Skip to main content
SpringerLink
Log in

Deep Learning for Analyzing Power Delivery Networks and Thermal Networks

  • Chapter
  • First Online:
Machine Learning Applications in Electronic Design Automation

  • 1812 Accesses

Abstract

The design of on-chip power delivery networks (PDNs) and thermal networks involves the solution of large systems of linear equations. This computational intensive step is a critical part of the IC design process and has been a significant computational bottleneck for electronic design automation. Machine learning techniques can efficiently solve these problems by performing fast and accurate analysis and optimization. This chapter presents ML methods in this domain: for analyzing PDNs for IR drop and electromigration, for analyzing thermal networks for temperature, for optimizing PDNs by mapping the problem to a classification problem, and for generating PDN benchmarks.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 119.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    The open-source version of PDNSim is for static IR drop analysis only. Therefore, a modified version of the source code to perform dynamic IR drop analysis.

  2. 2.

    In principle, the macro grid can be connected to the PDN through the edges of the macro. However, in practice, the regions around the macro are halos of placement and routing blockages, to avoid abutment and DRC issues.

References

  1. Allec, N., Hassan, Z., Shang, L., Dick, R.P., Yang, R.: ThermalScope: multi-scale thermal analysis for nanometer-scale integrated circuits. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design, pp. 603–610 (2008)

    Google Scholar 

  2. Amick, B.W., Gauthier, C.R., Liu, D.: Macro-modeling concepts for the chip electrical interface. In: Proceedings of the ACM/IEEE Design Automation Conference, pp. 391–394 (2002)

    Google Scholar 

  3. Ansys: Icepak (2018). https://www.ansys.com/products/electronics/ansys-icepak

  4. Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)

    Article  Google Scholar 

  5. Bhooshan, R.: Novel and efficient IR-drop models for designing power distribution network for sub-100nm integrated circuits. In: Proceedings of the IEEE International Symposium on Quality Electronic Design, pp. 287–292 (2007)

    Google Scholar 

  6. Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: Proceedings of the International Conference on Learning Research (2019)

    Google Scholar 

  7. Cadence: Innovus Implementation System (2018). https://www.cadence.com/en_US/home/tools/digital-design-and-signoff/soc-implementation-and-floorplanning/innovus-implementation-system.html

  8. Cadence: Voltus IC Power Integrity Solution (2018). https://www.cadence.com/en_US/home/tools/digital-design-and-signoff/silicon-signoff/voltus-ic-power-integrity-solution.html

  9. Chang, W., Lin, C., Mu, S., Chen, L., Tsai, C., Chiu, Y., Chao, M.C.: Generating routing-driven power distribution networks with machine-learning technique. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 36(8), 1237–1250 (2017)

    Article  Google Scholar 

  10. Chhabria, V.A., Sapatnekar, S.S.: OpeNPDN (2018). https://github.com/The-OpenROAD-Project/OpeNPDN

  11. Chhabria, V.A., Sapatnekar, S.S.: OpeNPDN: a neural-network-based framework for power delivery network synthesis. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 41(10), 3515–3528 (2022)

    Article  Google Scholar 

  12. Chhabria, V.A., Sapatnekar, S.S.: PDNSim (2021). https://github.com/The-OpenROAD-Project/OpenROAD/tree/master/src/psm

  13. Chhabria, V.A., Kahng, A.B., Kim, M., Mallappa, U., Sapatnekar, S.S., Xu, B.: Template-based PDN synthesis in floorplan and placement using classifier and CNN techniques. In: Proceedings of the Asia-South Pacific Design Automation Conference, pp. 44–49 (2020)

    Google Scholar 

  14. Chhabria, V.A., Ahuja, V., Prabhu, A., Patil, N., Jain, P., Sapatnekar, S.S.: Encoder-decoder networks for analyzing thermal and power delivery networks. ACM Trans. Des. Autom. Electron. Syst. (in press)

    Google Scholar 

  15. Chhabria, V.A., Ahuja, V., Prabhu, A., Patil, N., Jain, P., Sapatnekar, S.S.: Thermal and IR drop analysis using convolutional encoder-decoder networks. In: Proceedings of the Asia-South Pacific Design Automation Conference, pp. 690–696 (2021)

    Google Scholar 

  16. Chhabria, V.A., Kunal, K., Zabihi, M., Sapatnekar, S.S.: BeGAN-benchmarks (2021). https://github.com/UMN-EDA/BeGAN-benchmarks

  17. Chhabria, V.A., Kunal, K., Zabihi, M., Sapatnekar, S.S.: BeGAN: Power grid benchmark generation using a process-portable GAN-based methodology. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design (2021)

    Google Scholar 

  18. Chhabria, V.A., Zhang, Y., Ren, H., Keller, B., Khailany, B., Sapatnekar, S.S.: MAVIREC: ML-aided vectored IR-drop estimation and classification. In: Proceedings of the Design, Automation & Test in Europe, pp. 1825–1828 (2021)

