Revert r30539 and r30540; using the sqrt() to limit the computation is

just plain wrong (i.e., it gives wrong answers).  

When time permits, perhaps we can put in a better algorithm for
MPI_DIMS_CREATE (Andreas Schäfer mentioned that nnodes can now be on
the order of millions, and the current algorithm is... inefficient, at
best).

This commit was SVN r30606.

The following SVN revision numbers were found above:
  r30539 --> open-mpi/ompi@fb67d98867
  r30540 --> open-mpi/ompi@4417ed2133

ompi/mpi/c/dims_create.c

@@ -11,7 +11,6 @@
  *                         All rights reserved.
  * Copyright (c) 2012      Los Alamos National Security, LLC.  All rights
  *                         reserved. 
- * Copyright (c) 2014 Cisco Systems, Inc.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -21,8 +20,6 @@
 
 #include "ompi_config.h"
 
-#include <math.h>
-
 #include "ompi/mpi/c/bindings.h"
 #include "ompi/runtime/params.h"
 #include "ompi/communicator/communicator.h"
@@ -112,7 +109,7 @@ int MPI_Dims_create(int nnodes, int ndims, int dims[])
     }
 
     /* Compute the relevant prime numbers for factoring */
-    if (MPI_SUCCESS != (err = getprimes(sqrt(freeprocs), &nprimes, &primes))) {
+    if (MPI_SUCCESS != (err = getprimes(freeprocs, &nprimes, &primes))) {
        return OMPI_ERRHANDLER_INVOKE(MPI_COMM_WORLD, err,
                                      FUNC_NAME);
     }