dumb cuda + Boost::Python example

compile.sh

nvcc -arch sm_61 -O3 -L/usr/local/lib -lboost_python -I/usr/include/python2.7/ -Xcompiler -fPIC --shared test_python.cu -o test_python.so 

gistfile1.txt

$ python
Python 2.7.12 (default, Nov 19 2016, 06:48:10) 
[GCC 5.4.0 20160609] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import test_python
>>> test_python.test_saxpy()
Max error: 0.000000
0
>>> 

test_python.cu

#include <stdio.h>
#include <boost/python.hpp>

__global__
void saxpy(int n, float a, float *x, float *y)
{
  int i = blockIdx.x*blockDim.x + threadIdx.x;
  if (i < n) y[i] = a*x[i] + y[i];
}

int test_saxpy(void)
{
  int N = 1<<20;
  float *x, *y, *d_x, *d_y;
  x = (float*)malloc(N*sizeof(float));
  y = (float*)malloc(N*sizeof(float));

  cudaMalloc(&d_x, N*sizeof(float)); 
  cudaMalloc(&d_y, N*sizeof(float));

  for (int i = 0; i < N; i++) {
    x[i] = 1.0f;
    y[i] = 2.0f;
  }

  cudaMemcpy(d_x, x, N*sizeof(float), cudaMemcpyHostToDevice);
  cudaMemcpy(d_y, y, N*sizeof(float), cudaMemcpyHostToDevice);

  // Perform SAXPY on 1M elements
  saxpy<<<(N+255)/256, 256>>>(N, 2.0f, d_x, d_y);

  cudaMemcpy(y, d_y, N*sizeof(float), cudaMemcpyDeviceToHost);

  float maxError = 0.0f;
  for (int i = 0; i < N; i++)
    maxError = max(maxError, abs(y[i]-4.0f));
  printf("Max error: %f\n", maxError);

  cudaFree(d_x);
  cudaFree(d_y);
  free(x);
  free(y);

  return 0;
}

BOOST_PYTHON_MODULE(test_python)
{
    using namespace boost::python;
    def("test_saxpy", test_saxpy);
}