Resilience against soft faults through adaptivity in spectral deferred correction
Publikationstyp
Conference Paper
Date Issued
2026-08-06
Sprache
English
First published in
Number in series
535
Start Page
31
End Page
51
Citation
Go20 Conference on Scientific Computing and Software, Go20 CSCS 2024 (2026)
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
Springer
ISBN of container
978-3-032-17809-1
978-3-032-17810-7
978-3-032-17811-4
978-3-032-17812-1
Is Supplemented By
As supercomputers grow in hardware complexity, their susceptibility to faults increases, and measures need to be taken to ensure the correctness of results. Some numerical algorithms have certain characteristics that allow them to recover from some types of faults. It has been demonstrated that adaptive Runge–Kutta methods provide resilience against transient faults without adding computational cost. Using recent advances in adaptive step size selection for spectral deferred correction (SDC), an iterative numerical time stepping scheme that can achieve arbitrary order, we show that adaptive SDC can also detect and correct transient faults. Its performance is found to be comparable to that of the dedicated resilience strategy Hot Rod.
Subjects
Adaptivity
Resilience
Soft faults
Spectral deferred correction
Time integration
DDC Class
510: Mathematics
004: Computer Sciences