% 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{Nikitenko:894423,
author = {Nikitenko, D. A. and Wolf, F. and Mohr, B. and Hoefler, T.
and Stefanov, K. S. and Voevodin, Vad. V. and Antonov, A. S.
and Calotoiu, A.},
title = {{I}nfluence of {N}oisy {E}nvironments on {B}ehavior of
{HPC} {A}pplications},
journal = {Lobachevskii journal of mathematics},
volume = {42},
number = {7},
issn = {1818-9962},
address = {Heidelberg},
publisher = {Springer},
reportid = {FZJ-2021-03216},
pages = {1560 - 1570},
year = {2021},
abstract = {Many contemporary HPC systems expose their jobs to
substantial amounts of interference, leading to significant
run-to-run variation. For example, application runtimes on
Theta, a Cray XC40 system at Argonne National Laboratory,
vary by up to $70\%,$ caused by a mix of node-level and
system-level effects, including network and file-system
congestion in the presence of concurrently running jobs.
This makes performance measurements generally
irreproducible, heavily complicating performance analysis
and modeling. On noisy systems, performance analysts usually
have to repeat performance measurements several times and
then apply statistics to capture trends. First, this is
expensive and, second, extracting trends from a limited
series of experiments is far from trivial, as the noise can
follow quite irregular patterns. Attempts to learn from
performance data how a program would perform under different
execution configurations experience serious perturbation,
resulting in models that reflect noise rather than intrinsic
application behavior. On the other hand, although noise
heavily influences execution time and energy consumption, it
does not change the computational effort a program performs.
Effort metrics that count how many operations a machine
executes on behalf of a program, such as floating-point
operations, the exchange of MPI messages, or file reads and
writes, remain largely unaffected and—rare non-determinism
set aside—reproducible. This paper addresses initial stage
of an ExtraNoise project, which is aimed at revealing and
tackling key questions of system noise influence on HPC
applications.},
cin = {JSC},
ddc = {510},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
and Research Groups (POF4-511) / ExtraNoise –
Leistungsanalyse von HPC-Anwendungen in verrauschten
Umgebungen (449683531) / ATMLPP - ATML Parallel Performance
(ATMLPP)},
pid = {G:(DE-HGF)POF4-5112 / G:(GEPRIS)449683531 /
G:(DE-Juel-1)ATMLPP},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000683368000009},
doi = {10.1134/S1995080221070192},
url = {https://juser.fz-juelich.de/record/894423},
}