More on memory barriers

[Richard Henderson]

On Wed, Sep 15, 2004 at 08:53:11AM -0400, Paul Koning wrote:
>  Richard> We do still need a write_memory_barrier here.  For that,
>  Richard> __sync_synchronize is still the best implementation
>  Richard> available.
> 
> For which processor?

If you'd clipped less, you'd have seen it was specifically ia64.


r~