From 2b438a0d2aa80f051a09b245a58f643540d4004b Mon Sep 17 00:00:00 2001 From: Robin Dapp Date: Fri, 7 Jun 2024 14:36:41 +0200 Subject: [PATCH] vect: Merge loop mask and cond_op mask in fold-left reduction [PR115382]. Currently we discard the cond-op mask when the loop is fully masked which causes wrong code in gcc.dg/vect/vect-cond-reduc-in-order-2-signed-zero.c when compiled with -O3 -march=cascadelake --param vect-partial-vector-usage=2. This patch ANDs both masks. gcc/ChangeLog: PR tree-optimization/115382 * tree-vect-loop.cc (vectorize_fold_left_reduction): Use prepare_vec_mask. * tree-vect-stmts.cc (check_load_store_for_partial_vectors): Remove static of prepare_vec_mask. * tree-vectorizer.h (prepare_vec_mask): Export. --- gcc/tree-vect-loop.cc | 10 +++++++++- gcc/tree-vect-stmts.cc | 2 +- gcc/tree-vectorizer.h | 3 +++ 3 files changed, 13 insertions(+), 2 deletions(-) diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index c471f1564a7..5b1ad06eca6 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -7204,7 +7204,15 @@ vectorize_fold_left_reduction (loop_vec_info loop_vinfo, tree len = NULL_TREE; tree bias = NULL_TREE; if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)) - mask = vect_get_loop_mask (loop_vinfo, gsi, masks, vec_num, vectype_in, i); + { + tree loop_mask = vect_get_loop_mask (loop_vinfo, gsi, masks, + vec_num, vectype_in, i); + if (is_cond_op) + mask = prepare_vec_mask (loop_vinfo, TREE_TYPE (loop_mask), + loop_mask, vec_opmask[i], gsi); + else + mask = loop_mask; + } else if (is_cond_op) mask = vec_opmask[i]; if (LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo)) diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc index 05a169ecb2d..831f1825376 100644 --- a/gcc/tree-vect-stmts.cc +++ b/gcc/tree-vect-stmts.cc @@ -1643,7 +1643,7 @@ check_load_store_for_partial_vectors (loop_vec_info loop_vinfo, tree vectype, MASK_TYPE is the type of both masks. If new statements are needed, insert them before GSI. */ -static tree +tree prepare_vec_mask (loop_vec_info loop_vinfo, tree mask_type, tree loop_mask, tree vec_mask, gimple_stmt_iterator *gsi) { diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h index 97ec9c341e7..6bb0f5c3a56 100644 --- a/gcc/tree-vectorizer.h +++ b/gcc/tree-vectorizer.h @@ -2508,6 +2508,9 @@ extern void vect_free_slp_tree (slp_tree); extern bool compatible_calls_p (gcall *, gcall *); extern int vect_slp_child_index_for_operand (const gimple *, int op, bool); +extern tree prepare_vec_mask (loop_vec_info, tree, tree, tree, + gimple_stmt_iterator *); + /* In tree-vect-patterns.cc. */ extern void vect_mark_pattern_stmts (vec_info *, stmt_vec_info, gimple *, tree);