[patch] tuning gcc for Intel Core2

H. J. Lu hjl@lucon.org
Thu Nov 16 01:58:00 GMT 2006


On Wed, Nov 15, 2006 at 05:49:13PM -0500, Vladimir Makarov wrote:
> H. J. Lu wrote:
> 
> >On Tue, Nov 14, 2006 at 07:49:56AM -0800, H. J. Lu wrote:
> > 
> >
> >>Can you turn on x86_rep_movl_optimal for -mtune=generic to see what
> >>it does for SPEC CPU 2K on both 32bit and 64bit?
> >>
> >>   
> >>
> >
> >
> >So for 64bit, -O2 + x86_rep_movl_optimal is better than -O2 and
> >-O2 -mtune=core2 on Core 2 Duo and Nocona. I suspect that we will
> >see similar trend on Opteron.
> >
> > 
> >
> I've got about the same numbers for generic + x86_rep_movl_optimal. 
> Although with -m32 generic + x86_rep_movl_optimal is a bit worse than 
> -mtune=core2 (1836 vs 1841 for SPECINT and 1477 vs 1484 for SPECFP).  It 
> is in the range of measurement error.  But again code size is smaller 
> (0.73% and 0.66% correspondingly for SPECInt and SPECFp).

That is expected. 32bit memory functions aren't as bad as 64bit. Now,
the question is if we should turn on x86_rep_movl_optimal for
m_GENERIC64. I will investigate it on SPEC CPU 2000/2006 with optimized
memory functions.


H.J.



More information about the Gcc-patches mailing list