Dummy cuda load

hello.cu

#include "stdio.h"

__global__ void cuda_hello() {
  printf("Hello World from GPU!\n");
}

#define N 1000000000

__global__ void vector_add(float *out, float *a, float *b, int n) {
  for (int i = 0; i < n; i++) {
    out[i] = a[i] + b[i];
  }
}

int main() {
  cuda_hello<<<1,1>>>();

  float *a, *b, *out;
  cudaMalloc((void**)&a, sizeof(float) * N);
  cudaMalloc((void**)&b, sizeof(float) * N);
  cudaMalloc((void**)&out, sizeof(float) * N);

  for (int i = 0; i < 100; i++)
    vector_add<<<1,1>>>(out, a, b, N);

  cudaError_t cudaerr = cudaDeviceSynchronize();
  if (cudaerr != cudaSuccess)
    printf("kernel launch failed with error \"%s\".\n",
           cudaGetErrorString(cudaerr));

  cudaFree(out);
  cudaFree(b);
  cudaFree(a);
  return 0;
}