Subj : Re: questions re: atomic<>
To   : comp.programming.threads
From : Joe Seigh
Date : Sat Jun 25 2005 01:15 pm

Chris Thomasson wrote:
>>>Oops.  Okay, this makes sense now.
>>>
>>
>>And don't forget the release memory barrier before the store into a
>>non null hazard pointer also.
> 
> 
> :) 
> 
> 
Those two memory barriers really slow things down.  On a ppc it's
102 nsec with them and 4 nsec without them. 

-- 
Joe Seigh

When you get lemons, you make lemonade.
When you get hardware, you make software.

.