Accelerate SEU Simulation-Based Fault Injection With Spatio-Temporal Graph Convolutional Networks

Evaluating the sensitivity of circuits to single event upset (SEU) faults has become increasingly important and challenging due to the growing complexity of circuits. Simulation-based fault injection is time-intensive, particularly for highly complex circuits. This article proposes a novel approach using Spatio-temporal graph convolutional networks (STGCNs) to predict SEU fault propagation results in circuits. By representing circuits’ structure as graphs and integrating temporal features from the simulation workload, STGCNs can learn from these spatio-temporal graphs to identify SEU fault propagation patterns. To validate this method, we test it on six evaluation circuits, achieving a prediction accuracy of 93%–99%. Given this performance, to accelerate SEU simulation-based fault injection, we divide SEU faults into three subsets and use an STGCN fine-tuned on the training and validation dataset to predict SEU fault propagation in the test dataset, eliminating the need for simulation and reducing the required time. To identify an efficient dataset separation method, we compare three sampling methods: 1) spatial sampling (sampling flip-flops for injected faults); 2) temporal sampling (sampling time points for fault injection); and 3) hybrid sampling (incorporating both spatial and temporal sampling). The hybrid sampling approach is the most promising, optimizing the tradeoff between efficiency and accuracy. This approach reduces simulation time by 50% while maintaining accuracy above 95% on the six evaluation circuits.