The data processed by the loopfilter overlaps. At the block level, this
results in some redundant transforms. Grouping the filtering allows for
a single 16x16 transpose (and inversion) instead of three 16x8 transposes
(and three more inversions).

This implementation is x86_64 only. We retain the previous
implementation for x86.

Improvements are obviously material dependant, but it seems to be ~%1 in
tests here.

Change-Id: I467b7ec3655be98fb5f1a94b5d145e5e5a660007