Subj : Re: Memory Barriers, Compiler Optimizations, etc.
To   : comp.programming.threads
From : Alexander Terekhov
Date : Mon Feb 07 2005 01:57 pm


Joseph Seigh wrote:
> 
> On Mon, 07 Feb 2005 12:13:10 +0100, Alexander Terekhov <terekhov@web.de> wrote:
> 
> >
> > "Neill Clift [MSFT]" wrote:
> > [...]
> 
> >> I believe we do have a full barrier
> >
> > I believe that barrier makes little sense in the case of
> > comparison failure.
> >
> What are you saying?  That failed compare and swaps shouldn't
> have memory barrier semantics?

Yes (actually "unspecified"). Just like with failed 
pthread_mutex_trylock(). See XBD 4.10. "Unless explicitly stated 
otherwise, if one of the above functions returns an error, it is 
unspecified whether the invocation causes memory to be 
synchronized."

regards,
alexander.

.