High-Performance Computing

I ISHPC-VI Award PapersMulTIple Stream PredicTIon . . . 1Oliverio J. Santana, Alex Ramirez, and Mateo ValeroEnhanced Loop Coalescing: A Compiler Technique for TransformingNon-uniform IteraTIon Spaces  17Arun Kejariwal, Alexandru Nicolau, andConstanTIne D. PolychronopoulosII ISHPC-VI Regular PapersFolding Active List for High Performance and Low Power 33Yuichiro Imaizumi and Toshinori SatoReducing Misspeculation Penalty in Trace-Level SpeculativeMultithreaded Architectures  . . 43Carlos Molina, Jordi Tubella, and Antonio Gonz´alezExploiting Execution Locality with a Decoupled Kilo-InstructionProcessor  . . . . . 56Miquel Peric`as, Adrian Cristal, Ruben Gonz´alez,Daniel A. Jim´enez, and Mateo ValeroDecoupled State-Execute Architecture . . . . 68Miquel Peric`as, Adrian Cristal, Ruben Gonz´alez,Alex Veidenbaum, and Mateo ValeroA Scalable Methodology for Computing Fault-Free Paths in InfiniBandTorus Networks  79Jos´e M. Monta˜nana, Jos´e Flich, Antonio Robles, and Jos´e DuatoUsing a Way Cache to Improve Performance of Set-AssociativeCaches   93Dan Nicolaescu, Alexander Veidenbaum, and Alexandru NicolauDesign of Fast Collective Communication Functions on ClusteredWorkstations with Ethernet and Myrinet . 105Dongyoung Kim and Dongseung KimXII Table of ContentsDynamic Load Balancing in MPI Jobs . . . . 117Gladys Utrera, Julita Corbal´an, and Jes´us LabartaWorkload Characterization of Stateful Networking Applications  . 130Javier Verd´u, Mario Nemirovsky, Jorge Garc´ıa, and Mateo ValeroUsing Recursion to Boost ATLAS’s Performance  . 142Paolo D’Alberto and Alexandru NicolauTowards Generic Solver of Combinatorial Optimization Problems withAutonomous Agents in P2P Networks . . . . 152Shigeaki Tagashira, Masaya Mito, and Satoshi FujitaNew Evaluation Index of Incomplete Cholesky Preconditioning Effect . . . 164Takeshi Iwashita and Masaaki ShimasakiT-Map: A Topological Approach to Visual Exploration of Time-VaryingVolume Data  . . 176Issei Fujishiro, Rieko Otsuka, Shigeo Takahashi, andYuriko TakeshimaIII ISHPC-VI Short PapersCross-Line—A Globally Adaptive Control Method of InterconnectionNetwork  . . . . . . 191Takashi Yokota, Masashi Nishitani, Kanemitsu Ootsu,Fumihito Furukawa, and Takanobu BabaThe Bandwidth Expansion Effectiveness of Cache Levels BlockPrefetch  . . . . . . 199Youngkwan Ju, Bongyong Uh, and Sukil KimImplementation and Evaluation of the Mechanisms for Low LatencyCommunication on DIMMnet-2  . . . 211Yasuo Miyabe, Akira Kitamura, Yoshihiro Hamada,Tomotaka Miyasiro, Tetsu Izawa, Noboru Tanabe,Hironori Nakajo, and Hideharu AmanoComputationally Efficient Parallel Matrix-Matrix Multiplication on theTorus   . . 219Ahmed S. Zekri and Stanislav G. SedukhinA New Dynamic Load Balancing Technique for Parallel ModifiedPrefixSpan with Distributed Worker Paradigm and Its PerformanceEvaluation  . . . . 227Makoto Takaki, Keiichi Tamura, Toshihide Sutou, andHajime KitakamiTable of Contents XIIIPerformance-Based Loop Scheduling on Grid Environments  . . . . 238Wen-Chung Shih, Chao-Tung Yang, and Shian-Shyong TsengReconfigurable Middleware for Grid Environment  246Sungju Kwon, Jaeyoung Choi, and Jysoo LeeNetfiles: An Enhanced Stream-Based Communication Mechanism . . . . . . 254Philip Chan and David AbramsonPerformance of Coupled Parallel Finite Element Analysis in GridComputing Environment  . . . . . 