Estimating Code Vulnerability to Timing Errors Via Microarchitecture-Aware Machine Learning

Styliani Tompazi, Ioannis Tsiokanos, Jesús Martínez del Rincón, Georgios Karakonstantis

Abstract: This article addresses the microarchitecture-aware modeling of timing errors and the estimation of the vulnerability of SW programs to such errors. A significance-aware code vulnerability factor (SCVF) quantifies the susceptibility of applications to such timing errors, utilizing a machine learning (ML)-based error prediction model. This is complemented by a workloadaware error prediction model, which is based on supervised ML methods.