ManyCore Programming GPU： CUDA Part

转载请注明出处：http://blog.csdn.net/c602273091/article/details/55803498

介绍

18-645：how to write fast code中使用了CUDA，参考教材是【1】。在国外买这本书的话需要60刀，国内的话找一找就可以下到较为清晰的版本。

这一部分主要是介绍CUDA的基本的写法【2】

直接上CUDA的代码进行了解，然后从代码中学到需要的东西。就以【2】中提到的代码为例子：

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

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

// 核函数做了一个加法操作
__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.
    // 把需要做运算的参数传入Kernel里，并且调用Kernel计算，计算之后把数据传回host里，也就是c
    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]);

    // cudaThreadExit must be called before exiting in order for profiling and
    // tracing tools such as Nsight and Visual Profiler to show complete traces.
    // cudaThreadExit()这个函数就是在执行结束以后进行调用
    cudaStatus = cudaThreadExit();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaThreadExit 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, size_t 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.
    // 选择哪个GPU去跑，尤其是多GPU的时候
    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)
    // 为要进入GPU的数据分配存储    .
    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;
    }

    // 把要计算的数据放入GPU中进行计算
    // 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;
    }

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

    // cudaThreadSynchronize waits for the kernel to finish, and returns
    // any errors encountered during the launch.
    // 同步操作，直到上一步结束程序再执行到下面，否则等待
    cudaStatus = cudaThreadSynchronize();
    if (cudaStatus != cudaSuccess) {
        fprintf(stderr, "cudaThreadSynchronize returned error code %d after launching addKernel!\n", cudaStatus);
        goto Error;
    }

    // Copy output vector from GPU buffer to host memory.
    // 从slave中拷贝数据回host文件
    cudaStatus = cudaMemcpy(c, dev_c, size * sizeof(int), cudaMemcpyDeviceToH