将并行线程块修改为使用并行线程时的矢量相加

#include <cuda_runtime_api.h>
#include <iostream>
using namespace std;

const int N = 10 ;
__global__ void add(int *a , int *b , int *c)
{
int tid = threadIdx.x ;//通过线程索引来对数据进行索引
if (tid < N)
{
c[tid] = a[tid] + b[tid] ;
}
}
void main()
{
int a
, b
, c
;
int *dev_a , *dev_b , *dev_c ;

//在GPU上分配内存

cudaMalloc((void**)(&dev_a) , sizeof(int) * N) ;
cudaMalloc((void**)(&dev_b) , sizeof(int) * N) ;
cudaMalloc((void**)(&dev_c) , sizeof(int) * N) ;

for (int i = 0 ; i < N ; i++)
{
a[i] = i ;
b[i] = i * i ;
}

//将a,b复制到GPU
cudaMemcpy(dev_a , a , sizeof(int) * N , cudaMemcpyHostToDevice) ;
cudaMemcpy(dev_b , b , sizeof(int) * N , cudaMemcpyHostToDevice) ;
cudaMemcpy(dev_c , c , sizeof(int) * N , cudaMemcpyHostToDevice) ;

add<<<1 , N>>>(dev_a , dev_b , dev_c) ;//只有一个线程块

//将c从GPU复制到cpu
cudaMemcpy(c , dev_c , N * sizeof(int) , cudaMemcpyDeviceToHost) ;
for(int i = 0 ; i < N ; i++)
{
cout<<"a["<<i<<"]"<<" + b["<<i<<"] = "<<c[i]<<"\n";
}
cudaFree(dev_a) ;
cudaFree(dev_b) ;
cudaFree(dev_c) ;

return ;
}