CUDA函数的一些例子简介和下载链接

CUDA SAMPLES

TRM-06704-001_v6.0 | February 2014

Reference Manual

www.nvidia.com

CUDA Samples TRM-06704-001_v6.0|ii

TABLE OF CONTENTS

Chapter1.New Features.......................................................................................1

1.1.New Features in CUDA Toolkit 6.0.....................................................................1

1.1.1.CUDA Version 6.0 Highlights.......................................................................1

1.3.2.CUDA Dynamic Parallelism Samples in CUDA 5.0 and CUDA 5.5............................. 3

1.3.3.New Revised CUDA Code Samples................................................................ 4

1.4.New Features in CUDA Toolkit 4.2.....................................................................5

1.5.New Features in CUDA Toolkit 4.1.....................................................................5

Chapter2.Getting Started.....................................................................................8

2.1.Supported OS Platforms and Compilers...............................................................8

2.1.1.Supported Windows Platforms.................................................................... 8

2.1.2.Supported Linux Platforms.........................................................................9

2.1.3.Supported Mac Platforms......................................................................... 13

2.1.4.Supported Android Platforms.................................................................... 14

2.3.2.Creating CUDA Projects for Linux............................................................... 20

2.3.3.Creating CUDA Projects for Mac OS X.......................................................... 21

Chapter3.Samples Reference...............................................................................23

3.1.Simple Reference........................................................................................23

cppOverload................................................................................................. 23

Simple Quicksort (CUDA Dynamic Parallelism)........................................................ 24

Simple Print (CUDA Dynamic Parallelism).............................................................. 24

Simple Static GPU Device Library....................................................................... 24

Simple CUDA Callbacks.................................................................................... 24

simpleAssert................................................................................................. 25

www.nvidia.com

CUDA Samples TRM-06704-001_v6.0|iii

Simple Multi Copy and Compute........................................................................ 27

Vector Addition............................................................................................. 27

Vector Addition Driver API................................................................................27

Template using CUDA Runtime...........................................................................28

Template..................................................................................................... 28

C++ Integration............................................................................................. 28

asyncAPI......................................................................................................29

Clock..........................................................................................................29

Simple Atomic Intrinsics.................................................................................. 29

Pitch Linear Texture....................................................................................... 29

Simple Multi-GPU........................................................................................... 32

Matrix Multiplication (CUBLAS)...........................................................................32

Matrix Multiplication (CUDA Runtime API Version)................................................... 32

Matrix Multiplication (CUDA Driver API Version)...................................................... 33

Unified Memory Streams.................................................................................. 33

simpleMPI.................................................................................................... 33

cudaOpenMP.................................................................................................34

3.2.UtilitiesReference...................................................................................... 34

Peer-to-Peer Bandwidth Latency Test with Multi-GPUs.............................................. 34

Device Query................................................................................................ 34

Simple D3D11 Texture..................................................................................... 36

Simple Direct3D9 (Vertex Arrays)........................................................................37

Simple D3D9 Texture.......................................................................................37

Simple Direct3D10 (Vertex Array)....................................................................... 37

Simple Direct3D10 Render Target....................................................................... 38

Simple D3D10 Texture..................................................................................... 38

Simple OpenGL..............................................................................................39

Simple Texture 3D..........................................................................................39

Mandelbrot...................................................................................................39

Marching Cubes Isosurfaces...............................................................................40

www.nvidia.com

CUDA Samples TRM-06704-001_v6.0|iv

3.4.ImagingReference...................................................................................... 40

CUDA and OpenGL Interop of Images...................................................................40

Stereo Disparity Computation (SAD SIMD Intrinsics).................................................. 41

Optical Flow.................................................................................................41

CUDA Video Encode (C Library) API.....................................................................41

Bilateral Filter.............................................................................................. 42

DCT8x8....................................................................................................... 42

1D Discrete Haar Wavelet Decomposition..............................................................42

CUDA Histogram............................................................................................ 43

Box Filter.................................................................................................... 43

CUDA Video Decoder GL API............................................................................. 45

Bicubic B-spline Interoplation............................................................................46

FFT-Based 2D Convolution................................................................................ 46

CUDA Separable Convolution............................................................................. 47

Texture-based Separable Convolution.................................................................. 47

3.5.FinanceReference...................................................................................... 47

Binomial Option Pricing................................................................................... 47

Black-Scholes Option Pricing............................................................................. 47

Niederreiter Quasirandom Sequence Generator...................................................... 48

Monte Carlo Option Pricing with Multi-GPU support................................................. 48

Fluids (OpenGL Version)...................................................................................50

CUDA FFT Ocean Simulation............................................................................. 50

Particles...................................................................................................... 50

CUDA N-Body Simulation.................................................................................. 51

Smoke Particles............................................................................................. 52

3.7.AdvancedReference.................................................................................... 52

Quad Tree (CUDA Dynamic Parallelism)................................................................ 52

LU Decomposition (CUDA Dynamic Parallelism)....................................................... 52

Bezier Line Tesselation (CUDA Dynamic Parallelism).................................................53

Advanced Quicksort (CUDA Dynamic Parallelism).....................................................53

www.nvidia.com

CUDA Samples TRM-06704-001_v6.0|v

CUDA Parallel Prefix Sum with Shuffle Intrinsics (SHFL_Scan)...................................... 53

CUDA Segmentation Tree Thrust Library............................................................... 54

NewDelete................................................................................................... 54

Function Pointers........................................................................................... 54

Interval Computing.........................................................................................54

CUDA C 3D FDTD........................................................................................... 54

CUDA Context Thread Management..................................................................... 55

Matrix Multiplication (CUDA Driver API version with Dynamic Linking Version).................. 55

Scalar Product.............................................................................................. 55

Concurrent Kernels.........................................................................................56

CUDA Parallel Reduction.................................................................................. 57

CUDA Parallel Prefix Sum (Scan)........................................................................ 58

threadFenceReduction..................................................................................... 58

CUDA Radix Sort (Thrust Library)....................................................................... 58

CUDA Sorting Networks....................................................................................59

Stream Priorities............................................................................................59

Merge Sort................................................................................................... 59

3.8.CudalibrariesReference................................................................................60

JPEG encode/decode and resize with NPP............................................................ 60

simpleDevLibCUBLAS GPU Device API Library Functions (CUDA Dynamic Parallelism)...........60

Preconditioned Conjugate Gradient.....................................................................62

Random Fog................................................................................................. 62

Monte Carlo Single Asian Option........................................................................ 62

Monte Carlo Estimation of Pi (batch QRNG)........................................................... 62

Monte Carlo Estimation of Pi (batch PRNG)........................................................... 63

Monte Carlo Estimation of Pi (batch inline QRNG)................................................... 63

Monte Carlo Estimation of Pi (inline PRNG)........................................................... 63

ConjugateGradient......................................................................................... 63

batchCUBLAS................................................................................................ 64

Simple CUBLAS.............................................................................................. 64