Resch / Wang / Focht High Performance Computing on Vector Systems 2011

1. Auflage 2011
ISBN: 978-3-642-22244-3
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 184 Seiten, eBook

The book presents the state of the art in high performance computing and simulation on modern supercomputer architectures. It covers trends in hardware and software development in general and specifically the future of vector-based systems and heterogeneous architectures. The application contributions cover computational fluid dynamics, material science, medical applications and climate research. Innovative fields like coupled multi-physics or multi-scale simulations are presented. All papers were chosen from presentations given at the 13th Teraflop Workshop held in October 2010 at Tohoku University, Japan.

Zielgruppe

Research

Autoren/Hrsg.

Resch, Michael

Wang, Xin

Bez, Wolfgang

Focht, Erich

Kobayashi, Hiroaki

Roller, Sabine

Resch, Michael M.

Inhaltsverzeichnis

1;High Performance Computing on Vector Systems 2011
;3
1.1;Preface;5
1.2;Contents;7
1.3;Part I: Techniques and Tools for High Performance Systems;9
1.3.1;Performance and Scalability Analysisof a Chip Multi Vector Processor;10
1.3.1.1;1 Introduction;11
1.3.1.2;2 Chip Multi Vector Processor;12
1.3.1.2.1;2.1 Structure of a Chip Multi Vector Processor;12
1.3.1.2.2;2.2 Performance Model of a Chip Multi Vector Processor;13
1.3.1.3;3 Performance Tuning for a Chip Multi Vector Processor;15
1.3.1.3.1;3.1 Performance Analysis Using the Roofline Model;15
1.3.1.3.2;3.2 Program Optimization;16
1.3.1.3.2.1;3.2.1 Loop Unrolling;16
1.3.1.3.2.2;3.2.2 Cache Blocking;17
1.3.1.3.2.3;3.2.3 Performance Tuning Strategy Based on the Roofline Model;17
1.3.1.4;4 Performance and Scalability Analysis;18
1.3.1.4.1;4.1 Methodology;18
1.3.1.4.2;4.2 Benchmarks;19
1.3.1.4.3;4.3 Performance Evaluation of CMVP;20
1.3.1.4.4;4.4 Performance Evaluation of CMVP with Performance Tuning;22
1.3.1.5;5 Conclusions;25
1.3.1.6;References;26
1.3.2;I/O Forwarding for Quiet Clusters;28
1.3.2.1;1 Introduction;29
1.3.2.2;2 Operating System Noise;30
1.3.2.2.1;2.1 So …Who's the Noisy Neighbour?;31
1.3.2.2.2;2.2 Impact on Applications;31
1.3.2.2.3;2.3 Mitigation;32
1.3.2.2.3.1;2.3.1 Silence Your System;32
1.3.2.2.3.2;2.3.2 Embrace Noise;33
1.3.2.2.3.3;2.3.3 Synchronize Noise;33
1.3.2.2.3.4;2.3.4 Prioritize;33
1.3.2.2.3.5;2.3.5 Travel Light;33
1.3.2.3;3 Measuring Noise;34
1.3.2.3.1;3.1 Test System;34
1.3.2.3.2;3.2 Fixed Work Quanta Benchmark;35
1.3.2.3.3;3.3 Fixed Time Quanta Benchmark;36
1.3.2.4;4 I/O Induced Noise;36
1.3.2.5;5 I/O Forwarding;38
1.3.2.5.1;5.1 I/O Forwarding Architecture;39
1.3.2.5.2;5.2 System I/O Interceptors: Libsysio;40
1.3.2.5.3;5.3 I/O Forwarding Protocol: IOD Driver and Server;41
1.3.2.5.4;5.4 Communication Framework: Portals;41
1.3.2.5.5;5.5 Using the I/O Forwarding Framework;42
1.3.2.5.6;5.6 Noise;42
1.3.2.5.7;5.7 FUSE Driver;44
