Induction variable elimination, was: Re: On the x86_64, does one have to zero a vector register before filling it completely ?

[Toon Moene <toon at moene dot org>]

Toon Moene wrote:

> I wrote:

> > OK, so it is an alignment issue (with -mtune=barcelona):
> >
> > .L6:
> >         movups  0(%rbp,%rax), %xmm0
> >         movups  (%rbx,%rax), %xmm1
> >         incl    %ecx
> >         addps   %xmm1, %xmm0
> >         movaps  %xmm0, (%r8,%rax)
> >         addq    $16, %rax
> >         cmpl    %r10d, %ecx
> >         jb      .L6
>
> Once this problem is solved (well, determined how it could be solved), 
> we go on to the next, the extraneous induction variable %ecx.
>
> There are two ways to deal with it:
>
> 1. Eliminate it with respect to the other induction variable that
>    counts in the same direction (upwards, with steps 16) and remember
>    that induction variable's (%rax) limit.

Just for completeness - gcc *does* know how to do this; it just doesn't 
work when vectorizing.

This is what I get when compiling with -O2 -S:

.L3:
        movss   (%rdi,%rax), %xmm0
        addss   (%rsi,%rax), %xmm0
        movss   %xmm0, (%rdx,%rax)
        addq    $4, %rax
        cmpq    %rcx, %rax
        jne     .L3

Note how %rax remains as sole induction variable.

--
Toon Moene - e-mail: toon@moene.org - phone: +31 346 214290
Saturnushof 14, 3738 XG  Maartensdijk, The Netherlands
At home: http://moene.org/~toon/
Progress of GNU Fortran: http://gcc.gnu.org/gcc-4.5/changes.html