[MPICH] MPI_REDUCE with MPI_IN_PLACE fails with memory error

[Rajeev Thakur]

> One more question:
> wouldn't it have been clearer for the MPI_IN_PLACE argument 
> to be placed
> in the rcvbuf on the root process? This would eliminate the need to do
> different calls on the root and "other" processes...?

MPI_IN_PLACE is very tricky. It's use is different in each collective
function, so one has to read the standard carefully. I have myself got
confused a few times. 

Rajeev