[concurrency-interest] question the about the JMM
larryr at saturn.sdsu.edu
Wed Dec 5 19:21:20 EST 2007
> [...] your next paragraph illustrates exactly what's wrong
> with this mental model, and that is, there is almost
> always that hidden assumption of sequential consistency.
> "Before" and "after" simply have no meaning under the JMM
> except as defined by happens-before.
I am inclined to expect any intuitive model based on
the JMM, with a local clock and "happens-before", will
be homomorphic to a graph for a model based on a global
clock and local caches (using a typical cache coherence
protocol), with meaningful and well-defined "before" and
"after". But I would rather not try to prove it. (-:
More information about the Concurrency-interest