Abstract: The present invention is related to a learning-based surrogate model capable of predicting operating condition-dependent time and/or frequency domain waveforms at the IC pins. The model of the present invention consists of a set of discrete features that can be extracted from a time-domain waveform and can be used to reconstruct the continuous time-domain waveform accurately and consequently reconstruct the frequency-domain characteristics of the time-domain waveform. The model of the present invention has a machine-learning framework e.g. an Artificial Neural Network, which can be trained to predict all the features extracted as a function of parameters characterizing the operating conditions.

Abstract: The time domain response of a simulated system is simulated by first receiving variables for the simulated system. A frequency domain simulation is performed over different frequencies using each of the variables to provide simulated frequency domain responses for the simulated system. A time domain simulation is performed over the different frequencies using a subset of simulated frequency domain responses to produce a plurality of simulated time domain responses for the simulated system. The subset of the simulated frequency domain responses is mapped to the plurality of simulated time domain responses to produce a frequency-domain-to-time-domain mapping. A plurality of mapped time domain responses is determined using the frequency-domain-to-time-domain mapping, where the plurality of simulated time domain responses and the plurality of mapped time domain responses provide time domain responses for each of the plurality of variables for the simulated system.

Abstract: The time domain response of a simulated system is simulated by first receiving variables for the simulated system. A frequency domain simulation is performed over different frequencies using each of the variables to provide simulated frequency domain responses for the simulated system. A time domain simulation is performed over the different frequencies using a subset of simulated frequency domain responses to produce a plurality of simulated time domain responses for the simulated system. The subset of the simulated frequency domain responses is mapped to the plurality of simulated time domain responses to produce a frequency-domain-to-time-domain mapping. A plurality of mapped time domain responses is determined using the frequency-domain-to-time-domain mapping, where the plurality of simulated time domain responses and the plurality of mapped time domain responses provide time domain responses for each of the plurality of variables for the simulated system.