{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T22:14:09Z","timestamp":1773094449567,"version":"3.50.1"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T00:00:00Z","timestamp":1670630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"University of Minnesota Doctoral Dissertation Fellowship"},{"name":"Louise Dosdall Fellowship"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2023,1,31]]},"abstract":"<jats:p>Power delivery network (PDN) analysis and thermal analysis are computationally expensive tasks that are essential for successful integrated circuit (IC) design. Algorithmically, both these analyses have similar computational structure and complexity as they involve the solution to a partial differential equation of the same form. This article converts these analyses into image-to-image and sequence-to-sequence translation tasks, which allows leveraging a class of machine learning models with an encoder-decoder\u2013based generative (EDGe) architecture to address the time-intensive nature of these tasks. For PDN analysis, we propose two networks: (i)\u00a0IREDGe: a full-chip static and dynamic IR drop predictor and (ii)\u00a0EMEDGe: electromigration (EM) hotspot classifier based on input power, power grid distribution, and power pad distribution patterns. For thermal analysis, we propose ThermEDGe, a full-chip static and dynamic temperature estimator based on input power distribution patterns for thermal analysis. These networks are transferable across designs synthesized within the same technology and packing solution. The networks predict on-chip IR drop, EM hotspot locations, and temperature in milliseconds with negligibly small errors against commercial tools requiring several hours.<\/jats:p>","DOI":"10.1145\/3526115","type":"journal-article","created":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T11:48:53Z","timestamp":1648468133000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Encoder-Decoder Networks for Analyzing Thermal and Power Delivery Networks"],"prefix":"10.1145","volume":"28","author":[{"given":"Vidya A.","family":"Chhabria","sequence":"first","affiliation":[{"name":"University of Minnesota, USA"}]},{"given":"Vipul","family":"Ahuja","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies Inc., Bengaluru, Karnataka, India"}]},{"given":"Ashwath","family":"Prabhu","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies Inc., Bengaluru, Karnataka, India"}]},{"given":"Nikhil","family":"Patil","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies Inc., Bengaluru, Karnataka, India"}]},{"given":"Palkesh","family":"Jain","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies Inc., Bengaluru, Karnataka, India"}]},{"given":"Sachin S.","family":"Sapatnekar","sequence":"additional","affiliation":[{"name":"University of Minnesota, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,12,10]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"391","volume-title":"Proc. DAC","author":"Amick B. W.","year":"2002","unstructured":"B. W. Amick, C. R. Gauthier, and D. Liu. 2002. Macro-modeling concepts for the chip electrical interface. In Proc. DAC. ACM, New York, NY, 391\u2013394."},{"key":"e_1_3_2_3_2","unstructured":"Ansys. 2018. Icepak. Retrieved Oct. 23 2021 from https:\/\/www.ansys.com\/products\/electronics\/ansys-icepak."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1969.7340"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.322842"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_2_8_2","first-page":"690","volume-title":"Proc. ASP-DAC","author":"Chhabria V. A.","year":"2021","unstructured":"V. A. Chhabria, V. Ahuja, A. Prabhu, N. Patil, P. Jain, and Sachin S. Sapatnekar. 2021. Thermal and IR drop analysis using convolutional encoder-decoder networks. In Proc. ASP-DAC. ACM, New York, NY, 690\u2013696."},{"key":"e_1_3_2_9_2","first-page":"44","volume-title":"Proc. ASP-DAC","author":"Chhabria V. A.","year":"2020","unstructured":"V. A. Chhabria, A. B. Kahng, M. Kim, U. Mallappa, S. S. Sapatnekar, and B. Xu. 2020. Template-based PDN synthesis in floorplan and placement using classifier and CNN techniques. In Proc. ASP-DAC. IEEE, Piscataway, NJ, 44\u201349."},{"key":"e_1_3_2_10_2","unstructured":"V. A. Chhabria and S. S. Sapatnekar. 2021. PDNSim. Retrieved April 29 2022 from https:\/\/github.com\/The-OpenROAD-Project\/OpenROAD\/tree\/master\/src\/psm."