aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRobin Dapp <rdapp@ventanamicro.com>2024-06-07 14:36:41 +0200
committerRobin Dapp <rdapp@ventanamicro.com>2024-06-11 20:05:29 +0200
commit2b438a0d2aa80f051a09b245a58f643540d4004b (patch)
tree879fdb5f416f5c09c0b99e3e857227c594757dd7
parent1588983be6112561c805a50eb7a3c585865beffa (diff)
downloadgcc-2b438a0d2aa80f051a09b245a58f643540d4004b.zip
gcc-2b438a0d2aa80f051a09b245a58f643540d4004b.tar.gz
gcc-2b438a0d2aa80f051a09b245a58f643540d4004b.tar.bz2
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.
-rw-r--r--gcc/tree-vect-loop.cc10
-rw-r--r--gcc/tree-vect-stmts.cc2
-rw-r--r--gcc/tree-vectorizer.h3
3 files changed, 13 insertions, 2 deletions
diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index c471f15..5b1ad06 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 05a169e..831f182 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 97ec9c3..6bb0f5c 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);