CUDA（一）—基础知识

官方示例
新版本和老版本有一些不同之处
threadIdx，而不是blockIdx

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <iostream>
#include <stdio.h>
using namespace std;

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;
    }

    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;
}

#include "cuda_runtime.h"
#include <iostream>
#include "book.h"
#include <cstring>
using namespace std;
__global__ void add(int a,int b,int* c)//tell the visual studio the function run in GPU
{
    *c = a + b;
}
int main()
{
    //---
    int c;
    int* dev_c;
    HANDLE_ERROR(cudaMalloc((void**)& dev_c, sizeof(int)));
    add << <1, 1 >> > (2, 7, dev_c);
    HANDLE_ERROR(cudaMemcpy(&c, dev_c, sizeof(int), cudaMemcpyDeviceToHost));
    cout << "2+7=" << c << endl;
    cudaFree(dev_c);
    //---
    int count;
    //HANDLE_ERROR(cudaGetDeviceCount(&count));
    cudaGetDeviceCount(&count);
    cout <<"Device Count:"<< count << endl;
    cudaDeviceProp prop;
    for (int i = 0; i < count; i++)
    {
        cudaGetDeviceProperties(&prop, i);
    }
    cout << prop.name << endl;
    cout << prop.regsPerMultiprocessor << endl;
    cout << prop.totalGlobalMem << endl;
    memset(&prop, 0, sizeof(cudaDeviceProp));
    prop.major = 7;
    prop.minor = 5;
    cudaChooseDevice(&count, &prop);
    cout << "ID of revision:" << count << endl;
    cudaSetDevice(count);
    return 0;
}
/*
void *memcpy(void *dest, const void *src, size_t n);
从源src所指的内存地址的起始位置开始拷贝n个字节到目标dest所指的内存地址的起始位置中
void *memset(void *s, int ch, size_t n);
将s中当前位置后面的n个字节 （typedef unsigned int size_t ）用 ch 替换并返回 s 。
memset：作用是在一段内存块中填充某个给定的值，它是对较大的结构体或数组进行清零操作的一种最快方法
*/