. Yen, and L. Lin, “Efficient ml-based transient thermal prediction for 3d-ics,” in Proceedings of the 30th Asia and South Pacific Design Automation Conference, ASPDAC’25, (New York, NY, USA), p. 628–634, Association for Computing Machinery, 2025. Y. Ma, L. Delshadtehrani, C. Demirkiran, J. L. Abellan, and A. Joshi, “Tap-2.5 d: A thermally-aware chiplet placement methodology for 2.5 d systems,” in 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 1246–1251, IEEE, 2021. M. Molter, R. Kumar, S. Koller, O. W. Bhatti, N. Ambasana, E. Rosenbaum, and M. Swaminathan, “Thermal-aware soc macro placement and multi-chip module design optimization with bayesian optimization,” in 2023 IEEE 73rd Electronic Components and Technology Conference (ECTC), pp. 935–942, IEEE, 2023. Q. Wang, X. Li, T. Jia, Y. Lin, R. Wang, and R. Huang, “Atplace2. 5d: Analytical thermal-aware chiplet placement framework for large-scale 2.5 d-ic,” in Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, pp. 1–9, 2024. S. Inc., PrimeTime User Guide. Version T-2022.03. 2022. T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, (New York, NY, USA), p. 785–794, Association for Computing Machinery, 2016. A. Elsherbini, S. Liff, J. Swan, K. Jun, S. Tiagaraj, and G. Pasdast, “Hybrid bonding interconnect for advanced heterogeneously integrated processors,” in 2021 IEEE 71st Electronic Components and Technology Conference (ECTC), pp. 1014–1019, 2021. J. R. Cannon, The one-dimensional heat equation. No. 23, Cambridge University Press, 1984. V. Vashishtha, M. Vangala, and L. T. Clark, “Asap7 predictive design kit development and cell design technology co-optimization: Invited paper,” in 2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), pp. 992–998, 2017. I. Cadence Design Systems, Genus User Guide. Product Version 21.1. 2021. I. Cadence Design Systems, Innovus User Guide. Product Version 21.17. 2021. S. Inc., VCS User Guide. Version Q-2020.03. 2020. R. P. Weicker, “Dhrystone: a synthetic systems programming benchmark,” Communications of the ACM, vol. 27, no. 10, pp. 1013–1030, 1984. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97806 | - |
| dc.description.abstract | 隨著半導體製程進步,三維積體電路的高溫逐漸成為不可忽視的議題。溫度過高可能導致晶片損壞或晶片效能下降。然而傳統溫度分析需要非常長的運算時間,進一步使的三維積體電路設計空間探索速度極為緩慢。在本論文中,我們提出基於機器學習的暫態溫度預測器,以實現高速考慮溫度之三維積體電路使用空間探索。我們提出三項機器學習特徵,以此考慮三維積體電路的物理資訊與功率分佈。我們提出兩種使用多模型機器學習的技巧,以此考慮不同的物理層與不同的溫度區間。在我們的實驗當中,我們設計了一個三層堆疊、每層為4毫米 x 4毫米的三維積體電路。我們的溫度預測器準確度達到了平均絕對誤差0.23°C與最大誤差5.99°C。我們的溫度預測器的運算速度達到了相較於商業用有限元素法求解器551倍的速度提升。在一個每層含有13核心晶片之三維積體電路,我們提出的基於機器學習之使用空間探索得以求出符合溫度限制之佈局規劃,使三維積體電路之最高溫度下降10°C。我們提出方法成本為模型訓練時間(本研究中使用了36個佈局規劃訓練模型),但是這些訓練成本可以被多個使用相同封裝的三維積體電路共享。 | zh_TW |
| dc.description.abstract | As the technology nodes advance, the thermal issues of 3DIC need to be addressed. Thermal violation could cause chip damage or performance degradation. Traditional thermal simulation is too slow for 3DIC Design Space Exploration (DSE). In this thesis, we propose a machine learning (ML)-based transient thermal predictor to enable fast thermal-aware 3DIC DSE. We propose three ML features to include the physical information and the power distribution of a 3DIC. We propose two multiple ML models for different physical layers and different temperature regions. We set up a 3DIC with three stacked 4mm x 4mm dies. Our thermal predictor achieves a mean absolute error of 0.23°C and a maximum error of 5.99°C. Our thermal predictor achieves a 551X speedup compared to a commercial Finite Element Method (FEM) solver during DSE. In a 3DIC with 13 cores per die, our proposed ML-based DSE finds a thermal-safe floorplan, reducing peak temperature by 10°C. The cost of our proposal is the additional training time (36 floorplans in our case), which can be shared by many 3DICs using the same package. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-17T16:05:15Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-07-17T16:05:15Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements i
