On Fri, Jan 18, 2008 at 08:56:43AM -0500, H. Peter Anvin wrote:
quoted text
> Andi Kleen wrote:
> >>Simulators can be fixed, 
> >
> >They could, but why? I don't know of a good reason to require CLFLUSH.
> 
> Well, simulators are generally expected to follow the architecture, not 
> vice versa.  I would tend to agree with the coupling that recent 
> versions of Bochs appeared to have made here -- I think we're unlikely 
> to see any processors with sse2 sans clflush, so keeping code branches 
> in which will never be executed seems like a bad idea in the long term. 

Here's another argument: Ingo just asked me to add a noclflush option
to the code. Guess what check that option will need? 

Besides compared to the cost of a flushing clflush the branches are absolutely 
in the noise.

-Andi
--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/