},{"key":"e_1_3_2_11_2","first-page":"1825","volume-title":"Proc. DATE","author":"Chhabria V. A.","year":"2021","unstructured":"V. A. Chhabria, Y. Zhang, H. Ren, B. Keller, B. Khailany, and S. S. Sapatnekar. 2021. MAVIREC: ML-aided vectored IR-drop estimation and classification. In Proc. DATE. IEEE, Piscataway, NJ, 1825\u20131828."},{"key":"e_1_3_2_12_2","first-page":"485","volume-title":"Proc. ICCAD","author":"Chiprout E.","year":"2004","unstructured":"E. Chiprout. 2004. Fast flip-chip power grid analysis via locality and grid shells. In Proc. ICCAD. IEEE, Piscataway, NJ, 485\u2013488."},{"key":"e_1_3_2_13_2","first-page":"9260","volume-title":"Proc. CVPR","author":"Cui Y.","year":"2019","unstructured":"Y. Cui, M. Jia, T.-Y. Lin, Y. Song, and S. Belongie. 2019. Class-balanced loss based on effective number of samples. In Proc. CVPR. IEEE, Piscataway, NJ, 9260\u20139269."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.07285"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"e_1_3_2_16_2","volume-title":"Proc. ICCAD","author":"Ho C.-T.","year":"2019","unstructured":"C.-T. Ho and A. B. Kahng. 2019. IncPIRD: Fast learning-based prediction of incremental IR drop. In Proc. ICCAD. IEEE, Piscataway, NJ."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_18_2","first-page":"296","volume-title":"Proc. ICCD","author":"Jin W.","year":"2020","unstructured":"W. Jin, S. Sadiqbatcha, Z. Sun, H. Zhou, and S. X.-D. Tan. 2020. EM-GAN: Data-driven fast stress analysis for multi-segment interconnects. In Proc. ICCD. IEEE, Piscataway, NJ, 296\u2013303."},{"key":"e_1_3_2_19_2","volume-title":"Proc. ICCAD","author":"Jin W.","year":"2020","unstructured":"W. Jin, S. Sadiqbatcha, J. Zhang, and S. X. D. Tan. 2020. Full-chip thermal map estimation for commercial multi-core CPUs with generative adversarial learning. In Proc. ICCAD. IEEE, Piscataway, NJ."},{"key":"e_1_3_2_20_2","first-page":"597","volume-title":"Proc. ASP-DAC","author":"Juan D.","year":"2012","unstructured":"D. Juan, H. Zhou, D. Marculescu, and X. Li. 2012. A learning-based autoregressive model for fast transient thermal analysis of chip-multiprocessors. In Proc. ASP-DAC. IEEE, Piscataway, NJ, 597\u2013602."},{"key":"e_1_3_2_21_2","volume-title":"Proc. ICLR","author":"Kingma D.","year":"2015","unstructured":"D. Kingma and J. Ba. 2015. Adam: A method for stochastic optimization. In Proc. ICLR. OpenReview, openreview.net."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.354073"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2002.802271"},{"key":"e_1_3_2_24_2","volume-title":"Proc. VTS","author":"Lin S.-Y.","year":"2018","unstructured":"S.-Y. Lin, Y.-C. Fang, Y.-C. Li, Y. Liu, T. Yang, S.-C. Lin, C.-M. J. Li, and E. J.-W. Fang. 2018. IR drop prediction of ECO-revised circuits using machine learning. In Proc. VTS. IEEE, Piscataway, NJ."},{"key":"e_1_3_2_25_2","volume-title":"Adv. NeurIPS","author":"Luo W.","year":"2016","unstructured":"W. Luo, Y. Li, R. Urtasun, and R. Zemel. 2016. Understanding the effective receptive field in deep convolutional neural networks. In Adv. NeurIPS. Curran Associates, Inc., Red Hook, NY."},{"key":"e_1_3_2_26_2","volume-title":"Adv. NeurIPS","author":"Mao X.-J.","year":"2016","unstructured":"X.-J. Mao, C. Shen, and Y.-B. Yang. 2016. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In Adv. NeurIPS. Curran Associates, Inc., Red Hook, NY."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2002.00367"},{"key":"e_1_3_2_28_2","first-page":"376","volume-title":"Proc. ASP-DAC","author":"Nassif S. R.","year":"2008","unstructured":"S. R. Nassif. 2008. Power grid analysis benchmarks. In Proc. ASP-DAC. IEEE, Piscataway, NJ, 376\u2013381."},{"key":"e_1_3_2_29_2","first-page":"234","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assisted Intervention","author":"Ronneberger O.","year":"2015","unstructured":"O. Ronneberger, P. Fischer, and T. Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In Proc. Int. Conf. Med. Image Comput. Comput.-Assisted Intervention. Springer, Cham, 234\u2013241."},{"key":"e_1_3_2_30_2","doi-asserted-by":"crossref","DOI":"10.1109\/TC.2021.3086112","article-title":"Real-time full-chip thermal tracking: A post-silicon, machine learning perspective","author":"Sadiqbatcha S.","year":"2021","unstructured":"S. Sadiqbatcha, J. Zhang, H. Amrouch, and S. X.