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...
Jakub
