000830181 001__ 830181
000830181 005__ 20240313103119.0
000830181 0247_ $$2doi$$a10.3389/fninf.2017.00030
000830181 0247_ $$2Handle$$a2128/14537
000830181 0247_ $$2WOS$$aWOS:000401368100001
000830181 0247_ $$2altmetric$$aaltmetric:20207627
000830181 0247_ $$2pmid$$apmid:28559808
000830181 037__ $$aFZJ-2017-03757
000830181 082__ $$a610
000830181 1001_ $$0P:(DE-Juel1)161558$$aIppen, Tammo$$b0
000830181 245__ $$aConstructing Neuronal Network Models in Massively Parallel Environments
000830181 260__ $$aLausanne$$bFrontiers Research Foundation$$c2017
000830181 3367_ $$2DRIVER$$aarticle
000830181 3367_ $$2DataCite$$aOutput Types/Journal article
000830181 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1563262359_1217
000830181 3367_ $$2BibTeX$$aARTICLE
000830181 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000830181 3367_ $$00$$2EndNote$$aJournal Article
000830181 520__ $$aRecent advances in the development of data structures to represent spiking neuron network models enable us to exploit the complete memory of petascale computers for a single brain-scale network simulation. In this work, we investigate how well we can exploit the computing power of such supercomputers for the creation of neuronal networks. Using an established benchmark, we divide the runtime of simulation code into the phase of network construction and the phase during which the dynamical state is advanced in time. We find that on multi-core compute nodes network creation scales well with process-parallel code but exhibits a prohibitively large memory consumption. Thread-parallel network creation, in contrast, exhibits speedup only up to a small number of threads but has little overhead in terms of memory. We further observe that the algorithms creating instances of model neurons and their connections scale well for networks of ten thousand neurons, but do not show the same speedup for networks of millions of neurons. Our work uncovers that the lack of scaling of thread-parallel network creation is due to inadequate memory allocation strategies and demonstrates that thread-optimized memory allocators recover excellent scaling. An analysis of the loop order used for network construction reveals that more complex tests on the locality of operations significantly improve scaling and reduce runtime by allowing construction algorithms to step through large networks more efficiently than in existing code. The combination of these techniques increases performance by an order of magnitude and harnesses the increasingly parallel compute power of the compute nodes in high-performance clusters and supercomputers.
000830181 536__ $$0G:(DE-HGF)POF3-574$$a574 - Theory, modelling and simulation (POF3-574)$$cPOF3-574$$fPOF III$$x0
000830181 536__ $$0G:(DE-HGF)POF3-511$$a511 - Computational Science and Mathematical Methods (POF3-511)$$cPOF3-511$$fPOF III$$x1
000830181 536__ $$0G:(DE-Juel1)jinb33_20121101$$aBrain-Scale Simulations (jinb33_20121101)$$cjinb33_20121101$$fBrain-Scale Simulations$$x2
000830181 536__ $$0G:(DE-Juel1)HGF-SMHB-2013-2017$$aSMHB - Supercomputing and Modelling for the Human Brain (HGF-SMHB-2013-2017)$$cHGF-SMHB-2013-2017$$fSMHB$$x3
000830181 536__ $$0G:(EU-Grant)604102$$aHBP - The Human Brain Project (604102)$$c604102$$fFP7-ICT-2013-FET-F$$x4
000830181 536__ $$0G:(EU-Grant)720270$$aHBP SGA1 - Human Brain Project Specific Grant Agreement 1 (720270)$$c720270$$fH2020-Adhoc-2014-20$$x5
000830181 536__ $$0G:(DE-Juel1)Helmholtz-SLNS$$aSLNS - SimLab Neuroscience (Helmholtz-SLNS)$$cHelmholtz-SLNS$$x6
000830181 588__ $$aDataset connected to CrossRef
000830181 7001_ $$0P:(DE-Juel1)142538$$aEppler, Jochen M.$$b1
000830181 7001_ $$0P:(DE-Juel1)169781$$aPlesser, Hans E.$$b2
000830181 7001_ $$0P:(DE-Juel1)144174$$aDiesmann, Markus$$b3$$eCorresponding author
000830181 773__ $$0PERI:(DE-600)2452979-5$$a10.3389/fninf.2017.00030$$gVol. 11, p. 30$$p30$$tFrontiers in neuroinformatics$$v11$$x1662-5196$$y2017
000830181 8564_ $$uhttps://juser.fz-juelich.de/record/830181/files/fninf-11-00030.pdf$$yOpenAccess
000830181 8564_ $$uhttps://juser.fz-juelich.de/record/830181/files/fninf-11-00030.gif?subformat=icon$$xicon$$yOpenAccess
000830181 8564_ $$uhttps://juser.fz-juelich.de/record/830181/files/fninf-11-00030.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
000830181 8564_ $$uhttps://juser.fz-juelich.de/record/830181/files/fninf-11-00030.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
000830181 8564_ $$uhttps://juser.fz-juelich.de/record/830181/files/fninf-11-00030.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
000830181 8564_ $$uhttps://juser.fz-juelich.de/record/830181/files/fninf-11-00030.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000830181 8767_ $$92017-04-05$$d2017-04-05$$eAPC$$jDeposit$$lDeposit: Frontiers$$zUSD 1904,85
000830181 909CO $$ooai:juser.fz-juelich.de:830181$$pdnbdelivery$$popenCost$$pec_fundedresources$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000830181 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)161558$$aForschungszentrum Jülich$$b0$$kFZJ
000830181 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)142538$$aForschungszentrum Jülich$$b1$$kFZJ
000830181 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)169781$$aForschungszentrum Jülich$$b2$$kFZJ
000830181 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)144174$$aForschungszentrum Jülich$$b3$$kFZJ
000830181 9131_ $$0G:(DE-HGF)POF3-574$$1G:(DE-HGF)POF3-570$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lDecoding the Human Brain$$vTheory, modelling and simulation$$x0
000830181 9131_ $$0G:(DE-HGF)POF3-511$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vComputational Science and Mathematical Methods$$x1
000830181 9141_ $$y2017
000830181 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000830181 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews
000830181 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000830181 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bFRONT NEUROINFORM : 2015
000830181 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal
000830181 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ
000830181 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000830181 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000830181 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000830181 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000830181 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000830181 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bThomson Reuters Master Journal List
000830181 9201_ $$0I:(DE-Juel1)INM-6-20090406$$kINM-6$$lComputational and Systems Neuroscience$$x0
000830181 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lTheoretical Neuroscience$$x1
000830181 9201_ $$0I:(DE-Juel1)INM-10-20170113$$kINM-10$$lJara-Institut Brain structure-function relationships$$x2
000830181 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x3
000830181 9801_ $$aAPC
000830181 9801_ $$aFullTexts
000830181 980__ $$ajournal
000830181 980__ $$aVDB
000830181 980__ $$aI:(DE-Juel1)INM-6-20090406
000830181 980__ $$aI:(DE-Juel1)IAS-6-20130828
000830181 980__ $$aI:(DE-Juel1)INM-10-20170113
000830181 980__ $$aI:(DE-Juel1)JSC-20090406
000830181 980__ $$aAPC
000830181 980__ $$aUNRESTRICTED
000830181 981__ $$aI:(DE-Juel1)IAS-6-20130828