#include <iostream>
#include <vector>

int main()
{
  // shape, stride & data of the matrix

  size_t shape  [] = { 2, 3, 4, 5};
  size_t strides[] = {60,20, 5, 1};

  std::vector<double> data(2*3*4*5);

  for ( size_t i = 0 ; i < data.size() ; ++i ) data[i] = 1.;

  // shape, stride & data (zero-initialized) of the reduced matrix

  size_t rshape  [] = { 2, 4, 5};
  size_t rstrides[] = {20, 5, 1};

  std::vector<double> rdata(2*4*5, 0.0);

  // compute reduction

//   for ( size_t a = 0 ; a < shape[0] ; ++a )
//     for ( size_t c = 0 ; c < shape[2] ; ++c )
//       for ( size_t d = 0 ; d < shape[3] ; ++d )
//         for ( size_t b = 0 ; b < shape[1] ; ++b )
//           rdata[ a*rstrides[0]                 + c*rstrides[1] + d*rstrides[2] ] += \
//           data [ a*strides [0] + b*strides [1] + c*strides [2] + d*strides [3] ];

  size_t cmp_axis = 1, axis_count = sizeof shape/ sizeof *shape;
  std::vector<size_t> adjusted_strides;
  //adjusted strides is basically same as strides
  //only difference being that the first element is the 
  //total number of elements in the n dim array.

  //The only reason to introduce this array was
  //so that I don't have to write any if-elses
  adjusted_strides.push_back(shape[0]*strides[0]);
  adjusted_strides.insert(adjusted_strides.end(), strides, strides + axis_count);
  for(size_t i = 0; i < data.size(); ++i) {
    size_t ni = i/adjusted_strides[cmp_axis]*adjusted_strides[cmp_axis+1] + i%adjusted_strides[cmp_axis+1];
    rdata[ni] += data[i];
  }
  // print resulting reduced matrix

  for ( size_t a = 0 ; a < rshape[0] ; ++a )
    for ( size_t b = 0 ; b < rshape[1] ; ++b )
      for ( size_t c = 0 ; c < rshape[2] ; ++c )
        std::cout << "(" << a << "," << b << "," << c << ") " << \
        rdata[ a*rstrides[0] + b*rstrides[1] + c*rstrides[2] ] << std::endl;

  return 0;
}