Subj : Re: Memory Barriers, Compiler Optimizations, etc.
To   : comp.programming.threads
From : Joseph Seigh
Date : Mon Feb 07 2005 08:22 am

On Mon, 07 Feb 2005 13:57:23 +0100, Alexander Terekhov <terekhov@web.de> wrote:

>
> 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."
>
I'm aware of having failed CAS logic in singleton, DCL, etc... logic.
I'm not sure where trylock fits in.

-- 
Joe Seigh

.