000283461 001__ 283461 000283461 005__ 20250317091729.0 000283461 0247_ $$2Handle$$a2128/9990 000283461 037__ $$aFZJ-2016-01816 000283461 041__ $$aEnglish 000283461 0881_ $$aFZJ-JSC-IB-2016-01 000283461 088__ $$2JUEL$$aFZJ-JSC-IB-2016-01 000283461 1001_ $$0P:(DE-Juel1)143606$$aBrömmel, Dirk$$b0$$ufzj 000283461 245__ $$aJUQUEEN Extreme Scaling Workshop 2016 000283461 260__ $$c2016 000283461 300__ $$a67 p. 000283461 3367_ $$0PUB:(DE-HGF)3$$2PUB:(DE-HGF)$$aBook$$mbook 000283461 3367_ $$0PUB:(DE-HGF)15$$2PUB:(DE-HGF)$$aInternal Report$$bintrep$$mintrep$$s1458138444_32438 000283461 3367_ $$2DataCite$$aOutput Types/Report 000283461 3367_ $$2BibTeX$$aTECHREPORT 000283461 3367_ $$2ORCID$$aREPORT 000283461 3367_ $$010$$2EndNote$$aReport 000283461 3367_ $$2DRIVER$$areport 000283461 4900_ $$aJSC Internal Report 000283461 520__ $$aFeedback from last year's very successful workshop motivated the organisation of a three-day workshop 1-3 February 2016, during which the entire 28-rack JUQUEEN BlueGene/Q system with 458,752 cores was reserved for over 50 hours. Eight code teams were selected to use this opportunity to investigate and improve their application scalability, assisted by staff from JSC Simulation Laboratories and Cross-sectional Teams. Code_Saturne from Daresbury Lab and Seven-League Hydro from HITS (Heidelberg) were both able to display good strong scalability and thereby become candidates for High-Q Club membership. Both used 4 OpenMP threads per MPI process, over 1.8 million threads in total. Existing members, CIAO from RWTH-ITV and iFETI from University of Cologne and TU Freiberg, were able to show that they had additional solvers which also scaled acceptably. In-situ interactive visualisation was demonstrated with a CIAO simulation using 458,752 MPI processes running on 28 racks coupled via JUSITU to VisIt. Two adaptive mesh refinement libraries, p4est from University of Bonn and IciMesh from Ecole Central de Nantes, showed that they could respectively scale to run with 917,504 and 458,752 MPI ranks, but both encountered problems loading large meshes. Parallel file I/O limitations also prevented large-scale executions of the FZJ IEK-6/Amphos21 PFLOTRAN subsurface flow and reactive transport code, however, a NEST-import HDF5 module developed by the EPFL Blue Brain Project could be optimised to use collective MPI file reading calls to load and connect 1.9TB of neuron and synapse data and enable large-scale data-driven neuronal network simulations with 458,752 threads. Detailed reports are provided by each code-team, and additional comparative analysis to the 25 High-Q Club member codes. Despite more mixed results than the previous workshop, we learnt more about application file I/O limitations and inefficiencies which continue to be the primary inhibitor to large-scale simulations, and all of the participants found the workshop to have been very valuable. 000283461 536__ $$0G:(DE-HGF)POF3-511$$a511 - Computational Science and Mathematical Methods (POF3-511)$$cPOF3-511$$fPOF III$$x0 000283461 536__ $$0G:(DE-HGF)POF3-513$$a513 - Supercomputer Facility (POF3-513)$$cPOF3-513$$fPOF III$$x1 000283461 536__ $$0G:(DE-Juel-1)ATMLPP$$aATMLPP - ATML Parallel Performance (ATMLPP)$$cATMLPP$$x2 000283461 536__ $$0G:(DE-Juel-1)ATMLAO$$aATMLAO - ATML Application Optimization and User Service Tools (ATMLAO)$$cATMLAO$$x3 000283461 7001_ $$0P:(DE-Juel1)132108$$aFrings, Wolfgang$$b1$$ufzj 000283461 7001_ $$0P:(DE-Juel1)132302$$aWylie, Brian J. N.$$b2$$eCorresponding author$$ufzj 000283461 8564_ $$uhttps://juser.fz-juelich.de/record/283461/files/fzj-jsc-ib-2016-01.pdf$$yOpenAccess 000283461 8564_ $$uhttps://juser.fz-juelich.de/record/283461/files/fzj-jsc-ib-2016-01.gif?subformat=icon$$xicon$$yOpenAccess 000283461 8564_ $$uhttps://juser.fz-juelich.de/record/283461/files/fzj-jsc-ib-2016-01.jpg?subformat=icon-180$$xicon-180$$yOpenAccess 000283461 8564_ $$uhttps://juser.fz-juelich.de/record/283461/files/fzj-jsc-ib-2016-01.jpg?subformat=icon-700$$xicon-700$$yOpenAccess 000283461 909CO $$ooai:juser.fz-juelich.de:283461$$pdnbdelivery$$pVDB$$pdriver$$popen_access$$popenaire 000283461 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)143606$$aForschungszentrum Jülich GmbH$$b0$$kFZJ 000283461 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132108$$aForschungszentrum Jülich GmbH$$b1$$kFZJ 000283461 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132302$$aForschungszentrum Jülich GmbH$$b2$$kFZJ 000283461 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$$vComputational Science and Mathematical Methods$$x0 000283461 9131_ $$0G:(DE-HGF)POF3-513$$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$$vSupercomputer Facility$$x1 000283461 9141_ $$y2016 000283461 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess 000283461 920__ $$lyes 000283461 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0 000283461 980__ $$aintrep 000283461 980__ $$aVDB 000283461 980__ $$abook 000283461 980__ $$aI:(DE-Juel1)JSC-20090406 000283461 980__ $$aUNRESTRICTED 000283461 9801_ $$aUNRESTRICTED 000283461 9801_ $$aFullTexts