sync operations: where's the barrier?

[Richard Henderson]

On Mon, Apr 18, 2005 at 02:48:27PM -0700, Geoffrey Keating wrote:
> The documentation for the atomic operation patterns says things like:
> 
> >This pattern must issue any memory barrier instructions such that the
> >pattern as a whole acts as a full barrier.
> 
> Should the barrier happen before the operation, after the operation, 
> are there two barriers, or is it undefined?

Two barriers.


r~