Behavioral Modeling of Pre-emphasis Drivers Including Power Supply Noise Using Neural Networks. Yu, H., Shin, J., Michalka, T., Larbi, M., & Swaminathan, M. In 2019 IEEE 10th Latin American Symposium on Circuits Systems (LASCAS), pages 37–40, February, 2019. doi abstract bibtex This paper addresses the nonlinear behavioral modeling of pre-emphasis drivers including power supply noise. The proposed multiple-port model relies on the use of power-aware weighting functions that control the driver's output stage to model the pre-emphasis behavior with non-ideal power supply accurately. The weighting functions are implemented using feed-forward neural networks (FFNNs), and the dynamic memory characteristics of driver's ports are captured using recurrent neural networks (RNNs). Practical industrial driver example demonstrates that the proposed modeling method offers good accuracy, flexibility and significant simulation speed-up to facilitate signal integrity and power integrity analysis without compromising intellectual property (IP).
@inproceedings{yu_behavioral_2019,
title = {Behavioral {Modeling} of {Pre}-emphasis {Drivers} {Including} {Power} {Supply} {Noise} {Using} {Neural} {Networks}},
doi = {10.1109/LASCAS.2019.8667589},
abstract = {This paper addresses the nonlinear behavioral modeling of pre-emphasis drivers including power supply noise. The proposed multiple-port model relies on the use of power-aware weighting functions that control the driver's output stage to model the pre-emphasis behavior with non-ideal power supply accurately. The weighting functions are implemented using feed-forward neural networks (FFNNs), and the dynamic memory characteristics of driver's ports are captured using recurrent neural networks (RNNs). Practical industrial driver example demonstrates that the proposed modeling method offers good accuracy, flexibility and significant simulation speed-up to facilitate signal integrity and power integrity analysis without compromising intellectual property (IP).},
booktitle = {2019 {IEEE} 10th {Latin} {American} {Symposium} on {Circuits} {Systems} ({LASCAS})},
author = {Yu, H. and Shin, J. and Michalka, T. and Larbi, M. and Swaminathan, M.},
month = feb,
year = {2019},
keywords = {\#broken, Behavioral modeling, Driver circuits, FFNNs, Integrated circuit modeling, Jab/\#LASCAS, Load modeling, Power supplies, Power transmission lines, RNNs, Recurrent neural networks, circuit analysis computing, driver circuits, driver output stage, driver ports, dynamic memory characteristics, feedforward neural nets, feedforward neural networks, industrial driver, input/output buffer modeling, intellectual property, multiple-port model, neural network, nonideal power supply, nonlinear behavioral modeling, power integrity, power integrity analysis, power supply circuits, power supply noise, power-aware weighting functions, pre-emphasis driver, pre-emphasis drivers, recurrent neural nets, recurrent neural networks, signal integrity, signal integrity analysis},
pages = {37--40},
}
Downloads: 0
{"_id":"BTFhQS2J3vXxArPBq","bibbaseid":"yu-shin-michalka-larbi-swaminathan-behavioralmodelingofpreemphasisdriversincludingpowersupplynoiseusingneuralnetworks-2019","author_short":["Yu, H.","Shin, J.","Michalka, T.","Larbi, M.","Swaminathan, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Behavioral Modeling of Pre-emphasis Drivers Including Power Supply Noise Using Neural Networks","doi":"10.1109/LASCAS.2019.8667589","abstract":"This paper addresses the nonlinear behavioral modeling of pre-emphasis drivers including power supply noise. The proposed multiple-port model relies on the use of power-aware weighting functions that control the driver's output stage to model the pre-emphasis behavior with non-ideal power supply accurately. The weighting functions are implemented using feed-forward neural networks (FFNNs), and the dynamic memory characteristics of driver's ports are captured using recurrent neural networks (RNNs). Practical industrial driver example demonstrates that the proposed modeling method offers good accuracy, flexibility and significant simulation speed-up to facilitate signal integrity and power integrity analysis without compromising intellectual property (IP).","booktitle":"2019 IEEE 10th Latin American Symposium on Circuits Systems (LASCAS)","author":[{"propositions":[],"lastnames":["Yu"],"firstnames":["H."],"suffixes":[]},{"propositions":[],"lastnames":["Shin"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Michalka"],"firstnames":["T."],"suffixes":[]},{"propositions":[],"lastnames":["Larbi"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Swaminathan"],"firstnames":["M."],"suffixes":[]}],"month":"February","year":"2019","keywords":"#broken, Behavioral modeling, Driver circuits, FFNNs, Integrated circuit modeling, Jab/#LASCAS, Load modeling, Power supplies, Power transmission lines, RNNs, Recurrent neural networks, circuit analysis