1.3.2.6;6 Conclusion;44
1.3.2.7;References;45
1.3.3;A Prototype Implementation of OpenCL for SX Vector Systems;47
1.3.3.1;1 Introduction;48
1.3.3.2;2 OpenCL;48
1.3.3.3;3 OpenCL for SX;49
1.3.3.4;4 Early Evaluation and Discussions;51
1.3.3.5;5 Conclusions;53
1.3.3.6;References;55
1.3.4;Distributed Parallelization of Semantic Web Java Applications by Means of the Message-Passing Interface;57
1.3.4.1;1 Introduction;57
1.3.4.2;2 Use Case Description: Random Indexing;59
1.3.4.3;3 Parallelization Strategy;60
1.3.4.4;4 Realization by Means of MPI;61
1.3.4.5;5 Implementation;63
1.3.4.6;6 Application Performance Evaluation;64
1.3.4.7;7 Performance Tailoring: Hybrid MPI-Java Threads Communication Pattern;66
1.3.4.8;8 Final Discussion and Conclusion;68
1.3.4.9;References;69
1.3.5;HPC Systems at JAIST and Development of Dynamic Loop Monitoring Tools Toward Runtime Parallelization;71
1.3.5.1;1 Introduction;71
1.3.5.2;2 Information Environment and HPC Systems at JAIST;72
1.3.5.3;3 Development of Dynamic Loop Monitoring Tools Toward Runtime Parallelization;74
1.3.5.3.1;3.1 Background and Objectives of Dynamic Loop Monitoring Tools;75
1.3.5.3.2;3.2 Parallelism and Loop Nest Structures;75
1.3.5.3.3;3.3 Loop Nest Detection and Loop-Call Context Tree Generation;76
1.3.5.3.4;3.4 Evaluation of Our L-CCT Generation;78
1.3.5.3.4.1;3.4.1 Experiment;78
1.3.5.3.4.2;3.4.2 Results;78
1.3.5.3.5;3.5 Run-Time Data Dependence Analysis;80
1.3.5.3.5.1;3.5.1 Motivations and Strategies;81
1.3.5.3.5.2;3.5.2 Details of Our Runtime Data Dependence Analysis;81
1.3.5.3.5.3;3.5.3 Preliminary Evaluation of Runtime Data Dependence Analysis;82
1.3.5.4;4 Conclusions;83
1.3.5.5;References;83
1.4;Part II: Methods and Technologies for Large-Scale Systems;85
1.4.1;Tree Based Voxelization of STL Data;86
1.4.1.1;1 Introduction;86
1.4.1.2;2 Octree Overview;88
1.4.1.3;3 Mesh Generation;89
1.4.1.3.1;3.1 Intersection Algorithm and Tree Generation;90
1.4.1.3.2;3.2 Flooding;92
1.4.1.3.3;3.3 Boundary Conditions;92
1.4.1.3.4;3.4 The File Format;94
1.4.1.4;4 Sample Mesh;95
1.4.1.5;5 Outlook;96
1.4.1.6;References;96
1.4.2;An Adaptable Simulation Framework Based on a Linearized Octree;98
1.4.2.1;1 Introduction and Overall Layout of the Apes Framework;98
1.4.2.1.1;1.1 Used Technologies;99
1.4.2.1.2;1.2 Components of the Apes Suite;99
1.4.2.1.3;1.3 Distributed Computing;101
1.4.2.2;2 Related Work;101
1.4.2.3;3 The Distributed Linearized Octree;102
1.4.2.3.1;3.1 Implementation of the Element Description;102
1.4.2.3.2;3.2 Element Properties;104
1.4.2.3.3;3.3 Acting on the Tree;106
1.4.2.4;4 Configuration of Simulation Runs;107
1.4.2.5;5 Usage in Solvers;107
1.4.2.5.1;5.1 Ateles;108
1.4.2.5.2;5.2 Musubi;109
1.4.2.6;6 Outlook;110
1.4.2.7;References;110
1.4.3;High Performance Computing for Analyzing PB-Scale Data in Nuclear Experiments and Simulations;111
1.4.3.1;1 Introduction;111
