From d439b8a5ad0af8ae6b5e0086eed4eebc160fa9aa Mon Sep 17 00:00:00 2001 From: Eugene Rozenfeld Date: Tue, 26 Apr 2022 14:28:16 -0700 Subject: [PATCH] Fix profile count maintenance in vectorizer peeling. This patch changes the code to save/restore profile counts for the epliog loop (when not using scalar loop in the epilog) instead of scaling them down and then back up, which may lead to problems if we scale down to 0. Tested on x86_64-pc-linux-gnu. gcc/ChangeLog: * tree-loop-vect-manip.cc (vect_do_peeling): Save/restore profile counts for the epilog loop. --- gcc/tree-vect-loop-manip.cc | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc index a7bbc916bbc..501a6ab99f0 100644 --- a/gcc/tree-vect-loop-manip.cc +++ b/gcc/tree-vect-loop-manip.cc @@ -2803,10 +2803,21 @@ vect_do_peeling (loop_vec_info loop_vinfo, tree niters, tree nitersm1, if (LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo)) skip_epilog = false; + class loop *scalar_loop = LOOP_VINFO_SCALAR_LOOP (loop_vinfo); + auto_vec original_counts; + basic_block *original_bbs = NULL; + if (skip_vector) { split_edge (loop_preheader_edge (loop)); + if (epilog_peeling && (vect_epilogues || scalar_loop == NULL)) + { + original_bbs = get_loop_body (loop); + for (unsigned int i = 0; i < loop->num_nodes; i++) + original_counts.safe_push(original_bbs[i]->count); + } + /* Due to the order in which we peel prolog and epilog, we first propagate probability to the whole loop. The purpose is to avoid adjusting probabilities of both prolog and vector loops @@ -2821,7 +2832,6 @@ vect_do_peeling (loop_vec_info loop_vinfo, tree niters, tree nitersm1, } dump_user_location_t loop_loc = find_loop_location (loop); - class loop *scalar_loop = LOOP_VINFO_SCALAR_LOOP (loop_vinfo); if (vect_epilogues) /* Make sure to set the epilogue's epilogue scalar loop, such that we can use the original scalar loop as remaining epilogue if necessary. */ @@ -2975,16 +2985,19 @@ vect_do_peeling (loop_vec_info loop_vinfo, tree niters, tree nitersm1, a merge point of control flow. */ guard_to->count = guard_bb->count; - /* Scale probability of epilog loop back. - FIXME: We should avoid scaling down and back up. Profile may - get lost if we scale down to 0. */ - basic_block *bbs = get_loop_body (epilog); - for (unsigned int i = 0; i < epilog->num_nodes; i++) - bbs[i]->count = bbs[i]->count.apply_scale - (bbs[i]->count, - bbs[i]->count.apply_probability - (prob_vector)); - free (bbs); + /* Restore the counts of the epilog loop if we didn't use the scalar loop. */ + if (vect_epilogues || scalar_loop == NULL) + { + gcc_assert(epilog->num_nodes == loop->num_nodes); + basic_block *bbs = get_loop_body (epilog); + for (unsigned int i = 0; i < epilog->num_nodes; i++) + { + gcc_assert(get_bb_original (bbs[i]) == original_bbs[i]); + bbs[i]->count = original_counts[i]; + } + free (bbs); + free (original_bbs); + } } basic_block bb_before_epilog = loop_preheader_edge (epilog)->src; -- 2.25.1