Custom cover image
High Performance Computing on Vector Systems 2011 / edited by Michael Resch, Xin Wang, Wolfgang Bez, Erich Focht, Hiroaki Kobayashi, Sabine Roller
Contributor(s): Resource type: Ressourcentyp: Buch (Online)Book (Online)Language: English Series: SpringerLink BücherPublisher: Berlin, Heidelberg : Springer-Verlag Berlin Heidelberg, 2012Description: Online-Ressource (VIII, 184p. 89 illus., 68 illus. in color, digital)ISBN:- 9783642222443
- 004.1/1 004.11
- 004
- QA71-90
- QA76.88 .H54 2012
- Online Book
Contents:
Summary: 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.PPN: PPN: 1651095981Package identifier: Produktsigel: ZDB-2-SEB | ZDB-2-SXMS | ZDB-2-SMA
High Performance Computing on Vector Systems 2011; Preface; Contents; Part I: Techniques and Tools for High Performance Systems; Performance and Scalability Analysisof a Chip Multi Vector Processor; 1 Introduction; 2 Chip Multi Vector Processor; 2.1 Structure of a Chip Multi Vector Processor; 2.2 Performance Model of a Chip Multi Vector Processor; 3 Performance Tuning for a Chip Multi Vector Processor; 3.1 Performance Analysis Using the Roofline Model; 3.2 Program Optimization; 3.2.1 Loop Unrolling; 3.2.2 Cache Blocking; 3.2.3 Performance Tuning Strategy Based on the Roofline Model
4 Performance and Scalability Analysis4.1 Methodology; 4.2 Benchmarks; 4.3 Performance Evaluation of CMVP; 4.4 Performance Evaluation of CMVP with Performance Tuning; 5 Conclusions; References; I/O Forwarding for Quiet Clusters; 1 Introduction; 2 Operating System Noise; 2.1 So …Who's the Noisy Neighbour?; 2.2 Impact on Applications; 2.3 Mitigation; 2.3.1 Silence Your System; 2.3.2 Embrace Noise; 2.3.3 Synchronize Noise; 2.3.4 Prioritize; 2.3.5 Travel Light; 3 Measuring Noise; 3.1 Test System; 3.2 Fixed Work Quanta Benchmark; 3.3 Fixed Time Quanta Benchmark; 4 I/O Induced Noise
5 I/O Forwarding5.1 I/O Forwarding Architecture; 5.2 System I/O Interceptors: Libsysio; 5.3 I/O Forwarding Protocol: IOD Driver and Server; 5.4 Communication Framework: Portals; 5.5 Using the I/O Forwarding Framework; 5.6 Noise; 5.7 FUSE Driver; 6 Conclusion; References; A Prototype Implementation of OpenCL for SX Vector Systems; 1 Introduction; 2 OpenCL; 3 OpenCL for SX; 4 Early Evaluation and Discussions; 5 Conclusions; References; Distributed Parallelization of Semantic Web Java Applications by Means of the Message-Passing Interface; 1 Introduction; 2 Use Case Description: Random Indexing
3 Parallelization Strategy4 Realization by Means of MPI; 5 Implementation; 6 Application Performance Evaluation; 7 Performance Tailoring: Hybrid MPI-Java Threads Communication Pattern; 8 Final Discussion and Conclusion; References; HPC Systems at JAIST and Development of Dynamic Loop Monitoring Tools Toward Runtime Parallelization; 1 Introduction; 2 Information Environment and HPC Systems at JAIST; 3 Development of Dynamic Loop Monitoring Tools Toward Runtime Parallelization; 3.1 Background and Objectives of Dynamic Loop Monitoring Tools; 3.2 Parallelism and Loop Nest Structures
3.3 Loop Nest Detection and Loop-Call Context Tree Generation3.4 Evaluation of Our L-CCT Generation; 3.4.1 Experiment; 3.4.2 Results; 3.5 Run-Time Data Dependence Analysis; 3.5.1 Motivations and Strategies; 3.5.2 Details of Our Runtime Data Dependence Analysis; 3.5.3 Preliminary Evaluation of Runtime Data Dependence Analysis; 4 Conclusions; References; Part II: Methods and Technologies for Large-Scale Systems; Tree Based Voxelization of STL Data; 1 Introduction; 2 Octree Overview; 3 Mesh Generation; 3.1 Intersection Algorithm and Tree Generation; 3.2 Flooding; 3.3 Boundary Conditions
3.4 The File Format
No physical items for this record