Subj : Re: [.NET] Volatile Fields [correction]
To   : comp.programming.threads
From : Alexander Terekhov
Date : Mon Sep 19 2005 09:40 pm

Cool Guy wrote:
> 
> David Hopwood <david.nospam.hopwood@blueyonder.co.uk> wrote:
> 
> > The write to Y is not performed as a single atomic event; it has to be modelled
> > as two events: "Y = 1 is performed with respect to processor 2" and "Y = 1 is
> > performed with respect to processor 3". So it can happen that processor 2 sees
> > Y == 1 before writing Z = 1, but processor 3 does not see Y == 1 until after
> > it sees Z == 1.
> 
> <snip>
> 
> So it's impossible to make such code thread-safe, then?

Illusion of remote write atomicity can be achieved by turning all reads
into dummy RMWs. The problem is that even Intel's own architects don't 
seem to know how to do a dummy RMW that would be guaranteed not to 
optimize out a write part (so to speak) of a dummy RMW on their 
existing and future PC (x86/WB) processors.

regards,
alexander.

.