[cpp-threads] Memory model counterproposal:synchronization operations

Nelson, Clark clark.nelson at intel.com
Thu May 26 19:30:14 BST 2005


> > It is well that it is already acknowledged (as measured by the
> > introduction of __async) that a simple access to a volatile 
> object can
> > not be made into a synchronization operation (syncop), as 
> Intel would
> > have to firmly oppose such a proposal.
> 
> Can you explain what you mean by "syncop"?

Sorry, I tried to make that clear: it's just an abbreviation for
synchronization operation. (Maybe I should have tried s15n o9n instead.
:-)

Clark




More information about the cpp-threads mailing list