Towards analyzing and improving robustness of software applications to intermittent and permanent faults in hardware

Abstract

Abstract-Although a significant fraction of emerging failure and wearout mechanisms result in intermittent or permanent faults in hardware, their impact (as distinct from transient faults) on software applications has not been well studied. In this paper, we develop a distinguishing application characteristic, referred to as similarity from fundamental circuit-level understanding of the failure mechanisms. We present a mathematical definition and a procedure for similarity computation for practical software applications and experimentally verify the relationship between similarity and fault rate. Leveraging dependence of application robustness on the similarity metric, we present example architecture independent code transformations to reduce similarity and thereby the worst-case fault rate with minimal performance degradation. Our experimental results with arithmetic unit faults show as much as 74% improvement in the worst case fault rate on benchmark kernels, with less than 10% runtime penalty.

Safety Evaluation of Automotive Electronics Using Virtual Prototypes

“…The verification of real-time requirements requires simulating time and concurrency. Usually, current reliability-aware emulators such as VarEMU [38,39] only take time in number of instructions into account. In contrast, SystemC includes a simulation kernel for event-driven simulation.…”

A HW-dependent software model for cross-layer fault analysis in embedded systems

“…In [14] related goals are pursued and specific code transformations were proposed to increase the robustness of software against hardware faults. However, the verification in [14] relies on a simulation-based method.…”

“…In [14] related goals are pursued and specific code transformations were proposed to increase the robustness of software against hardware faults. However, the verification in [14] relies on a simulation-based method. Verifying the effectiveness of such approaches in a formal way can increase the confidence about the applied resilience measures and allows for formulating safety guarantees for the system.…”