In boost/mpi/collectives/reduce.hpp

The template function specialization for reduce-ing a std::vector, should probably be modified.

Ffrom

template<typename T, typename Op>

void

reduce(const communicator & comm, std::vector<T> const & in_values,

       std::vector<T> & out_values, Op op, int root)

{

  out_values.resize(in_values.size());

  reduce(comm, &in_values.front(), in_values.size(), &out_values.front(), op,

         root);

}

To

template<typename T, typename Op>

void

reduce(const communicator & comm, std::vector<T> const & in_values,

       std::vector<T> & out_values, Op op, int root)

{

  if( comm.rank() == root ) out_values.resize(in_values.size());

  reduce(comm, &in_values.front(), in_values.size(), &out_values.front(), op,

         root);

}

This will save an extraneous allocation on the non-root nodes.

-steve