摘要 iii Abstract iv Contents v List of Figures viii List of Tables x Chapter 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Proposed Technique . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.3 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.4 Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 Chapter 2 Background 7 2.1 Static / Transient Thermal Simulation . . . . . . . . . . . . . . . . . 7 2.2 Static and Transient Thermal Simulation for 2DIC . . . . . . . . . . 8 2.3 Static Thermal Simulation for 3DIC . . . . . . . . . . . . . . . . . . 11 2.4 Transient Thermal Simulation for 3DIC . . . . . . . . . . . . . . . . 13 2.5 Thermal-Aware DSE for 2DIC . . . . . . . . . . . . . . . . . . . . . 14 Chapter 3 Proposed Technique 16 3.1 Overall Flow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2 ML Features Extraction . . . . . . . . . . . . . . . . . . . . . . . . 18 3.2.1 Distance to Nearest XY Boundary . . . . . . . . . . . . . . . . . . 20 3.2.2 Distance to Nearest Four Hybrid Bondings . . . . . . . . . . . . . . 21 3.2.3 Concentric-Circle Total Power . . . . . . . . . . . . . . . . . . . . 22 3.2.4 Time-Decayed Feature . . . . . . . . . . . . . . . . . . . . . . . . 25 3.3 Multiple ML Models . . . . . . . . . . . . . . . . . . . . . . . . . . 26 3.3.1 Multiple ML Models by Die . . . . . . . . . . . . . . . . . . . . . 27 3.3.2 Multiple ML Models by Temperature . . . . . . . . . . . . . . . . . 28 Chapter 4 Experiments 30 4.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.1.1 3DIC Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.1.2 Multi-Core Die . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.1.3 RISC-V SoC Setup . . . . . . . . . . . . . . . . . . . . . . . . . . 31 4.1.4 Thermal Predictor Setup . . . . . . . . . . . . . . . . . . . . . . . 33 4.1.5 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . 33 4.2 Accuracy Comparison . . . . . . . . . . . . . . . . . . . . . . . . . 34 4.3 Runtime Comparison . . . . . . . . . . . . . . . . . . . . . . . . . . 39 4.4 Design Space Exploration Results . . . . . . . . . . . . . . . . . . . 40 Chapter 5 Discussion 43 5.1 Model Transferability . . . . . . . . . . . . . . . . . . . . . . . . . 43 5.2 Long Simulation Duration Prediction . . . . . . . . . . . . . . . . . 43 5.3 Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 Chapter 6 Conclusion 46 References 47 Appendix A — Definition of Terms 54 | - |
| dc.language.iso | en | - |
| dc.subject | 設計空間探索 | zh_TW |
| dc.subject | 暫態溫度 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 三維積體電路 | zh_TW |
| dc.subject | Design Space Exploration | en |
| dc.subject | 3DIC | en |
| dc.subject | machine learning | en |
| dc.subject | transient thermal | en |
| dc.title | 基於機器學習的三維積體電路暫態溫度預測器用於快速設計空間探索 | zh_TW |
| dc.title | ML-based 3DIC Transient Thermal Predictor for Fast Design Space Exploration | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| 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 | 三維積體電路; 機器學習; 暫態溫度; 設計空間探索 | zh_TW |
| dc.subject.keyword | 3DIC; machine learning; transient thermal; Design Space Exploration | en |
| dc.relation.page | 54 | - |
| dc.identifier.doi | 10.6342/NTU202501787 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-07-16 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 電子工程學研究所 | - |
| dc.date.embargo-lift | N/A | - |
| 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-113-2.pdf 未授權公開取用 | 6.44 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。
