In this work, we combine several previous efforts to simulate a large-scale
soot particle agglomeration with a dynamic, multi-scale turbulent background
flow field. We build upon previous simulations which include 3.2 million
particles and implement load-balancing into the used simulation software as
well as tests of the load-balancing mechanisms on this scenario. We increase
the simulation to 109.85 million particles, superpose a dynamically changing
multi-scale background flow field and use our software enhancements to the
molecular dynamics software ESPResSo to simulate this on a Cray XC40
supercomputer. To verify that our setup reproduces essential physics we scale
the influence of the flow field down to make the scenario mostly homogeneous on
the subdomain scale. Finally, we show that even on the homogeneous version of
this soot particle agglomeration simulation, load-balancing still pays off.
%0 Conference Paper
%1 INPROC-2020-16
%A Hirschmann, Steffen
%A Kronenburg, Andreas
%A Glass, Colin W.
%A Pflüger, Dirk
%B Parallel Computing: Technology Trends
%D 2020
%E Foster, Ian
%E Joubert, Gerhard R.
%E Kucera, Ludek
%E Nagel, Wolfgang E.
%E Peters, Frans
%I IOS Press
%K load-balancing molecular_dynamics soot-particle_aggomeration
%P 147--156
%R 10.3233/APC200035
%T Load-Balancing for Large-Scale Soot Particle Agglomeration Simulations
%U http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2020-16&engl=0
%V 36
%X In this work, we combine several previous efforts to simulate a large-scale
soot particle agglomeration with a dynamic, multi-scale turbulent background
flow field. We build upon previous simulations which include 3.2 million
particles and implement load-balancing into the used simulation software as
well as tests of the load-balancing mechanisms on this scenario. We increase
the simulation to 109.85 million particles, superpose a dynamically changing
multi-scale background flow field and use our software enhancements to the
molecular dynamics software ESPResSo to simulate this on a Cray XC40
supercomputer. To verify that our setup reproduces essential physics we scale
the influence of the flow field down to make the scenario mostly homogeneous on
the subdomain scale. Finally, we show that even on the homogeneous version of
this soot particle agglomeration simulation, load-balancing still pays off.
@inproceedings{INPROC-2020-16,
abstract = {In this work, we combine several previous efforts to simulate a large-scale
soot particle agglomeration with a dynamic, multi-scale turbulent background
flow field. We build upon previous simulations which include 3.2 million
particles and implement load-balancing into the used simulation software as
well as tests of the load-balancing mechanisms on this scenario. We increase
the simulation to 109.85 million particles, superpose a dynamically changing
multi-scale background flow field and use our software enhancements to the
molecular dynamics software ESPResSo to simulate this on a Cray XC40
supercomputer. To verify that our setup reproduces essential physics we scale
the influence of the flow field down to make the scenario mostly homogeneous on
the subdomain scale. Finally, we show that even on the homogeneous version of
this soot particle agglomeration simulation, load-balancing still pays off.},
added-at = {2020-04-28T10:30:30.000+0200},
author = {Hirschmann, Steffen and Kronenburg, Andreas and Glass, Colin W. and Pflüger, Dirk},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2597c594f904098b8fe92ea83723c8210/hirschsn},
booktitle = {Parallel Computing: Technology Trends},
cr-category = {G.0 Mathematics of Computing General},
department = {Universit{\"a}t Stuttgart, Institut f{\"u}r Parallele und Verteilte Systeme, Simulation gro{\ss}er Systeme},
doi = {10.3233/APC200035},
editor = {Foster, Ian and Joubert, Gerhard R. and Kucera, Ludek and Nagel, Wolfgang E. and Peters, Frans},
ee = {ftp://ftp.informatik.uni-stuttgart.de/pub/library/ncstrl.ustuttgart_fi/INPROC-2020-16/INPROC-2020-16.pdf},
institution = {Universit{\"a}t Stuttgart, Fakult{\"a}t Informatik, Elektrotechnik und Informationstechnik, Germany},
interhash = {4e5ac9b1eed1611fcefa9283e441ecc5},
intrahash = {597c594f904098b8fe92ea83723c8210},
keywords = {load-balancing molecular_dynamics soot-particle_aggomeration},
language = {Englisch},
month = {M{\"a}rz},
pages = {147--156},
publisher = {IOS Press},
series = {Advances in Parallel Computing},
timestamp = {2020-04-28T08:48:28.000+0200},
title = {{Load-Balancing for Large-Scale Soot Particle Agglomeration Simulations}},
type = {Konferenz-Beitrag},
url = {http://www2.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2020-16&engl=0},
volume = 36,
year = 2020
}