Re: [boost] [lockfree] review

Subject: Re: [boost] [lockfree] review
From: Alexander Terekhov (terekhov_at_[hidden])
Date: 2011-08-25 09:21:42

Gottlob Frege wrote:
> 
> On Thu, Aug 25, 2011 at 12:13 AM, Stephan T. Lavavej
> <stl_at_[hidden]> wrote:
> > [Gottlob Frege]
> >> 1. I wish that C++11 atomics defaulted to acquire-on-read and
> >> release-on-write, and that's how I will almost always use them.  It is
> >> also what java and C# use, I believe (on volatiles).
> >
> > That doesn't solve the "independent reads, independent writes" 
> > problem, which is why the non-Standard semantics that VC8 gave 
> > volatile aren't really useful. (volatile: a multithreaded 
> > programmer's worst enemy.)
> >
> 
> What's the "independent reads, independent writes" problem?  I've
> probably heard, seen, or mistakenly had a bug due to it once, but
> don't know it by name.
> 
> > The Standard's focus on sequential consistency by default was 
> > carefully thought out.
> 
> I find that most lockfree development uses acquire/release, not SC, so

Note also that according to 

http://msdn.microsoft.com/en-us/library/ms235435(v=vs.90).aspx
(Supported Platforms (Visual C++))

VC8 targets only x86/x64 and Itanium.

After Intel clarified x86/x64 MM back in 2008, we know that x86/x64 MM
is basically TSO, that is, acquire/release + remote write atomicity.

Itanium MM explicitly defines WB release stores to have remote write
atomicity.

http://download.intel.com/design/itanium/downloads/25142901.pdf
(3.3.7.1 Total Ordering of WB Releases)

So IRIW is not really a problem for VC8 acquire/release because on VC8
supported platforms remote write atomicity is guaranteed for
acquire/release.

regards,
alexander.