On Thu, May 24, 2018 at 10:31 AM Jakub Jelinek <ja...@redhat.com> wrote:
> On Thu, May 24, 2018 at 09:21:35AM +0100, Richard Sandiford wrote:
> > vect_recog_divmod_pattern currently bails out if the target has
> > native support for integer division, but I think in practice
> > it's always going to be better to open-code it anyway, just as
> > we usually open-code scalar divisions by constants.
> >
> > I think the only currently affected target is MIPS MSA, where for:
> Isn't powerpcspe affected too? It has a divv2si3 pattern.
> > --- gcc/tree-vect-patterns.c 2018-05-16 12:48:59.115202362 +0100
> > +++ gcc/tree-vect-patterns.c 2018-05-24 09:18:10.445466941 +0100
> > @@ -2639,7 +2639,6 @@ vect_recog_divmod_pattern (vec<gimple *>
> > enum tree_code rhs_code;
> > stmt_vec_info stmt_vinfo = vinfo_for_stmt (last_stmt);
> > vec_info *vinfo = stmt_vinfo->vinfo;
> > - optab optab;
> > tree q;
> > int dummy_int, prec;
> > stmt_vec_info def_stmt_vinfo;
> > @@ -2674,17 +2673,6 @@ vect_recog_divmod_pattern (vec<gimple *>
> > if (vectype == NULL_TREE)
> > return NULL;
> >
> > - /* If the target can handle vectorized division or modulo natively,
> > - don't attempt to optimize this. */
> > - optab = optab_for_tree_code (rhs_code, vectype, optab_default);
> > - if (optab != unknown_optab)
> > - {
> > - machine_mode vec_mode = TYPE_MODE (vectype);
> > - int icode = (int) optab_handler (optab, vec_mode);
> > - if (icode != CODE_FOR_nothing)
> > - return NULL;
> > - }
> > -
> Shouldn't we instead keep it, but only do it if
> optimize_bb_for_size_p (gimple_bb (last_stmt)) ?
> I mean, a hw division is very likely shorter than what we replace it
with...
Good idea. While loops are checked for optimize_loop_nest_for_speed if
not forced vect BB vectorization has no such predicate.
Richard.
> Jakub
