User control over splitting granularity while parallel processing

[Georgiy Rakov]

Hello,

current public API seems to have no means allowing user to control the 
granularity of splitting sequences while parallel processing.
It seems to be useful because the computational complexity of supplied 
functors (predicates, blocks, ... , etc) is known by nobody but user 
who's created it.

I wonder whether such means are going to be introduced. And if they are 
not why?

Thank you, Georgiy.