// matrix transpose, for_each version

#include <stdio.h>
#include <thrust/device_vector.h>

// functor; holds iterators for the input and output matrices, and each
// invocation of the function copies from one element from the former to
// the latter
struct copyelt2xp : public thrust::unary_function<int,void>
{
   int nrow;  
   int ncol;  
   const  thrust::device_vector<int>::iterator m;  // input matrix 
   const  thrust::device_vector<int>::iterator mxp;  // output matrix
   int *m1,*mxp1;
   copyelt2xp(thrust::device_vector<int>::iterator _m, 
            thrust::device_vector<int>::iterator _mxp, 
            int _nr, int _nc): 
      m(_m), mxp(_mxp), nrow(_nr), ncol(_nc) {
         m1 = thrust::raw_pointer_cast(&m[0]);
         mxp1 = thrust::raw_pointer_cast(&mxp[0]);
      }
   __device__
   void operator()(const int i)  
   // copies the i-th element of the input matrix to the output matrix
   {  // elt i in input is row r, col c there
      int r = i / ncol; int c = i % ncol;  
      // that elt will be row c and col r in output, which has nrow
      // cols, so copy as follows
      mxp1[c*nrow+r] = m1[r*ncol+c];
   }
};