mpi: add clock synchronization routines and benchmark

Add distributed clock synchronization routines.

@thibault @furmento @adenis can you please have a look on this MR, especially regarding the integration of the file mpi_sync_clocks.h:

• the typedef in starpu_mpi.h (maybe there is better solution than a typedef to a void* ?)
• the wrappers in starpu_mpi_sync_clocks.c: they are really basic wrappers, maybe we can make something cleaner/simpler with some #define ?