1、新建空專案

2、新增test.cu

3、右鍵專案---生成依賴項--生成自定義---CUDA8.0打鉤

4、右鍵test.cu---屬性--選擇CUDA C/C++

5、包含目錄

C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\include

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v8.0\common\inc

6、庫目錄

C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v8.0\lib\x64

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v8.0\common\lib\x64

7、輸入

cublas.lib
cublas_device.lib
cuda.lib
cudadevrt.lib
cudart.lib
cudart_static.lib
cufft.lib
cufftw.lib
curand.lib
cusparse.lib
nppc.lib
nppi.lib
npps.lib
nvcuvid.lib

OpenCL.lib

8、新增一個test.h

#pragma once
#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>

int xx();

9、新增一個main.cpp

#include <iostream>
#include "test.h"
#include <iostream>
#include <fstream>
#include <time.h>
#include <windows.h>
using namespace std;
int main()
{
Mat pad_Img = imread("./data/5X(1).bmp", CV_LOAD_IMAGE_GRAYSCALE);
xx();
return 0;
}

10、test.cu中新增

//#include "cuda_runtime.h"
//#include "device_launch_parameters.h"
//
//#include <stdio.h>
#include "larch_cuda.h"


cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size);


__global__ void addKernel(int *c, const int *a, const int *b)
{
int i = threadIdx.x;
c[i] = a[i] + b[i];
}


int xx()
{
const int arraySize = 5;
const int a[arraySize] = { 1, 2, 3, 4, 5 };
const int b[arraySize] = { 10, 20, 30, 40, 50 };
int c[arraySize] = { 0 };


// Add vectors in parallel.
cudaError_t cudaStatus = addWithCuda(c, a, b, arraySize);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "addWithCuda failed!");
return 1;
}


printf("{1,2,3,4,5} + {10,20,30,40,50} = {%d,%d,%d,%d,%d}\n",
c[0], c[1], c[2], c[3], c[4]);


// cudaDeviceReset must be called before exiting in order for profiling and
// tracing tools such as Nsight and Visual Profiler to show complete traces.
cudaStatus = cudaDeviceReset();
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaDeviceReset failed!");
return 1;
}


return 0;
}


// Helper function for using CUDA to add vectors in parallel.
cudaError_t addWithCuda(int *c, const int *a, const int *b, unsigned int size)
{
int *dev_a = 0;
int *dev_b = 0;
int *dev_c = 0;
cudaError_t cudaStatus;


// Choose which GPU to run on, change this on a multi-GPU system.
cudaStatus = cudaSetDevice(0);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaSetDevice failed!  Do you have a CUDA-capable GPU installed?");
goto Error;
}


// Allocate GPU buffers for three vectors (two input, one output)    .
cudaStatus = cudaMalloc((void**)&dev_c, size * sizeof(int));
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMalloc failed!");
goto Error;
}


cudaStatus = cudaMalloc((void**)&dev_a, size * sizeof(int));
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMalloc failed!");
goto Error;
}


cudaStatus = cudaMalloc((void**)&dev_b, size * sizeof(int));
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMalloc failed!");
goto Error;
}


// Copy input vectors from host memory to GPU buffers.
cudaStatus = cudaMemcpy(dev_a, a, size * sizeof(int), cudaMemcpyHostToDevice);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMemcpy failed!");
goto Error;
}


cudaStatus = cudaMemcpy(dev_b, b, size * sizeof(int), cudaMemcpyHostToDevice);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMemcpy failed!");
goto Error;
}


// Launch a kernel on the GPU with one thread for each element.
addKernel << <1, size >> >(dev_c, dev_a, dev_b);


// Check for any errors launching the kernel
cudaStatus = cudaGetLastError();
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "addKernel launch failed: %s\n", cudaGetErrorString(cudaStatus));
goto Error;
}


// cudaDeviceSynchronize waits for the kernel to finish, and returns
// any errors encountered during the launch.
cudaStatus = cudaDeviceSynchronize();
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\n", cudaStatus);
goto Error;
}


// Copy output vector from GPU buffer to host memory.
cudaStatus = cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToHost);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaMemcpy failed!");
goto Error;
}


Error:
cudaFree(dev_c);
cudaFree(dev_a);
cudaFree(dev_b);


return cudaStatus;

}

11、跑起來