@inproceedings{9d87375d85b84fb79b10eb69e77bd820,
title = "Correcting Soft Errors Online in Fast Fourier Transform",
abstract = "While many algorithm-based fault tolerance (ABFT) schemes have been proposed to detect soft errors offline in the fast Fourier transform (FFT) after computation finishes, none of the existing ABFT schemes detect soft errors online before the computation finishes. This paper presents an online ABFT scheme for FFT so that soft errors can be detected online and the corrupted computation can be terminated in a much more timely manner. We also extend our scheme to tolerate both arithmetic errors and memory errors, develop strategies to reduce its fault tolerance overhead and improve its numerical stability and fault coverage, and finally incorporate it into the widely used FFTW library - one of the today's fastest FFT software implementations. Experimental results demonstrate that: (1) the proposed online ABFT scheme introduces much lower overhead than the existing offline ABFT schemes; (2) it detects errors in a much more timely manner; and (3) it also has higher numerical stability and better fault coverage.",
keywords = "Algorithm-Based Fault Tolerance, DFT, FFT, FFTW, Soft Errors",
author = "Xin Liang and Jieyang Chen and Dingwen Tao and Sihuan Li and Panruo Wu and Hongbo Li and Kaiming Ouyang and Yuanlai Liu and Fengguang Song and Zizhong Chen",
note = "Publisher Copyright: {\textcopyright} 2017 ACM.; 2017 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017 ; Conference date: 12-11-2017 Through 17-11-2017",
year = "2017",
doi = "10.1145/3126908.3126915",
language = "English",
series = "International Conference for High Performance Computing, Networking, Storage and Analysis, SC",
publisher = "IEEE Computer Society",
booktitle = "SC 2017 - International Conference for High Performance Computing, Networking, Storage and Analysis",
}