% 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:910504,
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 Göddeke,
Dominik and Heisig, Marco and Jézéquel, Fabienne and Kohl,
Nils and Li, Xiaoye Sherry and Lion, Romain and Mehl, Miriam
and Mycek, Paul and Obersteiner, Michael and Quintana-Ortí,
Enrique S and Rizzi, Francesco and Rüde, Ulrich and Schulz,
Martin and Fung, Fred and Speck, Robert and Stals, Linda and
Teranishi, Keita and Thibault, Samuel and Thönnes, Dominik
and Wagner, Andreas and Wohlmuth, Barbara},
title = {{R}esiliency in numerical algorithm design for extreme
scale simulations},
journal = {The international journal of high performance computing
applications},
volume = {36},
number = {2},
issn = {1078-3482},
address = {Thousand Oaks, Calif.},
publisher = {Sage Science Press},
reportid = {FZJ-2022-03887},
pages = {251 - 285},
year = {2022},
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. Advanced supercomputing is
characterized by very high computation speeds at the cost of
involving an enormous amount of resources and costs. A
typical large-scale computation running for 48 h on a system
consuming 20 MW, as predicted for exascale systems, would
consume a million kWh, corresponding to about 100k Euro in
energy cost for executing 1023 floating-point operations. It
is clearly unacceptable to lose the whole computation if any
of the several million parallel processes fails during the
execution. Moreover, if a single operation suffers from a
bit-flip error, should the whole computation be declared
invalid? What about the notion of reproducibility itself:
should this core paradigm of science be revised and refined
for results that are obtained by large-scale simulation?
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? While the analysis of use cases can
help understand the particular reliability requirements, the
construction of remedies is currently wide open. 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. These
ideas constituted an essential topic of the seminar. 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. This article gathers a broad range of
perspectives on the role of algorithms, applications and
systems in achieving resilience for extreme scale
simulations. The ultimate goal is to spark novel ideas and
encourage the development of concrete solutions for
achieving such resilience holistically.},
cin = {JSC},
ddc = {004},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / DFG project
450829162 - Raum-Zeit-parallele Simulation multimodale
Energiesystemen (450829162)},
pid = {G:(DE-HGF)POF4-5111 / G:(GEPRIS)450829162},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000730172300001},
doi = {10.1177/10943420211055188},
url = {https://juser.fz-juelich.de/record/910504},
}