[AArch64] Don't generate st2 for 64bit store that can use stp (#69901)

D142966 made it so that st2 that do not start at element 0 use zip2
instead of st2. This extends that to any 64bit store that has a nearby
load that can better become a LDP operation, which is expected to have a
higher throughput. It searches up to 20 instructions away for a store to
p+16 or p-16.