use of incorrect initial value of variable
I've been seeing this recently on master with both kinds of MPI
Using 2 MPI threads Using 0 OpenMP thread per tMPI thread for PME
I suspect some of my refactoring broke it, but haven't looked into it
Fixed parallel distribution and thread count reporting
The domain decomposition no longer prints the atom count for all ranks
(which gets far too long at high parallelization), but rather av,
stddev, min and max.
Corrected the OpenMP thread count print, which often printed 0 thread
for (non-existent) PME ranks.
Fixes #1681, #1685.