In many parallel computer interconnects, some processors are closer to than others. These routines allow the MPI implementation to provide an ordering of processes in a topology that makes logical neighbors close in the physical interconnect.
127 Some parallel programmers may remember hypercubes and the effort that went into assigning nodes in a mesh to processors in a hypercube through the use of Grey codes. Many new systems have different interconnects; ones with multiple paths may have notions of near neighbors that changes with time. These routines free the programmer from many of these considerations. The reorder argument is used to request the best ordering.