With recent changes in multicore and general-purpose computing on graphics processing units, the way parallel computers are used and programmed has drastically changed. It is important to provide a comprehensive study on how to use such machines written by specialists of the domain. The book provides recent research results in high-performance computing on complex environments, information on how to efficiently exploit heterogeneous and hierarchical architectures and distributed systems, detailed studies on the impact of applying heterogeneous computing practices to real problems, and applications varying from remote sensing to tomography. The content spans topics such as Numerical Analysis for Heterogeneous and Multicore Systems; Optimization of Communication for High Performance Heterogeneous and Hierarchical Platforms; Efficient Exploitation of Heterogeneous Architectures, Hybrid CPU+GPU, and Distributed Systems; Energy Awareness in High-Performance Computing; and Applications of Heterogeneous High-Performance Computing. Covers cutting-edge research in HPC on complex environments, following an international collaboration of members of the ComplexHPC Explains how to efficiently exploit heterogeneous and hierarchical architectures and distributed systems Twenty-three chapters and over 100 illustrations cover domains such as numerical analysis, communication and storage, applications, GPUs and accelerators, and energy efficiency
Contributors xxiii Preface
PART I INTRODUCTION
1. Summary of the Open European Network for High-Performance Computing in Complex Environments
Emmanuel Jeannot and Julius Zilinskas 1.1 Introduction and Vision
1.2 Scientific Organization
1.3 Activities of the Project
1.4 Main Outcomes of the Action
1.5 Contents of the Book
PART II NUMERICAL ANALYSIS FOR HETEROGENEOUS AND MULTICORE SYSTEMS
2. On the Impact of the Heterogeneous Multicore and Many-Core Platforms on Iterative Solution Methods and Preconditioning Techniques
Dimitar Lukarski and Maya Neytcheva 2.1 Introduction
2.2 General Description of Iterative Methods and Preconditioning
2.3 Preconditioning Techniques
2.4 Defect-Correction Technique
2.5 Multigrid Method
2.6 Parallelization of Iterative Methods
2.7 Heterogeneous Systems
2.8 Maintenance and Portability
2.9 Conclusion
3. Efficient Numerical Solution of 2D Diffusion Equation on Multicore Computers
Matjaz Depolli, Gregor Kosec, and Roman Trobec 3.1 Introduction
3.2 Test Case
3.3 Parallel Implementation
3.4 Results
3.5 Discussion
3.6 Conclusion
4. Parallel Algorithms for Parabolic Problems on Graphs in Neuroscience
Natalija Tumanova and Raimondas Ciegis 4.1 Introduction
4.2 Formulation of the Discrete Model
4.3 Parallel Algorithms
4.4 Computational Results
4.5 Conclusions
PART III COMMUNICATION AND STORAGE CONSIDERATIONS IN HIGH-PERFORMANCE COMPUTING
5. An Overview of Topology Mapping Algorithms and Techniques in High-Performance Computing
Torsten Hoefler, Emmanuel Jeannot, and Guillaume Mercier 5.1 Introduction
5.2 General Overview
5.3 Formalization of the Problem
5.4 Algorithmic Strategies for Topology Mapping
5.5 Mapping Enforcement Techniques
5.6 Survey of Solutions
5.7 Conclusion and Open Problems
6. Optimization of Collective Communication for Heterogeneous HPC Platforms
Kiril Dichev and Alexey Lastovetsky 6.1 Introduction
6.2 Overview of Optimized Collectives and Topology-Aware Collectives
6.3 Optimizations of Collectives on Homogeneous Clusters
6.4 Heterogeneous Networks
6.5 Topology- and Performance-Aware Collectives
6.6 Topology as Input
6.7 Performance as Input
6.8 Non-MPI Collective Algorithms for Heterogeneous Networks
6.9 Conclusion
7. Effective Data Access Patterns on Massively Parallel Processors
Gabriele Capannini, Ranieri Baraglia, Fabrizio Silvestri, and Franco Maria Nardini 7.1 Introduction
7.2 Architectural Details
7.3 K-Model
7.4 Parallel Prefix Sum
7.5 Bitonic Sorting Networks
7.6 Final Remarks
8. Scalable Storage I/O Software for Blue Gene Architectures
Florin Isaila, Javier Garcia, and Jesus Carretero 8.1 Introduction
8.2 Blue Gene System Overview
8.3 Design and Implementation
8.4 Conclusions and Future Work
PART IV EFFICIENT EXPLOITATION OF HETEROGENEOUS ARCHITECTURES
9. Fair Resource Sharing for Dynamic Scheduling of Workflows on Heterogeneous Systems
Hamid Arabnejad, Jorge G. Barbosa, and Frederic Suter 9.1 Introduction
9.2 Concurrent Workflow Scheduling
9.3 Experimental Results and Discussion
9.4 Conclusions
10. Systematic Mapping of Reed Solomon Erasure Codes on Heterogeneous Multicore Architectures
Roman Wyrzykowski, Marcin Wozniak, and Lukasz Kuczynski 10.1 Introduction
10.2 Related Works
10.3 Reed Solomon Codes and Linear Algebra Algorithms
10.4 Mapping Reed Solomon Codes on Cell/B.E. Architecture
10.5 Mapping Reed Solomon Codes on Multicore GPU Architectures
10.6 Methods of Increasing the Algorithm Performance on GPUs
10.7 GPU Performance Evaluation
