[PATCH] aarch64: optimize the unaligned case of memcmp

[Wilco Dijkstra]

This looks like a good improvement - I think unlike memchr we can read
up to the number of bytes specified, so no special page checks are needed.

Huge memcmp's are very rare, so like most string functions the small case
is more important than the large case. So I think you could just skip the complex
alignment code and get better results in real applications. Btw why do the max
alignment thing? - that's a lot of code for very little benefit...

Wilco