CONTENIDO: WHY CUDA? WHY NOW?
Chapter Objectives
The Age of Parallel Processing
The Rise of GPU Computing
CUDA
Applications of CUDA
Chapter Review
GETTING STARTED
Chapter Objectives
Development Environment
Chapter Review
INTRODUCTION TO CUDA C
Chapter Objectives
A First Program
Querying Devices
Using Device Properties
Chapter Review
PARALLEL PROGRAMMING IN CUDA C
Chapter Objectives
CUDA Parallel Programming
Chapter Review
THREAD COOPERATION
Chapter Objectives
Splitting Parallel Blocks
Shared Memory and Synchronization
Chapter Review
CONSTANT MEMORY AND EVENTS
Chapter Objectives
Constant Memory
Measuring Performance with Events
Chapter Review
TEXTURE MEMORY
Chapter Objectives
Texture Memory Overview
Simulating Heat Transfer
Chapter Review
GRAPHICS INTEROPERABILITY
Chapter Objectives
Graphics Interoperation
GPU Ripple with Graphics Interoperability
Heat Transfer with Graphics Interop
DirectX Interoperability
Chapter Review
ATOMICS
Chapter Objectives
Compute Capability
Atomic Operations Overview
Computing Histograms
Chapter Review
STREAMS
Chapter Objectives
Page-Locked Host Memory
CUDA Streams
Using a Single CUDA Stream
Using Multiple CUDA Streams
GPU Work Scheduling
Using Multiple CUDA Streams Effectively
Chapter Review
CUDA C ON MULTIPLE GPU'S
Chapter Objectives
Zero-Copy Host Memory
Using Multiple GPUs
Portable Pinned Memory
Chapter Review
THE FINAL COUNTDOWN
Chapter Objectives
CUDA Tools
Written Resources
Code Resources
Chapter Review
ADVANCED ATOMICS
Dot Product Revisited
Implementing a Hash Table
Appendix Review
Index
