Session Full Program · Presenters · Organizations · Search ProgramResearch Poster: Research Posters SessionSession ChairsSunita ChandrasekaranAssistant ProfessorUniversity of DelawareRyusuke EgawaAssociate ProfessorTohoku UniversityCyberscience CenterEvent TypeResearch PosterPassesTimeTuesday, June 18th8:30am - 10am CESTLocationSubstanz 1, 2PresentationsIntroduction Research Posters SessionSpeakersSunita ChandrasekaranRyusuke Egawa(RP01) CPU Water Cooling Temperature Effects on the Performance and Energy ConsumptionPoster AuthorsFumiyoshi ShojiJorji NonakaMotohiko MatsudaHiroya MatsubaYasumitsu MaejimaKeiji YamamotoToshiyuki TsukamotoEnergy Consumption(RP02) DEEP: Hybrid Approach for Deep LearningPoster AuthorsAndy S. AlicMarica AntonacciMiguel CaballerIsabel CamposAlessandro CostantiniMario DavidStefan DlugolinskyGiacinto DonvitoCristina DumaJorge GomesMarcus HardtIgnacio HerediaLadislav HluchyKeiichi ItoValentin KozlovLara LloretAlvaro López GarcíaJesus MarcoLudek MatyskaGermán MoltóGiang NguyenPablo OrvizMarcin PlociennikZdeněk ŠustrViet TranPawel WolniewiczWolfgang zu CastellAI/Machine Learning/Deep LearningClouds and Distributed ComputingHeterogeneous SystemsScientific Software Development(RP03) Design of an FPGA-based Matrix Multiplier with Task ParallelismPoster AuthorsYiyu TanToshiyuki ImamuraHPC Accelerators(RP04) Distributed Deep Learning with FPGA Ring AllreducePoster AuthorsKenji TanakaYuki ArikawaKenji KawaiJunichi KatoTsuyoshi ItoHuy Cu NgoKazutaka MoritaFumiaki MiuraTakeshi SakamotoSatoshi ShigematsuAI/Machine Learning/Deep LearningClouds and Distributed ComputingCommunication OptimizationHeterogeneous SystemsNetworks(RP05) ENEA CRESCO HPC Clusters: A Working Example of a Multifabric GPFS Spectrum Scale LayoutPoster AuthorFrancesco IannoneFile SystemsHeterogeneous SystemsStorage Technologies(RP06) Reduction Operations on Modern Supercomputers: Challenges and SolutionsPoster AuthorsMohammadreza BayatpourJahanzeb Maqbool HashmiSourav ChakrabortyHari SubramoniDhabaleswar PandaExascale SystemsMPINetworksParallel Algorithms(RP07) Towards Clean Propulsion with Synthetic Fuels: A Cluster-Modularized Approach Employing Hierarchies of Simulations and Deep LearningPoster AuthorsMathis BodeMarco DavidovicJens H. GöbbertBjörn DickPhilipp OffenhäuserChristian TerbovenMatthias S. MüllerThomas LippertMichael M. ReschHeinz PitschAI/Machine Learning/Deep LearningClouds and Distributed ComputingExtreme-Scale ComputingHPC workflowsParallel Applications(RP08) News from Black Holes in Star Clusters Simulated with Large GPU ClustersPoster AuthorFrancesco Paolo RizzutoComputer ArchitectureMPIParallel AlgorithmsScientific Software Development(RP09) Accelerating Chemical Shift Prediction for Large-scale Biomolecular ModelingPoster AuthorsEric WrightMauricio FerratoAlex BryerRobert SearlesJuan PerillaSunita ChandrasekaranHPC AcceleratorsHeterogeneous SystemsMolecular ResearchParallel ApplicationsProgramming Models & Languages(RP10) High-Performance Computing of Thin QR Decomposition on Parallel SystemsPoster AuthorsTakeshi TeraoKatsuhisa OzakiTakeshi OgitaParallel Algorithms(RP11) HPC Oriented Algorithm for Computation of Recurrence Quantitative AnalysisPoster AuthorsTomáš MartinovičGeorg ZitzlsbergerMPIParallel Algorithms(RP12) A Container-Based Approach to HPC CloudPoster AuthorsGuohua LiJoon WooTaeyoung HongClouds and Distributed ComputingHPC workflowsMPIPerformance Analysis and Optimization(RP13) An