From 876e70d4681332a600492173af0c7259e5a438c6 Mon Sep 17 00:00:00 2001 From: Richard Biener Date: Fri, 4 Feb 2022 09:26:57 +0100 Subject: [PATCH] tree-optimization/103641 - improve vect_synth_mult_by_constant The following happens to improve compile-time of the PR103641 testcase on aarch64 significantly. I did not investigate the effect on the generated code but at least in theory choose_mult_variant should do a better job when we tell it the actual mode we are going to use for the operations it synthesizes. 2022-02-04 Richard Biener PR tree-optimization/103641 * tree-vect-patterns.cc (vect_synth_mult_by_constant): Pass the vector mode to choose_mult_variant. --- gcc/tree-vect-patterns.cc | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc index bea0499..2baf974 100644 --- a/gcc/tree-vect-patterns.cc +++ b/gcc/tree-vect-patterns.cc @@ -3041,6 +3041,9 @@ vect_synth_mult_by_constant (vec_info *vinfo, tree op, tree val, bool cast_to_unsigned_p = !TYPE_OVERFLOW_WRAPS (itype); tree multtype = cast_to_unsigned_p ? unsigned_type_for (itype) : itype; + tree vectype = get_vectype_for_scalar_type (vinfo, multtype); + if (!vectype) + return NULL; /* Targets that don't support vector shifts but support vector additions can synthesize shifts that way. */ @@ -3050,16 +3053,13 @@ vect_synth_mult_by_constant (vec_info *vinfo, tree op, tree val, /* Use MAX_COST here as we don't want to limit the sequence on rtx costs. The vectorizer's benefit analysis will decide whether it's beneficial to do this. */ - bool possible = choose_mult_variant (mode, hwval, &alg, - &variant, MAX_COST); + bool possible = choose_mult_variant (VECTOR_MODE_P (TYPE_MODE (vectype)) + ? TYPE_MODE (vectype) : mode, + hwval, &alg, &variant, MAX_COST); if (!possible) return NULL; - tree vectype = get_vectype_for_scalar_type (vinfo, multtype); - - if (!vectype - || !target_supports_mult_synth_alg (&alg, variant, - vectype, synth_shift_p)) + if (!target_supports_mult_synth_alg (&alg, variant, vectype, synth_shift_p)) return NULL; tree accumulator; -- 2.7.4