GATPS: An attention-based graph neural network for predicting SDC-causing instructions

• Published in: 2021 IEEE 39th VLSI Test Symposium (VTS) pp. 1 - 7
• Main Authors: Ma, Junchi, Duan, Zongtao, Tang, Lei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 25.04.2021
• Subjects: Adaptation models; Attention Mechanism; Graph Neural Network; Graph neural networks; Machine learning; Machine learning algorithms; Prediction algorithms; Predictive models; Silent Data Corruption; Soft Error; Very large scale integration
• ISSN: 2375-1053
• DOI: 10.1109/VTS50974.2021.9441056

Soft errors can lead to silent data corruption (SDC), seriously compromising the reliability of a system. To detect SDC, a profiling of SDC-causing instructions is usually needed to decide which instructions to protect. Current approaches gain SDC-causing instructions by using machine learning algorithms. Most of existing algorithms suffer from a lack of accuracy. Researchers choose certain structural features as input based on their understanding of fault propagation. Such hand-tuned features prevent models from reproducing the reasoning of fault propagation and that, in turn, limits their ability to make good prediction decisions. We propose GATPS, which is a Graph Attention neTwork to Predict SDC-causing instructions. The task of SDC prediction is converted into node classification in a heterogenous graph, which applies different types of edges to represent different instruction relations. Low dimensional embedding of each node is computed by attending over its neighbors through multiple types of edges. The hidden structural features related to SDC propagation can be captured automatically. To quantify fault effects between instructions, attention mechanism is applied to assign different importance to nodes of a same neighborhood. Experimental results show that GATPS improves F1 score of SDC prediction by 11.0 %-21.7 % over most competitive machine learning methods.