[rfc] coalesce stack slots
Vladimir Makarov
vmakarov@redhat.com
Wed Sep 8 19:04:00 GMT 2004
Richard Henderson wrote:
>On Tue, Sep 07, 2004 at 05:22:53PM -0400, Vladimir Makarov wrote:
>
>
>>This weekend I got some SPECINT results for your patch for P4. I've
>>checked -mtune=i386 and -march=i386/-mtune=pentium4. I am sorry,
>>Richard but in overall the score with the patch results in about 0.5%
>>slower code. I think freedom in insn scheduling (performed by P4) is
>>more important then better data locality for SPECINT.
>>
>>
>
>Any chance you could point me at the particular variables being combined
>in SPECINT that is causing the problem? I have trouble believing that
>many such variables exist.
>
>
>
Sorry, Richard. I have no idea where the problem occurs. It requires
big work to analyze that. IMHO, the best test for this is vortex
(becuase the biggest degradation -- about 2-3%). I don't remeber why but
I got a conclusion that vortex benchmark has a lot of parallelism.
Vlad
More information about the Gcc-patches
mailing list