------- Comment #5 from rguenth at gcc dot gnu dot org 2010-04-26 14:43 -------
(In reply to comment #4)
> Subject: Re: PowerPC suboptimal "add with carry" optimization
>
> "dje at gcc dot gnu dot org" <gcc-bugzi...@gcc.gnu.org> wrote on 2010/04/26
> 15:53:01:
> >
> > ------- Comment #3 from dje at gcc dot gnu dot org 2010-04-26 13:52 -------
> > As Jakub mentioned, i386.md implements the addcc named pattern and rs6000.md
> > does not provide that named pattern yet.
>
> Will that also address the loop optimization? I don't think so.
No.
Actually compilable testcase:
typedef unsigned int u32;
u32
add32carry(u32 sum, u32 x)
{
u32 z = sum + x;
if (sum + x < x)
z++;
return z;
}
u32
loop(u32 *buf, int len)
{
u32 sum = 0;
for(; len; --len)
sum = add32carry(sum, *++buf);
return sum;
}
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=43892
