% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Agullo:888522,
author = {Agullo, Emmanuel and Altenbernd, Mirco and Anzt, Hartwig
and Bautista-Gomez, Leonardo and Benacchio, Tommaso and
Bonaventura, Luca and Bungartz, Hans-Joachim and Chatterjee,
Sanjay and Ciorba, Florina M. and DeBardeleben, Nathan and
Drzisga, Daniel and Eibl, Sebastian and Engelmann, Christian
and Gansterer, Wilfried N. and Giraud, Luc and Goeddeke,
Dominik and Heisig, Marco and Jezequel, Fabienne and Kohl,
Nils and Li, Xiaoye Sherry and Lion, Romain and Mehl, Miriam
and Mycek, Paul and Obersteiner, Michael and Quintana-Orti,
Enrique S. and Rizzi, Francesco and Ruede, Ulrich and
Schulz, Martin and Fung, Fred and Speck, Robert and Stals,
Linda and Teranishi, Keita and Thibault, Samuel and
Thoennes, Dominik and Wagner, Andreas and Wohlmuth, Barbara},
title = {{R}esiliency in {N}umerical {A}lgorithm {D}esign for
{E}xtreme {S}cale {S}imulations},
reportid = {FZJ-2020-04986},
year = {2020},
note = {45 pages, 3 figures, submitted to The International Journal
of High Performance Computing Applications},
abstract = {This work is based on the seminar titled ``Resiliency in
Numerical Algorithm Design for Extreme Scale Simulations''
held March 1-6, 2020 at Schloss Dagstuhl, that was attended
by all the authors. Naive versions of conventional
resilience techniques will not scale to the exascale regime:
with a main memory footprint of tens of Petabytes,
synchronously writing checkpoint data all the way to
background storage at frequent intervals will create
intolerable overheads in runtime and energy consumption.
Forecasts show that the mean time between failures could be
lower than the time to recover from such a checkpoint, so
that large calculations at scale might not make any progress
if robust alternatives are not investigated. More advanced
resilience techniques must be devised. The key may lie in
exploiting both advanced system features as well as specific
application knowledge. Research will face two essential
questions: (1) what are the reliability requirements for a
particular computation and (2) how do we best design the
algorithms and software to meet these requirements? One
avenue would be to refine and improve on system- or
application-level checkpointing and rollback strategies in
the case an error is detected. Developers might use fault
notification interfaces and flexible runtime systems to
respond to node failures in an application-dependent
fashion. Novel numerical algorithms or more stochastic
computational approaches may be required to meet accuracy
requirements in the face of undetectable soft errors. The
goal of this Dagstuhl Seminar was to bring together a
diverse group of scientists with expertise in exascale
computing to discuss novel ways to make applications
resilient against detected and undetected faults. In
particular, participants explored the role that algorithms
and applications play in the holistic approach needed to
tackle this challenge.},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {511 - Computational Science and Mathematical Methods
(POF3-511) / DFG project 450829162 - Raum-Zeit-parallele
Simulation multimodale Energiesystemen (450829162)},
pid = {G:(DE-HGF)POF3-511 / G:(GEPRIS)450829162},
typ = {PUB:(DE-HGF)25},
eprint = {2010.13342},
howpublished = {arXiv:2010.13342},
archivePrefix = {arXiv},
SLACcitation = {$\%\%CITATION$ = $arXiv:2010.13342;\%\%$},
url = {https://juser.fz-juelich.de/record/888522},
}