Re: [PATCH] Optimize nested permutation to single VEC_PERM_EXPR [PR54346]

[Richard Biener <richard.guenther@gmail.com>]

On Fri, Oct 14, 2022 at 3:49 AM Lulu Cheng <chenglulu@loongson.cn> wrote:
>
>
> 在 2022/10/13 下午7:10, Richard Biener 写道:
> > On Thu, Oct 13, 2022 at 10:16 AM Lulu Cheng <chenglulu@loongson.cn> wrote:
> >>
> >> 在 2022/10/13 下午2:44, Xi Ruoyao 写道:
> >>> On Thu, 2022-10-13 at 14:15 +0800, Levy wrote:
> >>>> Hi RuoYao
> >>>>
> >>>> It’s probably because loongarch64 doesn’t support
> >>>> can_vec_perm_const_p(result_mode, op_mode, sel2, false)
> >>>>
> >>>> I’m not sure whether if loongarch will support it or should I just
> >>>> limit the test target for pr54346.c?
> >>> I'm not sure if we can add TARGET_VECTORIZE_VEC_PERM_CONST when we don't
> >>> actually support vector.  (LoongArch has SIMD instructions but the
> >>> support in GCC won't be added in a very recent future.)
> >>>
> >> If what I understand is correct, I think this might be a better solution.
> >>
> >>    /* { dg-do compile } */
> >>
> >> +/* { dg-require-effective-target vect_perm } */
> >>    /* { dg-options "-O -fdump-tree-dse1" } */
> > Btw, what forwprop does is check whether any of the original permutations are
> > not supported and then elide the supportability check for the result.
> > The reasoning
> > is that the original permute(s) would be lowered during vectlower so we can as
> > well do that for the result.  We should just never turn a supported permutation
> > sequence into a not supported one.
> >
> > Richard.
> >
> Hi Richard:
>
> I'm very sorry. I don't fully understand what you mean.
>
> Could you give me some more details?

The argument is that if Loongarch64 doesn't support the VEC_PERM_EXPR in the IL
before the transform then it doesn't matter if the transform introduces another
VEC_PERM_EXPR that isn't supported.  Both are later (in the veclower pass)
lowered to scalar operations.

So instead of

  if (can_vec_perm_const_p (result_mode, op_mode, sel2, false))
   ..

you'd do

  if (can_vec_perm_const_p (result_mode, op_mode, sel2, false)
      || !can_vec_perm_const_p ( ... original vec_perm1 ...)
      || !can_vec_perm_const_p ( ... original vec_perm2 ...))

Richard.

>
> Thanks!
>
> Lulu Cheng
>
>