Application Parameter Search Method Based on the Binary Search Algorithm for Performance TuningPoster AuthorsTakumi KishitaniKazuhiko KomatsuAkihiro MusaMasayuki SatoHiroaki KobayashiPerformance Analysis and OptimizationPerformance ToolsScientific Software Development(RP14) Automatic Port to OpenACC/OpenMP for Climate & Weather Code Using the CLAW CompilerPoster AuthorsValentin ClementPhilippe MartiXavier LapillonneOliver FuhrerWiliam B. SawyerCompilersHPC AcceleratorsProgramming Models & LanguagesScientific Software Development(RP15) Easy-to-use and Secure Web Command Line Interface for Heterogeneous Resources on Artificial Intelligence PlatformPoster AuthorsRongqiang CaoXiaoguang WangFang LiuJue WangYangang WangXuebin ChiClouds and Distributed ComputingEducation and TrainingSystem Software & Runtime Systems(RP16) Power Prediction with Probabilistic Topic Modeling for HPCPoster AuthorsShigeto SuzukiMichiko HiraokaTakashi ShiraishiHiroyuki FukudaTakuji YamamotoShuji MatsuiAtsuya UnoAI/Machine Learning/Deep LearningBig Data AnalyticsEnergy ConsumptionExascale SystemsScheduling(RP17) Cross-Architecture Affinity of SupercomputersPoster AuthorEdgar A. LeonExascale SystemsHPC AcceleratorsHeterogeneous SystemsMPISystem Software & Runtime Systems(RP18) Real-Time Fire Detection Using CUDAPoster AuthorsWissam AntounManal JalloulParallel AlgorithmsParallel ApplicationsPerformance Analysis and Optimization(RP19) Scalable Network PDE-Based Multiphysics Simulation Using the PETSc LibraryPoster AuthorHong ZhangExtreme-Scale ComputingNetworksParallel AlgorithmsParallel ApplicationsScientific Software Development(RP20) Development of Training Environment for Deep Learning With Medical Images on Supercomputer System Based on Asynchronous Parallel Bayesian OptimizationPoster AuthorsYukihiro NomuraToshihiro HanawaIssei SatoShouhei HanaokaTakahiro NakaoMasaki MurataTomomi TakenagaTetsuya HoshinoYuji SekiyaNaoto HayashiOsamu AbeAI/Machine Learning/Deep LearningBig Data AnalyticsParallel Applications(RP21) Optimizing Deep Learning LSTM Topologies on Intel Xeon ArchitecturePoster AuthorsKunal BanerjeeEvangelos GeorganasDhiraj KalamkarAlexander HeineckeAI/Machine Learning/Deep LearningParallel AlgorithmsPerformance Analysis and Optimization(RP22) Supercomputer-Scale Training of Large AI Radiology ModelsPoster AuthorsValeriu CodreanuDamian PodareanuLucas WilsonSrinivas VaradharajanVikram SaletoreAI/Machine Learning/Deep LearningHPC workflowsParallel Algorithms(RP23) A Skewed Multi-Bank Cache for Vector ProcessorsPoster AuthorsHikaru TakayashikiMasayuki SatoKazuhiko KomatsuHiroaki KobayashiComputer Architecture(RP25) Development of Performance Assessment Method Based on Aspen DSL and Micro-Kernels BenchmarkingPoster AuthorsEkaterina TyutlyaevaAlexander MoskovskyIgor OdintsovSergey KonyukhovHPC workflowsPerformance Analysis and Optimization(RP27) Memory First : A Performance Tuning Strategy Focusing on Memory Access PatternsPoster AuthorsNaoki EbataRyusuke EgawaYoko IsobeRyoji TakakiHiroyuki TakizawaComputer ArchitecturePerformance Analysis and OptimizationScientific Software Development(RP28) Performance Tuning of Deep Learning Framework Chainer on the K Computer.Poster AuthorsAkiyoshi KurodaKiyoshi KumahataSyuichi ChibaKatsutoshi TakashinaKazuo MinamiAI/Machine Learning/Deep LearningPerformance Analysis and OptimizationClosing & Transition to the Poster ReceptionSpeakersSunita ChandrasekaranRyusuke Egawa