ABSTRACT
Interconnect spacing is getting increasingly smaller in advanced technology nodes, which adversely increases the capacitive coupling of adjacent interconnect wires. It makes crosstalk a significant contributor to signal integrity and timing, and it is now imperative to prevent crosstalk-induced noise and delay issues in the earlier stages of VLSI design flow. Nonetheless, since the crosstalk effect depends primarily on the switching of neighboring nets, accurate crosstalk evaluation is only viable at the late stages of design flow with routing information available, e.g., after detailed routing. There have also been previous efforts in early-stage crosstalk prediction, but they mostly rely on time-expensive trial routing. In this work, we propose a machine learning-based routing-free crosstalk prediction framework. Given a placement, we identify routing and net topology-related features, along with electrical and logical features, which affect crosstalk-induced noise and delay. We then employ machine learning techniques to train the crosstalk prediction models, which can be used to identify crosstalk-critical nets in placement stages. Experimental results demonstrate that the proposed method can instantly classify more than 70% of crosstalk-critical nets after placement with a false-positive rate of less than 2%.
- Kanak Agarwal, Dennis Sylvester, and David Blaauw. 2006. Modeling and analysis of crosstalk noise in coupled RLC interconnects. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 25, 5 (2006), 892--901.Google ScholarDigital Library
- Christoph Albrecht. 2005. IWLS 2005 benchmarks. In IEEE International Workshop for Logic Synthesis (IWLS). 9--9.Google Scholar
- Charles J Alpert, Anirudh Devgan, and Stephen T Quay. 1999. Buffer insertion for noise and delay optimization. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 18, 11 (1999), 1633--1645.Google ScholarDigital Library
- Murat R Becer, David Blaauw, Ilan Algor, Rajendran Panda, Chanhee Oh, Vladimir Zolotov, and Ibrahim N Hajj. 2004. Postroute gate sizing for crosstalk noise reduction. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 23, 12 (2004), 1670--1677.Google ScholarDigital Library
- Murat R Becer, David Blaauw, Ibrahim N Hajj, and Rajendran Panda. 2002. Early probabilistic noise estimation for capacitively coupled interconnects. In ACM/IEEE International Workshop on System-level Interconnect Prediction (SLIP). 77--83.Google ScholarDigital Library
- Lauren Hui Chen and Malgorzata Marek-Sadowska. 2002. Incremental delay change due to crosstalk noise. In ACM International Symposium on Physical Design (ISPD). 120--125.Google ScholarDigital Library
- Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In ACM International Conference on Knowledge Discovery and Data Mining (DMKD). 785--794.Google ScholarDigital Library
- Lawrence T Clark, Vinay Vashishtha, Lucian Shifren, Aditya Gujja, Saurabh Sinha, Brian Cline, Chandarasekaran Ramamurthy, and Greg Yeric. 2016. ASAP7: A 7-nm finFET predictive process design kit. Microelectronics Journal 53 (2016), 105--115.Google ScholarDigital Library
- Chunjie Duan, Anup Tirumala, and Sunil P Khatri. 2001. Analysis and avoidance of cross-talk in on-chip buses. In IEEE International Symposium on High Performance Interconnects (ISHPI). 133--138.Google ScholarCross Ref
- Fang-Yu Fan, Hung-Ming Chen, and Isabel Liu. 2010. Technology mapping with crosstalk noise avoidance. In IEEE Asia and South Pacific Design Automation Conference (ASP-DAC). 319--324.Google Scholar
- Matthias Fey and Jan Eric Lenssen. 2019. Fast graph representation learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428 (2019).Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In IEEE Conference and Workshop on Neural Information Processing Systems (NIPS). 1024--1034.Google Scholar
- Andrew B Kahng, Mulong Luo, and Siddhartha Nath. 2015. SI for free: machine learning of interconnect coupling delay and transition effects. In ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP). 1--8.Google ScholarCross Ref
- Taghi M Khoshgoftaar, Moiz Golawala, and Jason Van Hulse. 2007. An empirical study of learning from imbalanced data using random forest. In IEEE International Conference on Tools with Artificial Intelligence (ICTAI). 310--317.Google ScholarDigital Library
