On soft errors in the Conjugate Gradient method: sensitivity and robust numerical detection: Sur les soft-erreurs dans la méthode du Gradient Conjugué: sensibilité et détection numérique robuste

Abstract : The conjugate gradient (CG) method is the most widely used iterative scheme for the solution of large sparse systems of linear equations when the matrix is symmetric positive definite. Although more than sixty year old, it is still a serious candidate for extreme-scale computation on large computing platforms. On the technological side, the continuous shrinking of transistor geometry and the increasing complexity of these devices affect dramatically their sensitivity to natural radiation, and thus diminish their reliability. One of the most common effects produced by natural radiation is the single event upset which consists in a bit-flip in a memory cell producing unexpected results at application level. Consequently, the future computing facilities at extreme scale might be more prone to errors of any kind including bit-flip during calculation. These numerical and technological observations are the main motivations for this work, where we first investigate through extensive numerical experiments the sensitivity of CG to bit-flips in its main computationally intensive kernels, namely the matrix-vector product and the preconditioner application. We further propose numerical criteria to detect the occurrence of such faults; we assess their robustness through extensive numerical experiments.
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download

https://hal.inria.fr/hal-01929738
Contributor : Luc Giraud <>
Submitted on : Wednesday, November 21, 2018 - 1:53:19 PM
Last modification on : Thursday, May 9, 2019 - 11:58:04 AM
Long-term archiving on : Friday, February 22, 2019 - 1:51:18 PM

File

RR-9226.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01929738, version 1

Citation

Emmanuel Agullo, Siegfried Cools, Emrullah Fatih-Yetkin, Luc Giraud, Wim Vanroose. On soft errors in the Conjugate Gradient method: sensitivity and robust numerical detection: Sur les soft-erreurs dans la méthode du Gradient Conjugué: sensibilité et détection numérique robuste. [Research Report] RR-9226, Inria Bordeaux Sud-Ouest. 2018. ⟨hal-01929738⟩

Share

Metrics

Record views

154

Files downloads

237