-D. Tan. 2021. Real-time full-chip thermal tracking: A post-silicon, machine learning perspective. IEEE Trans. Comput. (Early Access) (2021).","journal-title":"IEEE Trans. Comput."},{"key":"e_1_3_2_31_2","first-page":"48","volume-title":"Proc. DATE","author":"Sadiqbatcha S.","year":"2019","unstructured":"S. Sadiqbatcha, H. Zhao, H. Amrouch, J. Henkel, and S. X. Tan. 2019. Hot spot identification and system parameterized thermal modeling for multi-core processors through infrared thermal imaging. In Proc. DATE. IEEE, Piscataway, NJ, 48\u201353."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"e_1_3_2_33_2","volume-title":"Adv. NeurIPS","author":"Shi X.","year":"2015","unstructured":"X. Shi, Z. Chen, H.. Wang, D.-Y. Yeung, W.-K. Wong, and W.-C. Woo. 2015. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Adv. NeurIPS. Curran Associates, Inc., Red Hook, NY."},{"key":"e_1_3_2_34_2","volume-title":"Proc. ICCAD","author":"Shohel M. A. Al","year":"2021","unstructured":"M. A. Al Shohel, V. A. Chhabria, N. Evmorfopoulos, and S. S. Sapatnekar. 2021. Analytical modeling of transient electromigration stress based on boundary reflections. In Proc. ICCAD. IEEE, Piscataway, NJ. (to appear)."},{"key":"e_1_3_2_35_2","volume-title":"Proc. DAC","author":"Shohel M. A. Al","year":"2021","unstructured":"M. A. Al Shohel, V. A. Chhabria, and S. S. Sapatnekar. 2021. A new, computationally efficient \u201cBlech criterion\u201d for immortality in general interconnects. In Proc. DAC. IEEE, Piscataway, NJ(to appear; available at https:\/\/arxiv.org\/abs\/2105.08784)."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2006.870071"},{"key":"e_1_3_2_37_2","volume-title":"VLSI systems long-term reliability\u2014Modeling, simulation and optimization","author":"Tan S. X.-D.","year":"2019","unstructured":"S. X.-D. Tan, M. Tahoori, T. Kim, S. Wang, Z. Sun, and S. Kiamehr. 2019. VLSI systems long-term reliability\u2014Modeling, simulation and optimization. Springer, Boston, MA."},{"key":"e_1_3_2_38_2","first-page":"65","volume-title":"Proc. IEEE Symp. Semicond. Therm. Meas., Model. Manage.","author":"Wen J.","year":"2020","unstructured":"J. Wen, S. Pan, N. Chang, W. Chuang, W. Xia, D. Zhu, A. Kumar, E. Yang, K. Srinivasan, and Y. Li. 2020. DNN-based fast static on-chip thermal solver. In Proc. IEEE Symp. Semicond. Therm. Meas., Model. Manage.IEEE, Piscataway, NJ, 65\u201375."},{"key":"e_1_3_2_39_2","first-page":"13","volume-title":"Proc. ASP-DAC","author":"Xie Z.","year":"2020","unstructured":"Z. Xie, H. Ren, B. Khailany, Y. Sheng, S. Santosh, J. Hu, and Y. Chen. 2020. PowerNet: Transferable dynamic IR drop estimation via maximum convolutional neural network. In Proc. ASP-DAC. IEEE, Piscataway, NJ, 13\u201318."},{"key":"e_1_3_2_40_2","volume-title":"Foundations of Heterogeneous Integration: An Industry-Based, 2.5D\/3D Pathfinding and Co-Design Approach","author":"Yazdani F.","year":"2018","unstructured":"F. Yazdani. 2018. Foundations of Heterogeneous Integration: An Industry-Based, 2.5D\/3D Pathfinding and Co-Design Approach. Springer, Boston, MA."},{"key":"e_1_3_2_41_2","first-page":"2349","volume-title":"Proc. Intl. Conf. on Image. Process.","author":"You J.","year":"2019","unstructured":"J. You and J. Korhonen. 2019. Deep neural networks for no-reference video quality assessment. In Proc. Intl. Conf. on Image. Process.IEEE, Piscataway, NJ, 2349\u20132353."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000007"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2732951"},{"key":"e_1_3_2_44_2","first-page":"351","volume-title":"Proc. ICCAD","author":"Zhong Y.","year":"2005","unstructured":"Y. Zhong and M. D. F. Wong. 2005. Fast algorithms for IR drop analysis in large power grid. In Proc. ICCAD. IEEE, Piscataway, NJ, 351\u2013357."}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3526115","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3526115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:15Z","timestamp":1750186935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3526115"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,10]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,31]]}},"alternative-id":["10.1145\/3526115"],"URL":"https:\/\/doi.org\/10.1145\/3526115","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,10]]},"assertion":[{"value":"2021-10-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-11","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}