    Google Scholar 

  19. Chiprout, E.: Fast flip-chip power grid analysis via locality and grid shells. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design, pp. 485–488 (2004)

    Google Scholar 

  20. Dey, S., Nandi, S., Trivedi, G.: PowerPlanningDL: reliability-aware framework for on-chip power grid design using deep learning. In: Proceedings of the Design, Automation & Test in Europe, pp. 1520–1525 (2020)

    Google Scholar 

  21. Dumoulin, V., Visin, F.: A guide to convolution arithmetic for deep learning. arXiv:1603.07285 (2016)

    Google Scholar 

  22. Fang, Y.C., Lin, H.Y., Su, M.Y., Li, C.M., Fang, E.J.W.: Machine-learning-based dynamic IR drop prediction for ECO. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design (2018)

    Google Scholar 

  23. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. In: Proceedings of the Conference on Neural Information Processing Systems, pp. 2672–2680 (2014)

    Google Scholar 

  24. Ho, C.T., Kahng, A.B.: IncPIRD: fast learning-based prediction of incremental IR drop. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design (2019)

    Google Scholar 

  25. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  26. Hsu, H., Chen, M., Chen, H., Li, H., Chen, S.: On effective flip-chip routing via pseudo single redistribution layer. In: Proceedings of the Design, Automation & Test in Europe, pp. 1597–1602 (2012)

    Google Scholar 

  27. Jakushokas, R., Friedman, E.G.: Methodology for multi-layer interdigitated power and ground network design. In: Proceedings of the IEEE International Symposium on Circuits and Systems, pp. 3208–3211 (2010)

    Google Scholar 

  28. Jin, W., Sadiqbatcha, S., Sun, Z., Zhou, H., Tan, S.X.D.: EM-GAN: data-driven fast stress analysis for multi-segment interconnects. In: Proceedings of the IEEE International Conference on Computer Design, pp. 296–303 (2020)

    Google Scholar 

  29. Jin, W., Sadiqbatcha, S., Zhang, J., Tan, S.X..D.: Full-chip thermal map estimation for commercial multi-core CPUs with generative adversarial learning. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design (2020)

    Google Scholar 

  30. Juan, D., Zhou, H., Marculescu, D., Li, X.: A learning-based autoregressive model for fast transient thermal analysis of chip-multiprocessors. In: Proceedings of the Asia-South Pacific Design Automation Conference, pp. 597–602 (2012)

    Google Scholar 

  31. Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: Proceedings of the International Conference on Learning Research (2018)

    Google Scholar 

  32. Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4396–4405 (2019)

    Google Scholar 

  33. Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Research (2015)

    Google Scholar 

  34. Kozhaya, J.N., Nassif, S.R., Najm, F.N.: Multigrid-like technique for power grid analysis. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design, pp. 480–487 (2001)

    Google Scholar 

  35. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)

    Article  Google Scholar 

  36. Li, P.: Power grid simulation via efficient sampling-based sensitivity analysis and hierarchical symbolic relaxation. In: Proceedings of the ACM/IEEE Design Automation Conference, pp. 664–669 (2005)

    Google Scholar 

  37. Li, P., Pileggi, L., Asheghi, M., Chandra, R.: IC thermal simulation and modeling via efficient multigrid-based approaches. IEEE Trans. Comput. Aided Desig. Integr. Circuits Syst. 25(9), 1763–1776 (2006)

    Article  Google Scholar 

  38. Li, Z., Balasubramanian, R., Liu, F., Nassif, S.: 2012 TAU power grid simulation contest: benchmark suite and results. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design, pp. 478–481 (2012)

    Google Scholar 

  39. Lin, S.Y., Fang, Y.C., Li, Y.C., Liu, Y., Yang, T., Lin, S.C., Li, C.M.J., Fang, E.J.W.: IR drop prediction of ECO-revised circuits using machine learning. In: Proceedings of the VLSI Test Symposium (2018)

    Google Scholar 

  40. Mao, X.J., Shen, C., Yang, Y.B.: Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Proceedings of the Conference on Neural Information Processing Systems (2016)

    Google Scholar 

  41. Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: Proceedings of the International Conference on Learning Research (2018)

    Google Scholar 

  42. Müller, S., Schüler, L., Zech, A., Heße, F.: GSTools v1.3: a toolbox for geostatistical modelling in Python. Geosci. Model Dev. 15, 3161–3182 (2022)

    Google Scholar 

  43. Nassif, S.: Power grid analysis benchmarks. In: Proceedings of the Asia-South Pacific Design Automation Conference, pp. 376–381 (2008)

    Google Scholar 

  44. Noguchi, A., Harada, T.: Image generation from small datasets via batch statistics adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2750–2758 (2019)

    Google Scholar 

  45. Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1717–1724 (2014)

    Google Scholar 

  46. Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)

    Article  Google Scholar 

  47. Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional networks for biomedical image segmentation. In: Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 234–241 (2015)

    Google Scholar 

  48. Sadiqbatcha, S., Zhang, J., Amrouch, H., Tan, S.X.D.: Real-time full-chip thermal tracking: a post-silicon, machine learning perspective. IEEE Trans. Comput. 71(6), 1411–1424 (2022)

