Re: rep movsb vs. simpler instructions for memcpy/memmove

The REP MOV straddles the boundary between two MTRRs.

Why/when would this happen in practice?

Nobody said it was a good idea.

But if it doesn't happen in normal cases, then it shouldn't be
significant to performance.  So is the problem that just detecting the
occurrence of this situation is already too costly to make `rep
movsb` fast?

[ Of course, I still haven't understood either why it technically can
  happen in amd64 but not in My 66000.  ]


        Stefan