Subj : Re: CMPXCHG timing To : comp.programming.threads From : David Hopwood Date : Fri Apr 01 2005 09:53 pm Michael Pryhodko wrote: > No, this is a lock oriented only for x86. It could be easily adapted > for any other platfrom if it could provide necessary guarantees: [...] > - full store (i.e. store+sfence on x86) timing is predictable > - every processor runs at the same speed and can not be delayed/stopped These two assumptions don't hold for x86, and shouldn't be guaranteed to hold because they would prevent *many* important optimizations (really, not just theoretically). -- David Hopwood .