10.8 Conclusions and Future Works
11. Heterogeneous Parallel Computing Platforms and Tools for Compute-Intensive Algorithms: A Case Study
Daniele D'Agostino, Andrea Clematis, and Emanuele Danovaro 11.1 Introduction
11.2 A Low-Cost Heterogeneous Computing Environment
11.3 First Case Study: The N-Body Problem
11.4 Second Case Study: The Convolution Algorithm
11.5 Conclusions
12. Efficient Application of Hybrid Parallelism in Electromagnetism Problems
Alejandro Alvarez-Melcon, Fernando D. Quesada, Domingo Gimenez, Carlos Perez-Alcaraz, Jose-Gines Picon, and Tomas Ramirez 12.1 Introduction
12.2 Computation of Green s functions in Hybrid Systems
12.3 Parallelization in Numa Systems of a Volume Integral Equation Technique
12.4 Autotuning Parallel Codes
12.5 Conclusions and Future Research
PART V CPU + GPU COPROCESSING
13. Design and Optimization of Scientific Applications for Highly Heterogeneous and Hierarchical HPC Platforms Using Functional Computation Performance Models
David Clarke, Aleksandar Ilic, Alexey Lastovetsky, Vladimir Rychkov, Leonel Sousa, and Ziming Zhong 13.1 Introduction
13.2 Related Work
13.3 Data Partitioning Based on Functional Performance Model
13.4 Example Application: Heterogeneous Parallel Matrix Multiplication
13.5 Performance Measurement on CPUs/GPUs System
13.6 Functional Performance Models of Multiple Cores and GPUs
13.7 FPM-Based Data Partitioning on CPUs/GPUs System
13.8 Efficient Building of Functional Performance Models
13.9 FPM-Based Data Partitioning on Hierarchical Platforms
13.10 Conclusion
14. Efficient Multilevel Load Balancing on Heterogeneous CPU + GPU Systems
Aleksandar Ilic and Leonel Sousa 14.1 Introduction: Heterogeneous CPU + GPU Systems
14.2 Background and Related Work
14.3 Load Balancing Algorithms for Heterogeneous CPU + GPU Systems
14.4 Experimental Results
14.5 Conclusions
15. The All-Pair Shortest-Path Problem in Shared-Memory Heterogeneous Systems
Hector Ortega-Arranz, Yuri Torres, Diego R. Llanos, and Arturo Gonzalez-Escribano 15.1 Introduction
15.2 Algorithmic Overview
15.3 CUDA Overview
15.4 Heterogeneous Systems and Load Balancing
15.5 Parallel Solutions to The APSP
15.6 Experimental Setup
15.7 Experimental Results
15.8 Conclusions
PART VI EFFICIENT EXPLOITATION OF DISTRIBUTED SYSTEMS
16. Resource Management for HPC on the Cloud
Marc E. Frincu and Dana Petcu 16.1 Introduction
16.2 On the Type of Applications for HPC and HPC2
16.3 HPC on the Cloud
16.4 Scheduling Algorithms for HPC2
16.5 Toward an Autonomous Scheduling Framework
16.6 Conclusions
17. Resource Discovery in Large-Scale Grid Systems
Konstantinos Karaoglanoglou and Helen Karatza 17.1 Introduction and Background
17.2 The Semantic Communities Approach
17.3 The P2P Approach
17.4 The Grid-Routing Transferring Approach
17.5 Conclusions
PART VII ENERGY AWARENESS IN HIGH-PERFORMANCE COMPUTING
18. Energy-Aware Approaches for HPC Systems
Robert Basmadjian, Georges Da Costa, Ghislain Landry Tsafack Chetsa, Laurent Lefevre, Ariel Oleksiak, and Jean-Marc Pierson 18.1 Introduction
18.2 Power Consumption of Servers
18.3 Classification and Energy Profiles of HPC Applications
18.4 Policies and Leverages
18.5 Conclusion
19. Strategies for Increased Energy Awareness in Cloud Federations
Gabor Kecskemeti, AttilaKertesz, Attila Cs. Marosi, and Zsolt Nemeth 19.1 Introduction
19.2 Related Work
19.3 Scenarios
19.4 Energy-Aware Cloud Federations
19.5 Conclusions
20. Enabling Network Security in HPC Systems Using Heterogeneous CMPs
Ozcan Ozturk and Suleyman Tosun 20.1 Introduction
20.2 Related Work
20.3 Overview of Our Approach
20.4 Heterogeneous CMP Design for Network Security Processors
20.5 Experimental Evaluation
20.6 Concluding Remarks
PART VIII APPLICATIONS OF HETEROGENEOUS HIGH-PERFORMANCE COMPUTING
21. Toward a High-Performance Distributed CBIR System for Hyperspectral Remote Sensing Data: A Case Study in Jungle Computing
Timo van Kessel, NielsDrost, Jason Maassen, Henri E. Bal, Frank J. Seinstra, and Antonio J. Plaza 21.1 Introduction
21.2 CBIR For Hyperspectral Imaging Data
21.3 Jungle Computing
21.4 IBIS and Constellation
21.5 System Design and Implementation
21.6 Evaluation
21.7 Conclusions
22. Taking Advantage of Heterogeneous Platforms in Image and Video Processing
Sidi A. Mahmoudi, Erencan Ozkan, Pierre Manneback, and Suleyman Tosun 22.1 Introduction
22.2 Related Work
22.3 Parallel Image Processing on GPU
22.4 Image Processing on Heterogeneous Architectures
22.5 Video Processing on GPU
22.6 Experimental Results
22.7 Conclusion
23. Real-Time Tomographic Reconstruction Through CPU + GPU Coprocessing
Jose Ignacio Agulleiro, Francisco Vazquez, Ester M. Garzon, and Jose J. Fernandez 23.1 Introduction
23.2 Tomographic Reconstruction
23.3 Optimization of Tomographic Reconstruction for CPUs and for GPUs
23.4 Hybrid CPU + GPU Tomographic Reconstruction
23.5 Results
23.6 Discussion and Conclusion
Acknowledgments
References
Index
新书报道