FsimNNs: An Open-Source Graph Neural Network Platform for SEU Simulation-based Fault Injection

2025-11-12

AI Summary

To address the prohibitively high computational cost of fault injection in single-event upset (SEU) simulation—exacerbated by increasing circuit scale—this paper proposes a spatiotemporal graph neural network (STGNN)-based acceleration method. Methodologically, it innovatively integrates atrous spatial pyramid pooling (ASPP) with attention mechanisms to design three lightweight, efficient STGNN architectures. As a key contribution, we introduce the first open-source, multi-complexity circuit fault dataset specifically tailored for SEU simulation—comprising six benchmark circuits—to ensure model reproducibility and generalizability. Experimental results demonstrate that the proposed approach achieves high prediction accuracy (mean absolute error < 5.2%) while accelerating SEU vulnerability assessment by 12–47× compared to conventional simulation. This substantial speedup significantly reduces simulation overhead and establishes an efficient, scalable paradigm for robustness evaluation of large-scale integrated circuits under SEU effects.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Probabilistic Circuits and Graphical Models
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Simulation-based fault injection is a widely adopted methodology for assessing circuit vulnerability to Single Event Upsets (SEUs); however, its computational cost grows significantly with circuit complexity. To address this limitation, this work introduces an open-source platform that exploits Spatio-Temporal Graph Neural Networks (STGNNs) to accelerate SEU fault simulation. The platform includes three STGNN architectures incorporating advanced components such as Atrous Spatial Pyramid Pooling (ASPP) and attention mechanisms, thereby improving spatio-temporal feature extraction. In addition, SEU fault simulation datasets are constructed from six open-source circuits with varying levels of complexity, providing a comprehensive benchmark for performance evaluation. The predictive capability of the STGNN models is analyzed and compared on these datasets. Moreover, to further investigate the efficiency of the approach, we evaluate the predictive capability of STGNNs across multiple test cases and discuss their generalization capability. The developed platform and datasets are released as open-source to support reproducibility and further research on https://github.com/luli2021/FsimNNs.

Problem

• Accelerating SEU fault simulation using graph neural networks
• Addressing computational cost growth with circuit complexity
• Providing open-source platform for SEU vulnerability assessment

Innovation

• Uses Spatio-Temporal Graph Neural Networks
• Incorporates ASPP and attention mechanisms
• Provides open-source platform and datasets