This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: stepanov on i686-pc-linux-gnu
- To: rth at redhat dot com (Richard Henderson)
- Subject: Re: stepanov on i686-pc-linux-gnu
- From: Joe Buck <jbuck at racerx dot synopsys dot com>
- Date: Sun, 27 May 2001 19:38:09 -0700 (PDT)
- Cc: jbuck at synopsys dot COM (Joe Buck), gcc at gcc dot gnu dot org
> On Fri, May 25, 2001 at 06:24:39PM -0700, Joe Buck wrote:
> > .L262:
> > faddl (%eax)
> > leal 8(%eax), %edx
> > cmpl %ecx, %edx
> > movl %edx, %eax
> > jne .L262
> > movl %edx, 8(%ebp)
> >
> > Ouch! The iterator is being retrieved and stored to memory.
>
> Well, sorta. That last move is outside the loop.
Sigh. I'm so used to looking at Sparc assembly with the delayed
branch.
Nevertheless, there are two memory accesses in the loop, and only
one is needed. In principle, all the Stepanov tests should generate
equivalently fast code.