Subj : Re: Memory visibility and MS Interlocked instructions
To   : comp.programming.threads
From : Joe Seigh
Date : Mon Aug 29 2005 11:26 pm

Chris Thomasson wrote:
> "Alexander Terekhov" <terekhov@web.de> wrote in message 
> news:4310C372.2225A81@web.de...
> 
>>Joe Seigh wrote:
>>[...]
>>
>>>just trying to save Intel from themselves.  It's not a
>>>correctness of implementation issue, it's a performance
>>
>>Under x86 memory model, all loads (including dependent ones) behave
>>in-order with respect to preceding loads. Processor can perform out-
>>of-order speculative loads but they never yield incorrect results
>>(processor detects memory ordering violations and rolls back).
> 
> 
> http://groups.google.com/group/comp.programming.threads/msg/68ba70e66d6b6ee9?hl=en
> 
> any thoughts? 
> 
> 
Acquire would be #LoadLoad+#LoadStore.  In order loads would just be #LoadLoad.
The speculative read thing is a red herring.  You can have speculative reads
in both an in-order and out-of-order memory model.

-- 
Joe Seigh

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

.