AxoyTO

#include <cuda.h>
#include <chrono>
#include <cstdlib>
#include <iostream>

__global__ void addVectorsKernel(const double* A, const double* B, double* C, double n) {
  int i = blockDim.x * blockIdx.x + threadIdx.x;
  if (i < n) {
    C[i] = A[i] + B[i];
  }