CUDA Application Design and Development
Description
Key Features
- Includes multiple examples building from simple to more complex applications in four key areas: machine learning, visualization, vision recognition, and mobile computing
- Addresses the foundational issues for CUDA development: multi-threaded programming and the different memory hierarchy
- Includes teaching chapters designed to give a full understanding of CUDA tools, techniques and structure.
- Presents CUDA techniques in the context of the hardware they are implemented on as well as other styles of programming that will help readers bridge into the new material
Readership
Software engineers, programmers, hardware engineers, advanced students
Table of Contents
CHAPTER 1 First Programs and How to Think in CUDA
Source Code and Wiki
Distinguishing CUDA from Conventional Programming with a Simple Example
Choosing a CUDA API
Some Basic CUDA Concepts
Understanding Our First Runtime Kernel
Three Rules of GPGPU Programming
Big-O Considerations and Data Transfers
CUDA and Amdahl’s Law
Data and Task Parallelism
Hybrid Execution: Using Both CPU and GPU Resources
Regression Testing and Accuracy
Silent Errors
Introduction to Debugging
UNIX Debugging
Windows Debugging with Parallel Nsight
Summary
CHAPTER 2 CUDA for Machine Learning and Optimization
Modeling and Simulation
Machine Learning and Neural Networks
XOR: An Important Nonlinear Machine-Learning Problem
Performance Results on XOR
Performance Discussion
Summary
The C++ Nelder-Mead Template
CHAPTER 3 The CUDA Tool Suite: Profiling a PCA/NLPCA
Functor
PCA and NLPCA
Obtaining Basic Profile Information
Gprof: A Common UNIX Profiler
The NVIDIA Visual Profiler: Computeprof
Parallel Nsight for Microsoft Visual Studio
Tuning and Analysis Utilities (TAU)
Summary
CHAPTER 4 The CUDA Execution Model
GPU Architecture Overview
Warp Scheduling and TLP
ILP: Higher Performance at Lower Occupancy
Little’s Law
CUDA Tools to Identify Limiting Factors
Summary
CHAPTER 5 CUDA Memory
The CUDA Memory Hierarchy
GPU Memory
L2 Cache
L1 Cache
CUDA Memory Types
Global Memory
Summary
CHAPTER 6 Efficiently Using GPU Memory
Reduction
Utilizing Irregular Data Structures
Sparse Matrices and the CUSP Library
Graph Algorithms
SoA, AoS, and Other Structures
Tiles and Stencils
Summary
CHAPTER 7 Techniques to Increase Parallelism
CUDA Contexts Extend Parallelism
Streams and Contexts
Out-of-Order Execution with Multiple Streams
Tying Data to Computation
Summary
CHAPTER 8 CUDA for All GPU and CPU Applications
Pathways from CUDA to Multiple Hardware Backends
Accessing CUDA from Other Languages
Libraries
CUBLAS
CUFFT
Summary
CHAPTER 9 Mixing CUDA and Rendering
OpenGL
GLUT
Introduction to the Files in the Framework
Summary
CHAPTER 10 CUDA in a Cloud and Cluster Environments
The Message Passing Interface (MPI)
How MPI Communicates
Bandwidth
Balance Ratios
Considerations for Large MPI Runs
Cloud Computing
A Code Example
Summary
CHAPTER 11 CUDA for Real Problems
Working with High-Dimensional Data
PCA/NLPCA
Force-Directed Graphs
Monte Carlo Methods
Molecular Modeling
Quantum Chemistry
Interactive Workflows
A Plethora of Projects
Summary
CHAPTER 12 Application Focus on Live Streaming Video
Topics in Machine Vision
FFmpeg
TCP Server
Contents ix
Live Stream Application
The simpleVBO.cpp File
The callbacksVBO.cpp File
Building and Running the Code
The Future
Summary
Listing for simpleVBO.cpp
Product details
- No. of pages: 336
- Language: English
- Copyright: © Morgan Kaufmann 2011
- Published: October 8, 2011
- Imprint: Morgan Kaufmann
- eBook ISBN: 9780123884329
- Paperback ISBN: 9780123884268
About the Author
Rob Farber
