Subj : Re: questions re: atomic<>
To   : comp.programming.threads
From : Alexander Terekhov
Date : Fri Jun 24 2005 10:35 pm


Sean Kelly wrote:
[...]
> will be refreshed, etc.  This all seemed to make sense until the more
> recent addition of msync::slfence, as I can't envision an algorithm

Hazard pointers, for example.

> where I'd want to prevent a processor from reordering its stores below
> its loads, or vice-versa (since a processor cache is always consistent

Forget cache.

> with itself).  I can only conclude that this particular mechanism means
> "wait for pending writes from ALL processors to complete before
> beginning the following reads," so I'm wondering about my original

No. Only local pending writes.

regards,
alexander.

.