#include <mpi.h>
#include <hpc/matvec/gematrix.hpp>
#include <hpc/matvec/iterators.hpp>
#include <hpc/matvec/print.hpp>
#include <hpc/mpi/matrix.hpp>

int main(int argc, char** argv) {
   MPI_Init(&argc, &argv);

   int nof_processes; MPI_Comm_size(MPI_COMM_WORLD, &nof_processes);
   int rank; MPI_Comm_rank(MPI_COMM_WORLD, &rank);

   using namespace hpc::matvec;
   using namespace hpc::mpi;
   using namespace hpc::aux;

   using Matrix = GeMatrix<double>;
   int share = 3;
   int num_rows = nof_processes * share + 1;
   int num_cols = 5;

   Matrix A(num_rows, num_cols); /* entire matrix */
   MPI_Datatype rowtype_A = get_row_type(A);

   UniformSlices<int> slices(nof_processes, num_rows);
   Matrix B(slices.size(rank), num_cols,
      Order::RowMajor); /* individual share */
   MPI_Datatype rowtype_B = get_row_type(B);

   if (rank == 0) {
      for (auto [i, j, Aij]: A) {
	 Aij = i * 100 + j;
      }
   }

   scatter_by_row(A, B, 0, MPI_COMM_WORLD);
   for (auto [i, j, Bij]: B) {
      Bij += 10000 * (rank + 1);
      (void) i; (void) j; // suppress gcc warning
   }
   gather_by_row(B, A, 0, MPI_COMM_WORLD);

   MPI_Finalize();

   if (rank == 0) {
      print(A, " %6g");
   }
}