Modified the splitting rule for self tasks to be less conservative. Added proper documentation of the splitting conditions.

Add new function to decide on recursion with in a sub_pair task. Makes sure all recursion tests are identical.

Completes d8025de1

Use dx_max_sort_old and not dx_max_sort when checking whether cells have been sorted in DOPAIR1_BRANCH()

Created a branching function for DOPAIR1, so that the scalar version is called if it is a corner interaction when the code is vectorised. Also fixed a bug with runner_dopair1_density_vec so that hi_max and hj_max are used to find how many particles to read into the cache.

Add a separate timer for subset sub-cell tasks. Write the timers to a file. Make sure we can compile without timers. Add a configure option to switch the timers on.

Don't lock the tree for the grav_init task. Don't call the unsorted pairs at all. Skip the entire zeroing loop when no xparts in runner_do_sort()

sort and drift on-demand in a consistent way. yes, even for the force loops as changes in the smoothing lengths may require a re-sort or interactions at a different level.