CUDA-GPU编程

参考：http://blog.csdn.net/augusdi/article/details/12833235  第二节

新建NVIDIA项目：

新建项目及会生成一个简单的代码demo，计算矩阵的加法，如下（main中加了一些显示显卡性能的打印）：

#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}
",
        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;
    }

    int deviceCount;
    cudaGetDeviceCount(&deviceCount);
    int dev;
    for (dev = 0; dev < deviceCount; dev++)
    {
        cudaDeviceProp deviceProp;
        cudaGetDeviceProperties(&deviceProp, dev);
        if (dev == 0)
        {
            if (/*deviceProp.major==9999 && */deviceProp.minor = 9999&&deviceProp.major==9999)
                printf("
");

        }
        printf("
Device%d:"%s"
", dev, deviceProp.name);
        printf("Total amount of global memory                   %u bytes
", deviceProp.totalGlobalMem);
        printf("Number of mltiprocessors                        %d
", deviceProp.multiProcessorCount);
        printf("Total amount of constant memory:                %u bytes
", deviceProp.totalConstMem);
        printf("Total amount of shared memory per block         %u bytes
", deviceProp.sharedMemPerBlock);
        printf("Total number of registers available per block:  %d
", deviceProp.regsPerBlock);
        printf("Warp size                                       %d
", deviceProp.warpSize);
        printf("Maximum number of threada per block:            %d
", deviceProp.maxThreadsPerBlock);
        printf("Maximum sizes of each dimension of a block:     %d x %d x %d
", deviceProp.maxThreadsDim[0],
            deviceProp.maxThreadsDim[1],
            deviceProp.maxThreadsDim[2]);
        printf("Maximum size of each dimension of a grid:       %d x %d x %d
", deviceProp.maxGridSize[0], deviceProp.maxGridSize[1], deviceProp.maxGridSize[2]);
        printf("Maximum memory pitch :                          %u bytes
", deviceProp.memPitch);
        printf("Texture alignmemt                               %u bytes
", deviceProp.texturePitchAlignment);
        printf("Clock rate                                      %.2f GHz
", deviceProp.clockRate*1e-6f);
    }
    printf("
Test PASSED
");


    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
", 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!
", 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;
}