    MATH  Google Scholar 

  49. Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2017)

    Article  Google Scholar 

  50. Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Proceedings of the Conference on Neural Information Processing Systems (2015)

    Google Scholar 

  51. Singh, J., Sapatnekar, S.S.: Partition-based algorithm for power grid design using locality. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 25(4), 664–677 (2006)

    Article  Google Scholar 

  52. Su, H., Hu, J., Sapatnekar, S.S., Nassif, S.R.: Congestion-driven codesign of power and signal networks. In: Proceedings of the ACM/IEEE Design Automation Conference, pp. 64–69 (2002)

    Google Scholar 

  53. Tan, X.D., Shi, C.R., Lungeanu, D., Lee, J.C., Yuan, L.P.: Reliability-constrained area optimization of VLSI power/ground networks via sequence of linear programmings. In: Proceedings of the ACM/IEEE Design Automation Conference, pp. 78–83 (1999)

    Google Scholar 

  54. The OpenROAD project (2022). https://github.com/The-OpenROAD-Project

  55. Wei, Y., Sze, C., Viswanathan, N., Li, Z., Alpert, C.J., Reddy, L., Huber, A.D., Tellez, G.E., Keller, D., Sapatnekar, S.S.: GLARE: global and local wiring aware routability evaluation. In: Proceedings of the ACM/IEEE Design Automation Conference, pp. 768–773 (2012)

    Google Scholar 

  56. Wen, J., Pan, S., Chang, N., Chuang, W., Xia, W., Zhu, D., Kumar, A., Yang, E., Srinivasan, K., Li, Y.: DNN-based fast static on-chip thermal solver. In: Proceedings of the IEEE Symposium on Semiconductor Thermal Measurment, Modeling, and Management, pp. 65–75 (2020)

    Google Scholar 

  57. Wu, X., Hong, X., Cai, Y., Luo, Z., Cheng, C.K., Gu, J., Dai, W.: Area minimization of power distribution network using efficient nonlinear programming techniques. IEEE Trans. Comput. Aided Desig. Integr. Circuits Syst. 23(7), 1086–1094 (2004)

    Article  Google Scholar 

  58. Xie, Z., Ren, H., Khailany, B., Sheng, Y., Santosh, S., Hu, J., Chen, Y.: PowerNet: transferable dynamic IR drop estimation via maximum convolutional neural network. In: Proceedings of the Asia-South Pacific Design Automation Conference, pp. 13–18 (2020)

    Google Scholar 

  59. Yazdani, F.: Foundations of Heterogeneous Integration: An Industry-Based, 2.5D/3D Pathfinding and Co-Design Approach. Springer, Boston (2018)

    Google Scholar 

  60. Zhan, Y., Kumar, S.V., Sapatnekar, S.S.: Thermally-aware design. Found. Trends Electron. Desig. Automat. 2(3), 255–370 (2008)

    Article  MATH  Google Scholar 

  61. Zhang, K., Guliani, A., Ogrenci-Memik, S., Memik, G., Yoshii, K., Sankaran, R., Beckman, P.: Machine learning-based temperature prediction for runtime thermal management across system components. IEEE Trans. Parallel Distrib. Syst. 29(2), 405–419 (2018)

    Article  Google Scholar 

  62. Zhao, M., Panda, R., Sapatnekar, S., Blaauw, D.: Hierarchical analysis of power distribution networks. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 21(2), 159–168 (2002)

    Article  Google Scholar 

  63. Zhao, M., Cong, Y., Carin, L.: On leveraging pretrained GANs for limited-data generation. In: International Conference on Machine Learning, pp. 11340–11351 (2020)

    Google Scholar 

  64. Zhong, Y., Wong, M.D.F.: Fast algorithms for IR drop analysis in large power grid. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design, pp. 351–357 (2005)

    Google Scholar 

  65. Zhuang, H., Yu, W., Weng, S., Kang, I., Lin, J., Zhang, X., Coutts, R., Cheng, C.: Simulation algorithms with exponential integration for time-domain analysis of large-scale power delivery networks. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 35(10), 1681–1694 (2016)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Minnesota, Minneapolis, MN, USA

    Vidya A. Chhabria & Sachin S. Sapatnekar

Authors
  1. Vidya A. Chhabria
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sachin S. Sapatnekar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Vidya A. Chhabria .

Editor information

Editors and Affiliations

  1. NVIDIA, Austin, TX, USA

    Haoxing Ren

  2. Texas A&M University, College Station, TX, USA

    Jiang Hu

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Chhabria, V.A., Sapatnekar, S.S. (2022). Deep Learning for Analyzing Power Delivery Networks and Thermal Networks. In: Ren, H., Hu, J. (eds) Machine Learning Applications in Electronic Design Automation. Springer, Cham. https://doi.org/10.1007/978-3-031-13074-8_5

Download citation

Publish with us

Policies and ethics

Search

Navigation