This moves all the CUBE section above the gradients section,
so that the gradient emission happens on one block which
is what sb/hardware expect.

v2: avoid changes to bytecode by using spare temps
v2.1: shame gcc, oh the shame. (uninit var warnings)

Cc: "10.4 10.3" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Glenn Kennard <glenn.kennard@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
(cherry picked from commit c8838560)