#include <mpi.h>
#include <hpc/mpi/matrix.hpp>
#include <hpc/matvec/gematrix.hpp>
#include <hpc/matvec/iterators.hpp>
#include <hpc/matvec/print.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 Matrix = GeMatrix<double>;
   int share = 3;
   int num_rows = nof_processes * share;
   int num_cols = 5;

   Matrix B(share, num_cols, Order::RowMajor); /* individual share */

   if (rank == 0) {
      Matrix A(num_rows, num_cols); /* entire matrix */
      for (auto [i, j, Aij]: A) {
	 Aij = i * 100 + j;
      }

      /* using MPI_Scatter: scatter A / receive our share into B */

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

      /* using MPI_Gather: gather into A / send our share from B */

      print(A, " %6g");
   } else {

      /* using MPI_Scatter: receive our share into B */

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

      /* using MPI_Gather: send our share from B */
   }
   MPI_Finalize();
}