skip to main content
10.1145/3670474.3685965acmconferencesArticle/Chapter ViewAbstractPublication PagesmlcadConference Proceedingsconference-collections
research-article

Cell Library Characterization for Composite Current Source Models Based on Gaussian Process Regression and Active Learning

Published: 09 September 2024 Publication History

Abstract

The composite current source (CCS) model has been adopted as an advanced timing model that represents the current behavior of cells for improved accuracy and better capability than traditional non-linear delay models (NLDM) to model complex dynamic effects and interactions under advanced process nodes. However, the high accuracy requirement, large amount of data and extensive simulation cost pose severe challenges to CCS characterization. To address these challenges, we introduce a novel Gaussian Process Regression(GPR) model with active learning(AL) to establish the characterization framework efficiently and accurately. Our approach significantly outperforms conventional commercial tools as well as learning based approaches by achieving an average absolute error of 2.05 ps and a relative error of 2.27% for current waveform of 57 cells under 9 process, voltage, temperature (PVT) corners with TSMC 22nm process. Additionally, our model drastically reduces the runtime to 27% and the storage by up to 19.5× compared with that required by commercial tools.

References

[1]
I. K. Rachit and M. S. Bhat. Autolibgen: An open source tool for standard cell library characterization at 65nm technology. In International Conference on Electronic Design, pages 1--6, 2008.
[2]
Ratnakar Goyal and Naresh Kumar. Current based delay models: A must for nanometer timing. In Cadence Live Conference (CDNLive), pages 1--8, 2005.
[3]
Dimitrios Garyfallou, Stavros Simoglou, Nikolaos Sketopoulos, Charalampos Antoniadis, Christos P. Sotiriou, Nestor Evmorfopoulos, and George Stamoulis. Gate delay estimation with library compatible current source models and effective capacitance. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, pages 962--972, 2021.
[4]
Waseem Raslan and Yehea Ismail. Deep learning autoencoder-based compression for current source model waveforms. In IEEE International Conference on Electronics, Circuits, and Systems (ICECS), pages 1--6, 2021.
[5]
Dimitrios Garyfallou, Anastasis Vagenas, Charalampos Antoniadis, Yehia Massoud, and George Stamoulis. Leveraging machine learning for gate-level timing estimation using current source models and effective capacitance. In Proceedings of the Great Lakes Symposium on VLSI 2022, pages 77--83, 2022.
[6]
Siemens. Addressing library characterization and verification challenges using ml. pages 4--6, 2022.
[7]
Synopsys. CCS timing library characterization guidelines, version 3.4. 2016.
[8]
Safar Hatami, Peter Feldmann, Soroush Abbaspour, and Massoud Pedram. Efficient compression and handling of current source model library waveforms. In Design, Automation Test in Europe Conference Exhibition, pages 1178--1183, 2009.
[9]
Eunice Naswali, Namhoon Kim, and Pravin Chandran. Fast and accurate library generation leveraging deep learning for ocv modelling. In International Symposium on Quality Electronic Design (ISQED), pages 349--354, 2021.
[10]
Eunice Naswali, Adalberto Claudio Quiros, and Pravin Chandran. Dnnlibgen: Deep neural network based fast library generator. In International Conference on Electronics, Circuits and Systems (ICECS), pages 574--577, 2019.
[11]
Florian Klemme and Hussam Amrouch. Machine learning for on-the-fly reliability-aware cell library characterization. IEEE Transactions on Circuits and Systems I: Regular Papers, pages 2569--2579, 2021.
[12]
Seyed Milad Ebrahimipour, Behnam Ghavami, Hamid Mousavi, Mohsen Raji, Zhenman Fang, and Lesley Shannon. Aadam: A fast, accurate, and versatile aging-aware cell library delay model using feed-forward neural network. In Proceedings of the 39th International Conference on Computer-Aided Design, pages 1--9, 2020.
[13]
Mohammad Saeed Abrishami, Massoud Pedram, and Shahin Nazarian. Csm-nn: Current source model based logic circuit simulation - a neural network approach. In International Conference on Computer Design (ICCD), pages 393--400, 2019.
[14]
Yufei Chen, Xiao Dong, Wei-Kai Shih, and Cheng Zhuo. Unleashing the potential of machine learning: Harnessing the dynamics of supply noise for timing signoff. In IEEE/ACM International Conference on Computer Aided Design (ICCAD), pages 1--6, 2023.
[15]
Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. The MIT Press, 2012.
[16]
Charu C. Aggarwal, Xiangnan Kong, Quanquan Gu, Jiawei Han, and Philip S. Yu. Active Learning: A Survey, chapter 22, pages 572--605. Chapman and Hall/CRC Press, 2014.
[17]
Dongrui Wu. Pool-based sequential active learning for regression. IEEE Transactions on Neural Networks and Learning Systems, pages 1348--1359, 2019.

Index Terms

  1. Cell Library Characterization for Composite Current Source Models Based on Gaussian Process Regression and Active Learning
                  Index terms have been assigned to the content through auto-classification.

                  Recommendations

                  Comments

                  Information & Contributors

                  Information

                  Published In

                  cover image ACM Conferences
                  MLCAD '24: Proceedings of the 2024 ACM/IEEE International Symposium on Machine Learning for CAD
                  September 2024
                  321 pages
                  ISBN:9798400706998
                  DOI:10.1145/3670474
                  Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

                  Sponsors

                  Publisher

                  Association for Computing Machinery

                  New York, NY, United States

                  Publication History

                  Published: 09 September 2024

                  Permissions

                  Request permissions for this article.

                  Check for updates

                  Author Tags

                  1. Active Learning
                  2. Current Source Models
                  3. Gaussian Process Regression
                  4. Standard Cell

                  Qualifiers

                  • Research-article
                  • Research
                  • Refereed limited

                  Conference

                  MLCAD '24
                  Sponsor:

                  Acceptance Rates

                  MLCAD '24 Paper Acceptance Rate 35 of 83 submissions, 42%;
                  Overall Acceptance Rate 35 of 83 submissions, 42%

                  Contributors

                  Other Metrics

                  Bibliometrics & Citations

                  Bibliometrics

                  Article Metrics

                  • 0
                    Total Citations
                  • 115
                    Total Downloads
                  • Downloads (Last 12 months)115
                  • Downloads (Last 6 weeks)15
                  Reflects downloads up to 16 Feb 2025

                  Other Metrics

                  Citations

                  View Options

                  Login options

                  View options

                  PDF

                  View or Download as a PDF file.

                  PDF

                  eReader

                  View online with eReader.

                  eReader

                  Figures

                  Tables

                  Media

                  Share

                  Share

                  Share this Publication link

                  Share on social media