Silent error detection in numerical time-stepping schemes

Abstract

Errors due to hardware or low level software problems, if detected, can be fixed by various schemes, such as recomputation from a checkpoint. Silent errors are errors in application state that have escaped low-level error detection. At extreme scale, where machines can perform astronomically many operations per second, silent errors threaten the validity of computed results. We propose a new paradigm for detecting silent errors at the application level. Our central idea is to frequently compare computed values to those provided by a cheap checking computation, and to build error detectors based on the difference between the two output sequences. Numerical analysis provides us with usable checking computations for the solution of initial-value problems in ODEs and PDEs, arguably the most common problems in computational science. Here, we provide, optimize, and test methods based on Runge-Kutta and linear multistep methods for ODEs, and on implicit and explicit finite difference schemes for PDEs. We take the heat equation and Navier-Stokes equations as examples. In tests with artificially injected errors, this approach effectively detects almost all meaningful errors, without significant slowdown.

Cited by in corpus (6)

• Reproducibility, Replicability, and Repeatability: A survey of reproducible research with a focus on high performance computing
• Achieving algorithmic resilience for temporal integration through spectral deferred corrections
• Is the Multigrid Method Fault Tolerant? The Multilevel Case
• Is the Multigrid Method Fault Tolerant? The Two-Grid Case
• A Backward/Forward Recovery Approach for the Preconditioned Conjugate Gradient Method
• Resilience Against Soft Faults through Adaptivity in Spectral Deferred Correction