/****c code****/#include<stdio.h>int main(){    printf("Hello world!\n);    return 0;}/****CUDA code****/_global_ void mykernel(void){}int main(){    mykernel<<<1,1>>>();    printf("Hello world!\n");    return 0;}

/**** 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 = 2;    b = 7;        //Cope inputs to device        cudaMemcpy(d_a, &a, size, cudaMemcpyHostToDevice);    cudaMemcpy(d_b, &b, size, cudaMemcpyHostToDevice);        //Launch add() kernel on GPU     add<<<1,1>>>(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 0;}