1.4.3.2;2 Large-Scale Data Integrated Analysis System;112
1.4.3.3;3 Heterogeneous Processors for Acceleration Large-Data Analyses;113
1.4.3.4;4 Distributed Parallel Computing Framework with Fault-Tolerance;116
1.4.3.5;5 Summary;120
1.4.3.6;References;121
1.5;Part III: Computational Fluid Dynamics, Physical Simulation and Engineering Application;122
1.5.1;TASCOM3D: A Scientific Code for Compressible Reactive Flows;123
1.5.1.1;1 Introduction;123
1.5.1.2;2 Governing Equations and Numerical Schemes;124
1.5.1.3;3 Numerical Investigations of NOx-Formation in Scramjet Combustors Using Wall and Strut Injectors;125
1.5.1.3.1;3.1 Configuration and Numerical Setup;126
1.5.1.3.2;3.2 Results;128
1.5.1.3.3;3.3 Conclusion and Further Reading;131
1.5.1.4;4 Steady and Unsteady RANS Simulations of a Cryogenic Rocket Combustor;131
1.5.1.4.1;4.1 Configuration and Numerical Setup;131
1.5.1.4.2;4.2 Results;133
1.5.1.4.3;4.3 Conclusion and Further Reading;136
1.5.1.5;5 Performance Analysis;136
1.5.1.5.1;5.1 Single CPU Performance;137
1.5.1.5.2;5.2 Scaling Performance;138
1.5.1.5.3;5.3 Conclusion and Further Reading;139
1.5.1.6;6 Conclusion;140
1.5.1.7;References;141
1.5.2;Investigations of Human Nasal Cavity Flows Based on a Lattice-Boltzmann Method;144
1.5.2.1;1 Introduction;144
1.5.2.2;2 Numerical Methods;146
1.5.2.2.1;2.1 The Lattice-Boltzmann Method with Local Grid Refinement;146
1.5.2.2.2;2.2 Computational Grid;149
1.5.2.3;3 Scalability and Performance Analysis;150
1.5.2.4;4 Nasal Cavity Flows;152
1.5.2.5;5 Discussion;156
1.5.2.6;6 Conflict of Interest;157
1.5.2.7;References;158
1.5.3;Influence of Adatoms on the Quantum Conductance and Metal-Insulator Transition of Atomic-Scale Nanowires;160
1.5.3.1;1 Introduction;160
1.5.3.2;2 Computational Method;161
1.5.3.3;3 Results;162
1.5.3.4;References;170
1.5.4;Current Status and Future Direction of Full-Scale Vibration Simulator for Entire Nuclear Power Plants;172
1.5.4.1;1 Introduction;172
1.5.4.2;2 Three-Dimensional Vibration Simulator for an Entire Nuclear Power Plant;174
1.5.4.2.1;2.1 Methodology of Assembled-Structure Analysis;174
1.5.4.2.2;2.2 Computation Platform for Large-Scale Simulation of an Entire Nuclear Plant;175
1.5.4.3;3 Current Status of Vibration Simulator;175
1.5.4.3.1;3.1 Development of Elastic Analysis of High Temperature Engineering Test Reactor;175
1.5.4.3.2;3.2 Development of a Feasible Design for the New Concept Tubesheet Structure in Fast Breeder Reactors;177
1.5.4.4;4 Future Direction of Vibration Simulator;177
1.5.4.4.1;4.1 Development of Algorithm in Numerical Calculation;177
1.5.4.4.2;4.2 Response Estimation Method for Elasto-Plastic Analysis;179
1.5.4.4.3;4.3 Analysis Capability for Seismic Fluid Phenomena;179
1.5.4.4.3.1;4.3.1 Installation of Open Source CFD Software on BX900;179
1.5.4.4.3.2;4.3.2 Development of Characteristic Simulation of Two-Phase Flow Turbulence;180
1.5.4.5;5 Conclusion;183
1.5.4.6;References;184