Heterogeneous Computing with OpenCL, 2nd Edition

Table of contents

1. Cover image
2. Title page
3. Table of Contents
4. Copyright
5. Foreword to the Revised OpenCL 1.2 Edition
6. Foreword to the First Edition
7. Preface
   1. Our Heterogeneous World
   2. OpenCL
   3. This Text
8. Acknowledgments
9. About the Authors
10. Chapter 1. Introduction to Parallel Programming
    1. Introduction
    2. OpenCL
    3. The Goals of This Book
    4. Thinking Parallel
    5. Concurrency and Parallel Programming Models
    6. Structure
    7. Reference
    8. Further Reading and Relevant Websites
11. Chapter 2. Introduction to OpenCL
    1. Introduction
    2. Platform and Devices
    3. The Execution Environment
    4. Memory Model
    5. Writing Kernels
    6. Full Source Code Example for Vector Addition
    7. Vector Addition with C++ Wrapper
    8. Summary
    9. Reference
12. Chapter 3. OpenCL Device Architectures
    1. Introduction
    2. Hardware trade-offs
    3. The architectural design space
    4. Summary
    5. References
13. Chapter 4. Basic OpenCL Examples
    1. Introduction
    2. Example Applications
    3. Compiling OpenCL Host Applications
    4. Summary
14. Chapter 5. Understanding OpenCL’s Concurrency and Execution Model
    1. Introduction
    2. Kernels, Work-Items, Workgroups, and the Execution Domain
    3. OpenCL Synchronization: Kernels, Fences, and Barriers
    4. Queuing and Global Synchronization
    5. The Host-Side Memory Model
    6. The Device-Side Memory Model
    7. Summary
15. Chapter 6. Dissecting a CPU/GPU OpenCL Implementation
    1. Introduction
    2. OpenCL on an AMD Bulldozer CPU
    3. OpenCL on the AMD Radeon HD7970 GPU
    4. Memory Performance Considerations in OpenCL
    5. Summary
    6. References
16. Chapter 7. Data Management
    1. Memory management
    2. Data transfer in a discrete environment
    3. Data placement in a shared-memory environment
    4. Example application—work group reduction
    5. References
17. Chapter 8. OpenCL Case Study: Convolution
    1. Introduction
    2. Convolution Kernel
    3. Conclusions
    4. Code Listings
    5. Reference
18. Chapter 9. OpenCL Case Study: Histogram
    1. Introduction
    2. Choosing the Number of Workgroups
    3. Choosing the Optimal Workgroup Size
    4. Optimizing Global Memory Data Access Patterns
    5. Using Atomics to Perform Local Histogram
    6. Optimizing Local Memory Access
    7. Local Histogram Reduction
    8. The Global Reduction
    9. Full Kernel Code
    10. Performance and Summary
19. Chapter 10. OpenCL Case Study: Mixed Particle Simulation
    1. Introduction
    2. Overview of the Computation
    3. GPU Implementation
    4. CPU Implementation
    5. Load Balancing
    6. Performance and Summary
    7. Kernel for Uniform Grid Creation
    8. Kernels for Simulation
20. Chapter 11. OpenCL Extensions
    1. Introduction
    2. Overview of Extension Mechanism
    3. Device Fission
    4. Double Precision
    5. References
21. Chapter 12. Foreign Lands: Plugging OpenCL In
    1. Introduction
    2. Beyond C and C++
    3. Haskell OpenCL
    4. Summary
    5. References
22. Chapter 13. OpenCL Profiling and Debugging
    1. Introduction
    2. Profiling with events
    3. AMD Accelerated Parallel Processing Profiler
    4. AMD Accelerated Parallel Processing KernelAnalyzer
    5. Walking through the AMD APP Profiler
    6. Debugging OpenCL Applications
    7. Overview of gDEBugger
    8. AMD Printf Extension
    9. Conclusion
23. Chapter 14. Performance Optimization of an Image Analysis Application
    1. Introduction
    2. Description of the algorithm
    3. Migrating multithreaded CPU implementation to OpenCL
    4. Performance optimization
    5. Power and performance analysis
    6. Conclusion
    7. References
24. Index