amd64: move memcmp checks upfront

This is a tradeoff which saves jumps for smaller sizes while making
the 8-16 range slower (roughly in line with the other cases).

Tested with glibc test suite.

For example size 3 (most common with vfs namecache) (ops/s):
before: 407086026
after: 461391995

The regressed range of 8-16 (with 8 as example):
before: 540850489
after: 461671032

(cherry picked from commit f1be262ec11c1c35e6485f432415b5b52adb505d)