CUDA初学，实现1000*256的数组运算

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include <iostream>
#define N 1000
#define M 256
float A[N][M],B[N][M],C[N][M];
__global__ void add(float *A,float *B,float *C){
	int i = blockIdx.x; 
	int j = threadIdx.x;
	int id = i*256+j;
		C[id]=A[id]+B[id];
}
int main()
{
	 int size = M*N*sizeof(float);
	 for(int i=0;i<N;i++)
		 for(int j=0;j<M;j++)
		 {
	 A[i][j]=i;B[i][j]=j;
	 }
	 float *d_a;
	 float *d_b;
	 float *d_c;
	 cudaMalloc((void**)&d_a,size);
	 cudaMalloc((void**)&d_b,size);
	 cudaMalloc((void**)&d_c,size);
	 cudaMemcpy(d_a,A,size,cudaMemcpyHostToDevice);
	 cudaMemcpy(d_b,B,size,cudaMemcpyHostToDevice);
	 add<<<N,M>>>(d_a,d_b,d_c);
	 cudaMemcpy(C,d_c,size,cudaMemcpyDeviceToHost);
	 cudaFree(d_a);
	 cudaFree(d_b);
	 cudaFree(d_c);
	 for(int i=0;i<N;i++)
	    for(int j = 0;j<M;j++)
	 {
	 std::cout<<C[i][j]<<" ";
	 }
	 int m;
	 std::cin>>m;
}