CUDA编程学习（一）

/****c code****/
#include<stdio.h>

int main()
{
    printf("Hello world!\n);
    return ;
}

/****CUDA code****/

_global_ void mykernel(void)
{
}

int main()
{
    mykernel<<<,>>>();
    printf("Hello world!\n");
    return ;
}

1: _global_ 这个符号代表这个函数是在GPU里面跑的

2: mykernel<<<1,1>>>() Also called a "kernel launch"

/**** Add two integers****/

_global_ void add(int *a, int *b, int *c);
{
    *c = *a + *b;
}

int main()
{
    int a, b, c;            //host copies of a, b ,c
    int *d_a, *d_b, *d_c;    //device copies of a, b, c
    int size = sizeof(int);

    //Allocate space for device copies of a, b, c
    cudaMalloc((void **)&d_a, size);
    cudaMalloc((void **)&d_b, size);
    cudaMalloc((void **)&d_c, size);

    //Setup input values
    a = ;
    b = ;

    //Cope inputs to device

    cudaMemcpy(d_a, &a, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_b, &b, size, cudaMemcpyHostToDevice);

    //Launch add() kernel on GPU
    add<<<,>>>(d_a, d_b, d_c);

    //Copy result back to host
    cudaMemcpy(&c, d_c, size, cudaMemcpyDeviceToHost);

    //Cleanup
    cudaFree(d_a); cudaFree(d_b); cudaFree(d_c);
    return ;
}