Subj : Re: Memory visibility and MS Interlocked instructions
To   : comp.programming.threads
From : Alexander Terekhov
Date : Fri Aug 26 2005 07:04 pm


Joe Seigh wrote:
[...]
> One issue you seem to be touching upon is whether memory accesses have to
> complete before some instruction "executes", or not initiate until after
> some instruction "executes".  

It only seems that way to you. Actually, it's about "touching" shared 
memory (performing accesses that yield observable results stored/loaded 
to/from shared memory), not initiation or completion of instructions 
(whatever that means).

regards,
alexander.

.