问cuda中矢量加法的故障分割

EN

#include <iostream>
using namespace std;

__global__ void kern(float *a, float *C){
    for (int i = 0; i < 3; i++) C[i] = a[i] + i;
}

int main(){
    float *A = new float[3];
    for(int i = 0; i < 3; i++){
        A[i] = i;
    }

    float * d;
    float * C;
    cudaMalloc(&C, sizeof(float)*3);
    cudaMalloc(&d, sizeof(float)*3);
    cudaMemcpy(&d, A, sizeof(float)*3, cudaMemcpyHostToDevice);
    kern<<<1, 1>>>(d, C);

    cudaMemcpy(&A, C, sizeof(float)*3, cudaMemcpyDeviceToHost);

    cout << A[2];

}