% 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{Witzler:1033636,
author = {Witzler, Christian and Guimarães, Filipe Souza Mendes and
Mira, Daniel and Anzt, Hartwig and Göbbert, Jens Henrik and
Frings, Wolfgang and Bode, Mathis},
title = {{J}u{M}on{C}: {A} {REST}ful tool for enabling monitoring
and control of simulations at scale},
journal = {Future generation computer systems},
volume = {164},
issn = {0167-739X},
address = {Amsterdam [u.a.]},
publisher = {Elsevier Science},
reportid = {FZJ-2024-06508},
pages = {107541 -},
year = {2025},
abstract = {As systems and simulations grow in size and complexity, it
is challenging to maintain efficient use of resources and
avoid failures. In this scenario, monitoring becomes even
more important and mandatory. This paper describes and
discusses the benefits of the advanced monitoring and
control tool JuMonC, which runs under user control alongside
HPC simulations and provides valuable metrics via REST-API.
In addition, plugin extensibility allows JuMonC to go a step
further and provide computational steering of the simulation
itself. To demonstrate the benefits and usability of JuMonC
for large-scale simulations, two use cases are described
employing nekRS and ICON on JURECA-DC, a supercomputer
located at the Jülich Supercomputing Centre (JSC).
Furthermore, a large-scale use case with nekRS on JSC’s
flagship system JUWELS Booster is described. Finally, the
interplay between JuMonC and LLview (a standard monitoring
tool for HPC systems) is presented using a simple and secure
JuMonC-LLview plugin, which collects performance metrics and
enables their analysis in LLview. Overall, the portability
and usefulness of JuMonC, together with its low performance
impact, make it an important application for both current
and future generations of exascale HPC systems.},
cin = {JSC},
ddc = {004},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
and Research Groups (POF4-511) / CoEC - Center of Excellence
in Combustion (952181) / IO-SEA - IO Software for Exascale
Architecture (955811) / DEEP-SEA - DEEP – SOFTWARE FOR
EXASCALE ARCHITECTURES (955606) / JLESC - Joint Laboratory
for Extreme Scale Computing (JLESC-20150708) / ATMLAO - ATML
Application Optimization and User Service Tools (ATMLAO)},
pid = {G:(DE-HGF)POF4-5112 / G:(EU-Grant)952181 /
G:(EU-Grant)955811 / G:(EU-Grant)955606 /
G:(DE-Juel1)JLESC-20150708 / G:(DE-Juel-1)ATMLAO},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001358353300001},
doi = {10.1016/j.future.2024.107541},
url = {https://juser.fz-juelich.de/record/1033636},
}