Re: [PATCH-1v2, rs6000] Enable SImode in FP registers on P7 [PR88558]

["Kewen.Lin" <linkw@linux.ibm.com>]

Hi Haochen,

on 2023/9/14 16:35, HAO CHEN GUI wrote:
> Hi Kewen,
> 
> 在 2023/9/12 17:33, Kewen.Lin 写道:
>> Ok, at least regression testing doesn't expose any needs to do disparaging
>> for this.  Could you also test this patch with SPEC2017 for P7 and P8
>> separately at options like -O2 or -O3, to see if there is any assembly
>> change, and if yes filtering out some typical to check it's expected or
>> not?  I think it can help us to better evaluate the impact.  Thanks!
> 
> Just compared the object files of SPEC2017 for P7 and P8. There is no
> difference between P7s'. For P8, some different object files are found.
> All differences are the same. Patched object files replace xxlor with fmr.
> It's expected as the fmr is added to ahead of xxlor in "*movsi_internal1".

Thanks for checking!  So for P7, this patch looks neutral, but for P8 and
later, it may cause some few differences in code gen.  I'm curious that how
many total object files and different object files were checked and found
on P8?  fmr or xxlor preference can be further considered along with existing:
https://gcc.gnu.org/pipermail/gcc-patches/2023-February/612821.html
I also wonder if it's easy to reduce some of them further as small test cases.

Since xxlor is better than fmr at least on Power10, could you also evaluate
the affected bmks on P10 (even P8/P9) to ensure no performance degradation?

Thanks!

BR,
Kewen