CUDA從入門到放棄（三）：Hello World 之第一個CUDA程式

vs2015中打開建立一個CUDA程式

拿個CUDA中的 hello world 示例程式過來跑一下吧！

示例來源于：​​CUDA Samples​​ 計算兩個數組間的加法

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include <stdio.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 main()
{
    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;
    }

    getchar();

    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;
}      

編譯資訊：

1>------ 已啟動全部重新生成: 項目: TestCUDA, 配置: Release x64 ------
1>
1>  E:\code\cppcode\TestCUDA\TestCUDA>"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\bin\nvcc.exe" -ccbin "C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\bin\x86_amd64" -x cu  -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\include"     --keep-dir x64\Release -maxrregcount=0  --machine 64 --compile      -DWIN32 -DWIN64 -DNDEBUG -D_CONSOLE -D_MBCS -Xcompiler "/EHsc /W0 /nologo /O2 /FS /Zi  /MD " -o x64\Release\kernel.cu.obj "E:\code\cppcode\TestCUDA\TestCUDA\kernel.cu" -clean
1>  kernel.cu
1>  Compiling CUDA source file kernel.cu...
1>
1>  E:\code\cppcode\TestCUDA\TestCUDA>"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\bin\nvcc.exe" -gencode=arch=compute_30,code=\"sm_30,compute_30\" --use-local-env --cl-version 2015 -ccbin "C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\bin\x86_amd64" -x cu  -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\include" -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\include"     --keep-dir x64\Release -maxrregcount=0  --machine 64 --compile -cudart static     -DWIN32 -DWIN64 -DNDEBUG -D_CONSOLE -D_MBCS -Xcompiler "/EHsc /W0 /nologo /O2 /FS /Zi  /MD " -o x64\Release\kernel.cu.obj "E:\code\cppcode\TestCUDA\TestCUDA\kernel.cu"
1>  kernel.cu
1>  LINK : 已指定 /LTCG，但不需要生成代碼；從連結指令行中移除 /LTCG 以提高連結器性能
1>  TestCUDA.vcxproj -> E:\code\cppcode\TestCUDA\x64\Release\TestCUDA.exe
1>  TestCUDA.vcxproj -> E:\code\cppcode\TestCUDA\x64\Release\TestCUDA.pdb (Full PDB)
1>  copy "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\bin\cudart*.dll" "E:\code\cppcode\TestCUDA\x64\Release\"
1>  C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\bin\cudart32_90.dll
1>  C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\bin\cudart64_90.dll
1>  已複制         2 個檔案。
========== 全部重新生成: 成功 1 個，失敗 0 個，跳過 0 個 ==========      

顯示結果：

參考資料

1 ​​CUDA程式設計入門​​​ 2 ​​Nvidia官方教程​​

3 ​​CUDA程式設計入門極簡教程​​

4 ​​CUDA Toolkit Documentation v9.0.176​​

5 ​​NVIDIA CUDA初級教程視訊​​

6 CUDA專家手冊 [GPU程式設計權威指南]

7 CUDA并行程式設計：GPU程式設計指南