Buffer-Parameterized Machine Learning Surrogate Models for Cross-Technology Signal Integrity Analysis and Optimization

TL;DR

This paper presents a buffer-parameterized machine learning surrogate modeling approach for PCB signal integrity analysis that handles cross-technology variations without retraining, enabling faster design optimization.

Contribution

It introduces a novel ML surrogate framework incorporating buffer parameters as dynamic inputs and benchmarks various models for high-dimensional SI prediction.

Findings

Gaussian process regression performs best with limited data.

Neural networks outperform other models on large datasets.

The approach enables rapid cross-technology SI analysis and optimization.

Abstract

Signal integrity (SI) analysis in printed circuit board (PCB) interconnects faces increasing complexity due to diverse integrated circuit (IC) buffer technologies, varying operating conditions, and manufacturing tolerances. Existing machine learning (ML) surrogate models for predicting SI metrics such as the inner eye contour, eye-height (EH), eye-width (EW), and transient waveform features typically rely on fixed buffer parameters, requiring costly new data generation and retraining cycles for every technology shift. This paper introduces a buffer-parameterized ML surrogate modeling methodology capable of handling cross-technology variations without retraining by treating IC buffer characteristics, e.g., clock frequency, supply voltage, rise/fall times, jitter, and internal resistors and capacitors, as dynamic model inputs alongside PCB parameters. To identify the optimal surrogate architecture for this high-dimensional space, a comprehensive benchmarking study compares tree-based methods (RFR/GBM), kernel methods (SVR/KRR), Gaussian process regression (GPR), and neural networks. The framework is subsequently validated on a complex interconnect with 44 design parameters. Results show that while anisotropic GPR excels in low-data regimes, neural networks heavily outperform other models on large datasets. Finally, the practical value of the ML surrogate models is demonstrated through a cross-technology design space exploration and optimization scenario, showcasing massive computational speedups for eye mask compliance checking compared to simulation.