A Data-Efficient Training Model for Signal Integrity Analysis based on Transfer Learning

The signal integrity analysis is an essential part of electronic design, while direct high speed signal analysis becomes a time-consuming work. As machine learning exhibits high performance in communication fields in recent years, deep neural network(DNN) is thought to be a key tool to predict eye diagram metrics. However, DNN based signal integrity analysis faces two challenges: demands for amounts of labelled data and long training period. In this paper, we propose a signal integrity analysis model based on transfer learning. The model makes full use of a trained network and trains networks for various channel environments. To achieve the same predicting accuracy, 64% labelled data are utilized for training compared to DNN. The application of hyper-parameters in the neural network improves the prediction accuracy of the eye diagram width and height by 42.7% and 49.24% compared to current methods in few shot signal integrity analysis.

[1]  Sunil Sudhakaran,et al.  Using deep neural networks to model nonlinear circuit blocks in wireline links , 2017, 2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS).

[2]  Ken Wu,et al.  High-Speed Channel Modeling With Machine Learning Methods for Signal Integrity Analysis , 2018, IEEE Transactions on Electromagnetic Compatibility.

[3]  Davy Pissoort,et al.  Combined circuit/full-wave simulations for electromagnetic immunity studies based on an extended S-parameter formulation , 2014, 2014 IEEE 18th Workshop on Signal and Power Integrity (SPI).

[4]  Jun Fan,et al.  Signal Integrity Design for High-Speed Digital Circuits: Progress and Directions , 2010, IEEE Transactions on Electromagnetic Compatibility.

[5]  Marvna Nesterova,et al.  Experimental Assessment of Stochastic Signals Through the Power Density Method , 2018, 2018 IEEE Symposium on Electromagnetic Compatibility, Signal Integrity and Power Integrity (EMC, SI & PI).

[6]  Mruganka Kashyap,et al.  A novel use of deep learning to optimize solution space exploration for signal integrity analysis , 2017, 2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS).

[7]  Ryo Mori,et al.  A high-speed, long-reach signal design challenge for 2.5-D LSI based on a low-cost silicon interposer and a large-scale SSO analysis , 2015, 2015 IEEE 65th Electronic Components and Technology Conference (ECTC).

[8]  Hua Zhao,et al.  Deep Belief Networks and deep learning , 2015, Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things.

[9]  Rakesh Malik,et al.  Signal Integrity and Power Integrity Methodology for Robust Analysis of On-the-Board System for High Speed Serial Links , 2009, 2009 12th Euromicro Conference on Digital System Design, Architectures, Methods and Tools.

[10]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[11]  Ranga Vemuri,et al.  Efficient Symbolic Sensitivity based Parasitic-Inclusive Optimization in Layout Aware Analog Circuit Synthesis , 2007, 20th International Conference on VLSI Design held jointly with 6th International Conference on Embedded Systems (VLSID'07).