- Martin Kuhlmann and Sachin S Sapatnekar. 2001. Exact and efficient crosstalk estimation. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 20, 7 (2001), 858--866.Google ScholarDigital Library
- Jinan Lou and Wei Chen. 2004. Crosstalk-aware placement. IEEE Design & Test of Computers 21, 1 (2004), 24--32.Google ScholarDigital Library
- Giovanna Menardi and Nicola Torelli. 2014. Training and assessing classification rules with imbalanced data. Data Mining and Knowledge Discovery 28, 1 (2014), 92--122.Google ScholarDigital Library
- Phiroze N Parakh and Richard B Brown. 1999. Crosstalk constrained global route embedding. In ACM Proceedings of the International Symposium on Physical Design (ISPD). 201--206.Google ScholarDigital Library
- Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. PyTorch: An imperative style, high-performance deep learning library. In IEEE Conference on Neural Information Processing Systems (NIPS). 8024--8035.Google Scholar
- Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12 (2011), 2825--2830.Google ScholarDigital Library
- Khalid Rahmat, Jose Neves, and Jin-Fuw Lee. 1998. Methods for calculating coupling noise in early design: a comparative analysis. In IEEE/ACM International Conference on Computer Design (ICCAD). 76--81.Google ScholarCross Ref
- Haoxing Ren, David Pan, and Paul G. Villarubia. 2004. True crosstalk aware incremental placement with noise map. In IEEE/ACM International Conference on Computer Aided Design (ICCAD). 402--409.Google Scholar
- Hariharan Sankaran and Srinivas Katkoori. 2009. Simultaneous Scheduling, Allocation, Binding, Re-Ordering, and Encoding for Crosstalk Pattern Minimization During High-Level Synthesis. IEEE Transactions on Very Large Scale Integration Systems 19, 2 (2009), 217--226.Google ScholarDigital Library
- Peter Spindler and Frank M Johannes. 2007. Fast and accurate routing demand estimation for efficient routability-driven placement. In IEEE Design, Automation & Test in Europe Conference & Exhibition (DATE). 1--6.Google Scholar
- Hsiao-Ping Tseng, Louis Scheffer, and Carl Sechen. 2001. Timing-and crosstalk-driven area routing. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 20, 4 (2001), 528--544.Google ScholarDigital Library
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- Ashok Vittal and Malgorzata Marek-Sadowska. 1997. Crosstalk reduction for VLSI. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 16, 3 (1997), 290--298.Google ScholarDigital Library
- Di Wu, Jiang Hu, Rabi Mahapatra, and Min Zhao. 2004. Layer assignment for crosstalk risk minimization. In IEEE Asia and South Pacific Design Automation Conference (ASP-DAC). 159--162.Google Scholar
- Zhiyao Xie, Yu-Hung Huang, Guan-Qi Fang, Haoxing Ren, Shao-Yun Fang, Yiran Chen, and Jiang Hu. 2018. RouteNet: Routability prediction for mixed-size designs using convolutional neural network. In IEEE/ACM International Conference on Computer-Aided Design (ICCAD). 1--8.Google ScholarDigital Library
- Hai Zhou and Martin D F Wong. 1999. Global routing with crosstalk constraints. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 18, 11 (1999), 1683--1688.Google ScholarDigital Library
Index Terms
- Routing-free crosstalk prediction
Recommendations
Crosstalk Estimation in Dual Aggressor Environment
ARTCOM '10: Proceedings of the 2010 International Conference on Advances in Recent Technologies in Communication and ComputingThe paper aims to analyze the effect of crosstalk in dual aggressor environment. The extent of crosstalk noise with the increment in the interconnect length is observed. It also observes the effect on delay with the gradual increment in the interconnect ...
Compact models and computation of crosstalk for sub-threshold interconnect circuits
In this paper, an analytical framework to model crosstalk in sub-threshold regime of buffer driven coupled interconnects has been presented. Sub-threshold current model is used to represent the transistor. Propagation delay and timing are determined for ...
Crosstalk analysis of CMOS buffer driven interconnects for ultra-low power applications
In this paper, an analytical framework to model crosstalk in sub-threshold regime of buffer driven capacitively coupled interconnects has been carried out. The proposed analytical model captures waveform shape and noise peaks quite efficiently. It is ...
Comments