computing, driver circuits, driver output stage, driver ports, dynamic memory characteristics, feedforward neural nets, feedforward neural networks, industrial driver, input/output buffer modeling, intellectual property, multiple-port model, neural network, nonideal power supply, nonlinear behavioral modeling, power integrity, power integrity analysis, power supply circuits, power supply noise, power-aware weighting functions, pre-emphasis driver, pre-emphasis drivers, recurrent neural nets, recurrent neural networks, signal integrity, signal integrity analysis","pages":"37–40","bibtex":"@inproceedings{yu_behavioral_2019,\n\ttitle = {Behavioral {Modeling} of {Pre}-emphasis {Drivers} {Including} {Power} {Supply} {Noise} {Using} {Neural} {Networks}},\n\tdoi = {10.1109/LASCAS.2019.8667589},\n\tabstract = {This paper addresses the nonlinear behavioral modeling of pre-emphasis drivers including power supply noise. The proposed multiple-port model relies on the use of power-aware weighting functions that control the driver's output stage to model the pre-emphasis behavior with non-ideal power supply accurately. The weighting functions are implemented using feed-forward neural networks (FFNNs), and the dynamic memory characteristics of driver's ports are captured using recurrent neural networks (RNNs). Practical industrial driver example demonstrates that the proposed modeling method offers good accuracy, flexibility and significant simulation speed-up to facilitate signal integrity and power integrity analysis without compromising intellectual property (IP).},\n\tbooktitle = {2019 {IEEE} 10th {Latin} {American} {Symposium} on {Circuits} {Systems} ({LASCAS})},\n\tauthor = {Yu, H. and Shin, J. and Michalka, T. and Larbi, M. and Swaminathan, M.},\n\tmonth = feb,\n\tyear = {2019},\n\tkeywords = {\\#broken, Behavioral modeling, Driver circuits, FFNNs, Integrated circuit modeling, Jab/\\#LASCAS, Load modeling, Power supplies, Power transmission lines, RNNs, Recurrent neural networks, circuit analysis computing, driver circuits, driver output stage, driver ports, dynamic memory characteristics, feedforward neural nets, feedforward neural networks, industrial driver, input/output buffer modeling, intellectual property, multiple-port model, neural network, nonideal power supply, nonlinear behavioral modeling, power integrity, power integrity analysis, power supply circuits, power supply noise, power-aware weighting functions, pre-emphasis driver, pre-emphasis drivers, recurrent neural nets, recurrent neural networks, signal integrity, signal integrity analysis},\n\tpages = {37--40},\n}\n\n\n\n","author_short":["Yu, H.","Shin, J.","Michalka, T.","Larbi, M.","Swaminathan, M."],"key":"yu_behavioral_2019","id":"yu_behavioral_2019","bibbaseid":"yu-shin-michalka-larbi-swaminathan-behavioralmodelingofpreemphasisdriversincludingpowersupplynoiseusingneuralnetworks-2019","role":"author","urls":{},"keyword":["#broken","Behavioral modeling","Driver circuits","FFNNs","Integrated circuit modeling","Jab/#LASCAS","Load modeling","Power supplies","Power transmission lines","RNNs","Recurrent neural networks","circuit analysis computing","driver circuits","driver output stage","driver ports","dynamic memory characteristics","feedforward neural nets","feedforward neural networks","industrial driver","input/output buffer modeling","intellectual property","multiple-port model","neural network","nonideal power supply","nonlinear behavioral modeling","power integrity","power integrity analysis","power supply circuits","power supply noise","power-aware weighting functions","pre-emphasis driver","pre-emphasis drivers","recurrent neural nets","recurrent neural networks","signal integrity","signal integrity analysis"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/bxt101","dataSources":["Wsv2bQ4jPuc7qme8R"],"keywords":["#broken","behavioral modeling","driver circuits","ffnns","integrated circuit modeling","jab/#lascas","load modeling","power supplies","power transmission lines","rnns","recurrent neural networks","circuit analysis computing","driver circuits","driver output stage","driver ports","dynamic memory characteristics","feedforward neural nets","feedforward neural networks","industrial driver","input/output buffer modeling","intellectual property","multiple-port model","neural network","nonideal power supply","nonlinear behavioral modeling","power integrity","power integrity analysis","power supply circuits","power supply noise","power-aware weighting functions","pre-emphasis driver","pre-emphasis drivers","recurrent neural nets","recurrent neural networks","signal integrity","signal integrity analysis"],"search_terms":["behavioral","modeling","pre","emphasis","drivers","including","power","supply","noise","using","neural","networks","yu","shin","michalka","larbi","swaminathan"],"title":"Behavioral Modeling of Pre-emphasis Drivers Including Power Supply Noise Using Neural Networks","year":2019}