Logo image
Transformer-Based Architecture for Fault Propagation Modeling in Transient Fault Analysis
會議論文

Transformer-Based Architecture for Fault Propagation Modeling in Transient Fault Analysis

Chia-Ying Lin, Jing-Jia Liou 和 Harry Chen
Proceedings - Asian Test Symposium, 頁碼.37-42
IEEE
2025 IEEE 34th Asian Test Symposium (ATS) (Tokyo, Japan, 16/12/2025–19/12/2025)
16/12/2025

摘要

Circuit noise Circuit synthesis Circuits Fault injection Fault propagation modeling Fault simulation Filtering Flip-flops Logic circuits Register transfer level Signal correlation System-on-chip Transformer model Transient fault Circuits and Systems Microprocessors
Fault simulation is essential for transient fault analysis, yet it is extremely time-consuming. Fault propagation depends on signal logic values and their correlations with circuit logics. This paper proposes a Transformer-based architecture for fault propagation modeling to predict fault propagation outcomes at the register-transfer level (RTL). For the proposed method, we encoded logic values of all signals of the circuit with two-layer embeddings and fault injection information to construct the model's input token sequence. The self-attention mechanism of Transformer is responsible for capturing intersignal dependencies. The training dataset is collected from the PicoRV32 RISC-V core through traditional bit-level fault simulation. Experimental results show that the proposed model achieves an average propagation accuracy of 99.78% on the training group and 97.68% on the testing group (unseen benchmarks), with a speedup ranging from677 \timesto{3}{0}{4}4 \timescompared to RTL simulation. The proposed approach provides a scalable and efficient solution for accelerating transient fault analysis.

相關連結

指標

1 檢視次數

詳細資料

Logo image