Re: [Qemu-devel] /* XXX: suppress this hack */

[Laurent Amon]

On 31 oct. 04, at 12:31, Magnus Damm wrote:

> By comparing CVS today with and without AREG4-AREG11 we can see that 
> the
> /* XXX: suppress this hack */-change that Fabrice implemented gave us:
>
> Integer performance is +20%, Floating-point performance is -2%.
> ---------------------------------------------------------------
>
> Please take this with a grain of salt, I did only one test and cron
> might have kicked in during the tests...
>
> And yes, adding cpu-specific flags to gcc seems pointless.
I believe this need to be tested further. On the version I use (a CVS 
somewhat later that 0.6.0), and the regular gcc 3.3 on OSX 10.3.5 
(TiBook G4/400), I get more or less a consistent 8% speed increase  
with -mcpu=7400 using Sandra on Win98 guest. Unless the flag interferes 
with AREG4-AREG11, it should get better.

Lga.