A learning-based methodology for routability prediction in placement

The routability of a circuit is a critical challenge due to the complexity of design rules. Global routing produces a congestion map on a coarse grid and feeds the results to the placer to optimize the design for reducing detailed-route DRC violations. However, there is a growing gap between global routing and the actual violations in detailed routing. This miscorrelation may end up unroutable for back-end detailed routing. In this work, a methodology as well as the framework flow based on machine learning technique is proposed to effectively predict detailed routing violations. After extracting appropriate features from placement, fast global routing and detailed routing violations, we use support vector machine techniques to train the prediction model, different from regression framework. We then also develop a prediction model for DRC violation density which can be integrated into placers. Experimental results show that the proposed approach can effectively forecast routability during placement stage.

[1]  Jin Hu,et al.  Progress and Challenges in VLSI Placement Research , 2012, Proceedings of the IEEE.

[2]  Zhongdong Qi,et al.  Accurate prediction of detailed routing congestion using supervised data learning , 2014, 2014 IEEE 32nd International Conference on Computer Design (ICCD).

[3]  Cheng-Kok Koh,et al.  Case study for placement solutions in ispd11 and dac12 routability-driven placement contests , 2013, ISPD '13.

[4]  Sachin S. Sapatnekar,et al.  GLARE: Global and local wiring aware routability evaluation , 2012, DAC Design Automation Conference 2012.

[5]  Hung-Ming Chen,et al.  Closing the Gap between Global and Detailed Placement: Techniques for Improving Routability , 2015, ISPD.

[6]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[7]  Andrew B. Kahng,et al.  BEOL stack-aware routability prediction from placement using data mining techniques , 2016, 2016 IEEE 34th International Conference on Computer Design (ICCD).

[8]  Ismail Bustany,et al.  ISPD 2014 benchmarks with sub-45nm technology rules for detailed-routing-driven placement , 2014, ISPD '14.

[9]  Andrew A. Kennings,et al.  Detailed routing violation prediction during placement using machine learning , 2017, 2017 International Symposium on VLSI Design, Automation and Test (VLSI-DAT).

[10]  Mango C.-T. Chao,et al.  Generating Routing-Driven Power Distribution Networks With Machine-Learning Technique , 2017, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[11]  Andrew B. Kahng,et al.  Routability Optimization for Industrial Designs at Sub-14nm Process Nodes Using Machine Learning , 2017, ISPD.

[12]  Tao Lin,et al.  POLAR 2.0: An effective routability-driven placer , 2014, 2014 51st ACM/EDAC/IEEE Design Automation Conference (DAC).

[13]  Tao Huang,et al.  Ripple 2.0: High quality routability-driven placement via global router integration , 2013, 2013 50th ACM/EDAC/IEEE Design Automation Conference (DAC).

[14]  Zhongdong Qi,et al.  An accurate detailed routing routability prediction model in placement , 2015, 2015 6th Asia Symposium on Quality Electronic Design (ASQED).

[15]  Jin Hu,et al.  A SimPLR method for routability-driven placement , 2011, 2011 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[16]  Jarrod A. Roy,et al.  What makes a design difficult to route , 2010, ISPD '10.

[17]  Yunqian Ma,et al.  Imbalanced Learning: Foundations, Algorithms, and Applications , 2013 .