[cpp-threads] memory model

[Alexander Terekhov]

On 4/28/05, Doug Lea <dl at cs.oswego.edu> wrote:
[...]
> That said, Alexander: I think most people are in favor of
> something close to your atomic templates. Could you
> write up and send to list a self-contained initial
> proposal for people to work on?

I do not know much about writing proposals: that is not my 
trade. 

Hoist and sink stuff is nothing but constituents of classic
acquire and release. As for cc and dd on hoist stuff, they 
are simply optimizations meant to take advantage of implied 
ordering due to data dependencies and conditional branching 
on existing hardware (e.g. cchsb is implied on all existing 
hardware and ddhsb/ddhlb/ddacq on everything except {RIP-}
Alpha AFAIK). See also:

http://www.google.de/groups?selm=4251896E.5D7F03D5%40web.de

regards,
alexander.