我最近开始了CUDA编程。 我遵循了有关它的教程和指南，并制作了第一个程序从最初的例子复制（这里第25页），它基本上使用GPU添加两个向量。 我可以编译它，但是我得到的结果不是我期望的结果。

下面是我的代码:

#include <iostream>
#include <random>

using namespace std;

//Size of vector
#define N 16


//Kernel for adding vector
__global__ void add(int* a, int* b, int* c){
  c[blockIdx.x] = a[blockIdx.x] + b[blockIdx.x];
}


//Functions
void printArray(int* a){
  cout << "[ ";
  for(int i = 0; i < N; i++){
    cout << *(a+i) << " ";
  } cout << "]" << endl;
}

void fillRandomValue(int* a, int size, int range){
  for(int i = 0; i < size; i++){
    *(a+i) = rand() % range;
  }
}


int main(void){
  //Declaration of vector for host and device : a for host ; d_a for device a ;
  int* a,* b,* c;
  int* d_a,* d_b,*d_c;
  int size = N * sizeof(int);

  //Allocate memory into the device
  cudaMalloc((void** )&d_a, size);
  cudaMalloc((void** )&d_b, size);
  cudaMalloc((void** )&d_c, size);

  //Declaring 3 array
  a = new int[size];
  b = new int[size];
  c = new int[size];

  //Randomn array
  //Initialize randomn seed
  srand (time(NULL));
  fillRandomValue(a, N, 10);
  fillRandomValue(b, N, 10);

  //Copy host to device
  cudaMemcpy(d_a, &a, size, cudaMemcpyHostToDevice);
  cudaMemcpy(d_b, &b, size, cudaMemcpyHostToDevice);

  //Adding vector
  add<<<N,1>>>(d_a, d_b, d_c);

  //Get back the result
  cudaMemcpy(c, d_c, size, cudaMemcpyDeviceToHost);

  //Output to console
  cout << "a = "; printArray(a); cout << endl;
  cout << "b = "; printArray(b); cout << endl;
  cout << "a + b = "; printArray(c); cout << endl;

  //Free memory
  free(a); free(b); free(c);
  cudaFree(d_a); cudaFree(d_b); cudaFree(d_c);

  return 0;

}

问题是我得到了以下结果:

a = [ 5 5 7 2 9 5 3 5 4 5 2 9 6 7 4 9 ]

b = [ 9 6 9 8 9 7 5 6 6 6 2 8 7 3 1 2 ]

a + b = [ -971240544 44196 -2117203120 54617 1031799296 65038 1031800320 65038 -2117199280 54617 -1009853744 44196 -1048817168 44196 -1307968288 54865 ]

我可以想多多地再现这种行为。