问CUDA核函数未调用

EN

#include <stdio.h>

static const unsigned short N = 3;

// Kernel definition
__global__ void VecAdd(float* A, float* B, float* C)
{
    int i = threadIdx.x;
    C[i] = A[i] + B[i];
} 

int main()
{
  float *A, *B, *C;
  float a[N] = {1,2,3}, b[N] = {4,5,6}, c[N] = {0,0,0};

  cudaMalloc( (void **)&A, sizeof(float)*N );
  cudaMalloc( (void **)&B, sizeof(float)*N );
  cudaMalloc( (void **)&C, sizeof(float)*N );

  cudaMemcpy( A, a, sizeof(float)*N, cudaMemcpyHostToDevice );
  cudaMemcpy( B, b, sizeof(float)*N, cudaMemcpyHostToDevice );

  VecAdd<<<1, N>>>(A, B, C);

  cudaMemcpy( c, C, sizeof(float)*N, cudaMemcpyHostToDevice );

  printf("%f %f %f\n", c[0],c[1],c[2]);

  cudaFree(A);
  cudaFree(B);
  cudaFree(C);

  return 0;
}