262Tomoya Niho and Tomoyoshi HoriePhoto-Realistic Visualization for the Blast Wave of TNT Explosion byGrid-Based Rendering   271Kaori Kato, Takayuki Aoki, Tei Saburi, and Masatake YoshidaDevelopment of an Interactive Visual Data Mining System forAtmospheric Science   . 279Chiemi Watanabe, Eriko Touma, Kazuko Yamauchi,Katsuyuki Noguchi, Sachiko Hayashida, and Kazuki JoeA Calculus Effectively Performing Event Formation withVisualization  . . 287Susumu Yamasaki and Mariko SasakuraA Similarity Evaluation Method for Volume Data Sets by Using CriticalPoint Graph  . . . 295Tomoki Minami, Koji Sakai, and Koji KoyamadaIV HiWEP2005Hybrid Parallelization and Flat Parallelization in HPF (HighPerformance Fortran)  . 305Yasuharu Hayashi and Kenji SuehiroMapping Normalization Technique on the HPF Compiler fhpf . . . 315Hidetoshi Iwashita and Masaki AokiDevelopment of Electromagnetic Particle Simulation Code in an OpenSystem   329Hiroaki Ohtani, Seiji Ishiguro, Ritoku Horiuchi,Yasuharu Hayashi, and Nobutoshi HoriuchiDevelopment of Three-Dimensional Neoclassical Transport SimulationCode with High Performance Fortran on a Vector-Parallel Computer . . . 344Shinsuke Satake, Masao Okamoto, Noriyoshi Nakajima, andHisanori TakamaruXIV Table of ContentsDistributed Parallelization of Exact Charge Conservative ParticleSimulation Code by High Performance Fortran  . . 358Hiroki Hasegawa, Seiji Ishiguro, and Masao OkamotoPipelined Parallelization in HPF Programs on the Earth Simulator . . . . . 365Hitoshi Murai and Yasuo OkabeV APC2005Sampling of Protein Conformations with Computers to Predict theNative Structure   . . . . . 374Junichi HigoSpacecraft Plasma Environment Analysis Via Large Scale 3D PlasmaParticle Simulation   . . . 383Masaki Okada, Hideyuki Usui, Yoshiharu Omura, Hiroko O. Ueda,Takeshi Murata, and Tooru SugiyamaPetaFLOPS Computing and Computational Nanotechnology onIndustrial Issues   . . . . . 393Shuhei Ohnishi and Satoshi Itoh16.14 TFLOPS Eigenvalue Solver on the Earth Simulator: ExactDiagonalization for Ultra Largescale Hamiltonian Matrix . 402Susumu Yamada, Toshiyuki Imamura, and Masahiko MachidaNumerical Simulation of Combustion Dynamics at ISTA/JAXA . 414Junji Shinjo, Shingo Matsuyama, Yasuhiro Mizobuchi, andSatoru OgawaRealization of a Computer Simulation Environment Based on ITBLand a Large Scale GW Calculation Performed on This Platform  427Yoshiyuki Kawazoe, Marcel Sluiter, Hiroshi Mizuseki,Kyoko Ichinoseki, Amit Jain, Kaoru Ohno, Soh Ishii,Hitoshi Adachi, and Hiroshi YamaguchiComputations of Global Seismic Wave Propagation in ThreeDimensional Earth Model  . . . . 434Seiji Tsuboi, Dimitri Komatitsch, Chen Ji, and Jeroen TrompLattice QCD Simulations as an HPC Challenge  . . 444Atsushi NakamuraVI ALPS2006Energy-Efficient Embedded System Design at 90nm and Below – ASystem-Level Perspective –  . . . 452Tohru IshiharaTable of Contents XVEmpirical Study for Optimization of Power-Performance with On-ChipMemory  . . . . . . 466Chikafumi Takahashi, Mitsuhisa Sato, Daisuke Takahashi,Taisuke Boku, Hiroshi Nakamura, Masaaki Kondo, andMotonobu FujitaPerformance Evaluation of Compiler Controlled Power SavingScheme   480Jun Shirako, Munehiro Yoshida, Naoto Oshiyama, Yasutaka Wada,Hirofumi Nakano, Hiroaki Shikano, Keiji Kimura, andHironori KasaharaProgram Phase Detection Based Dynamic Control Mechanisms forPipeline Stage Unification Adoption . . . . . . 494Jun Yao, Hajime Shimada, Yasuhiko Nakashima,Shin-ichiro Mori, and Shinji TomitaReducing Energy in Instruction Caches by Using Multiple Line Bufferswith Prediction  508Kashif Ali, Mokhtar Aboelaze, and Suprakash DattaAuthor Index  523