繼上一篇部落格安裝完cuda8.0之後，現在在vs裡面配置一個cuda專案。
vs2017，新建專案，我發現已安裝模板沒有跳出NVDIA，所以我選擇了vs2010來新建cuda專案。

檔案--->新建--->專案--->Win32控制檯程式--->空專案

原始檔--->新增--->新建項--->NVIDIA CUDA 8.0--->code--->CUDA C/C++ File

右鍵新建好的test.cu--->配置屬性--->常規--->項型別：CUDA C/C++

右鍵cuda_test專案--->生成自定義--->勾選CUDA 8.0

右鍵cuda_test專案--->配置屬性--->CUDA C/C++--->Additional Include Directories: C:\ProgramData\NVIDIA Corporation\CUDA Samples\v8.0\common\inc
檢查一下自己是不是這個路徑。這一步的目的是為了找到所需的標頭檔案

<helper_string.h>
<helper_cuda.h>
<helper_functions.h>

連結器--->輸入--->附加依賴項: cudart.lib

test.cu(cuda原始碼的vectorAdd)

/**
 * Copyright 1993-2015 NVIDIA Corporation.  All rights reserved.
 *
 * Please refer to the NVIDIA end user license agreement (EULA) associated
 * with this source code for terms and conditions that govern your use of
 * this software. Any use, reproduction, disclosure, or distribution of
 * this software and related documentation outside the terms of the EULA
 * is strictly prohibited.
 *
 */

/**
 * Vector addition: C = A + B.
 *
 * This sample is a very basic sample that implements element by element
 * vector addition. It is the same as the sample illustrating Chapter 2
 * of the programming guide with some additions like error checking.
 */

#include <stdio.h>

// For the CUDA runtime routines (prefixed with "cuda_")
#include <cuda_runtime.h>

#include <helper_cuda.h>
/**
 * CUDA Kernel Device code
 *
 * Computes the vector addition of A and B into C. The 3 vectors have the same
 * number of elements numElements.
 */
__global__ void
vectorAdd(const float *A, const float *B, float *C, int numElements)
{
    int i = blockDim.x * blockIdx.x + threadIdx.x;

    if (i < numElements)
    {
        C[i] = A[i] + B[i];
    }
}

/**
 * Host main routine
 */
int
main(void)
{
    // Error code to check return values for CUDA calls
    cudaError_t err = cudaSuccess;

    // Print the vector length to be used, and compute its size
    int numElements = 50000;
    size_t size = numElements * sizeof(float);
    printf("[Vector addition of %d elements]\n", numElements);

    // Allocate the host input vector A
    float *h_A = (float *)malloc(size);

    // Allocate the host input vector B
    float *h_B = (float *)malloc(size);

    // Allocate the host output vector C
    float *h_C = (float *)malloc(size);

    // Verify that allocations succeeded
    if (h_A == NULL || h_B == NULL || h_C == NULL)
    {
        fprintf(stderr, "Failed to allocate host vectors!\n");
        exit(EXIT_FAILURE);
    }

    // Initialize the host input vectors
    for (int i = 0; i < numElements; ++i)
    {
        h_A[i] = rand()/(float)RAND_MAX;
        h_B[i] = rand()/(float)RAND_MAX;
    }

    // Allocate the device input vector A
    float *d_A = NULL;
    err = cudaMalloc((void **)&d_A, size);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector A (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Allocate the device input vector B
    float *d_B = NULL;
    err = cudaMalloc((void **)&d_B, size);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector B (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Allocate the device output vector C
    float *d_C = NULL;
    err = cudaMalloc((void **)&d_C, size);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector C (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Copy the host input vectors A and B in host memory to the device input vectors in
    // device memory
    printf("Copy input data from the host memory to the CUDA device\n");
    err = cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector A from host to device (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector B from host to device (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Launch the Vector Add CUDA Kernel
    int threadsPerBlock = 256;
    int blocksPerGrid =(numElements + threadsPerBlock - 1) / threadsPerBlock;
    printf("CUDA kernel launch with %d blocks of %d threads\n", blocksPerGrid, threadsPerBlock);
    vectorAdd<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_B, d_C, numElements);
    err = cudaGetLastError();

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to launch vectorAdd kernel (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Copy the device result vector in device memory to the host result vector
    // in host memory.
    printf("Copy output data from the CUDA device to the host memory\n");
    err = cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector C from device to host (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Verify that the result vector is correct
    for (int i = 0; i < numElements; ++i)
    {
        if (fabs(h_A[i] + h_B[i] - h_C[i]) > 1e-5)
        {
            fprintf(stderr, "Result verification failed at element %d!\n", i);
            exit(EXIT_FAILURE);
        }
    }

    printf("Test PASSED\n");

    // Free device global memory
    err = cudaFree(d_A);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector A (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaFree(d_B);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector B (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaFree(d_C);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector C (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Free host memory
    free(h_A);
    free(h_B);
    free(h_C);

    printf("Done\n");
    return 0;
}


 

執行結果

參考部落格：
https://blog.csdn.net/u012033124/article/details/70665838?utm_source=blogxgwz3