aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorManolis Tsamis <manolis.tsamis@vrull.eu>2023-11-01 12:27:28 +0100
committerPhilipp Tomsich <philipp.tomsich@vrull.eu>2024-05-24 14:11:51 +0200
commit6d6f324bda1ccb51cd43ff9d4d017eb71bb2d690 (patch)
tree20558f0a6c4aaa12601d55fb4832eb99e3d7e35c
parent7acd5d71547f74a2af35bab1b17a518197d25d23 (diff)
downloadgcc-6d6f324bda1ccb51cd43ff9d4d017eb71bb2d690.zip
gcc-6d6f324bda1ccb51cd43ff9d4d017eb71bb2d690.tar.gz
gcc-6d6f324bda1ccb51cd43ff9d4d017eb71bb2d690.tar.bz2
MATCH: Look through VIEW_CONVERT when folding VEC_PERM_EXPRs.
The match.pd patterns to merge two vector permutes into one fail when a potentially no-op view convert expressions is between the two permutes. This change lifts this restriction. gcc/ChangeLog: * match.pd: Allow no-op view_convert between permutes. gcc/testsuite/ChangeLog: * gcc.dg/fold-perm-2.c: New test.
-rw-r--r--gcc/match.pd14
-rw-r--r--gcc/testsuite/gcc.dg/fold-perm-2.c16
2 files changed, 24 insertions, 6 deletions
diff --git a/gcc/match.pd b/gcc/match.pd
index 7081d76..024e335 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -10082,19 +10082,21 @@ and,
d = VEC_PERM_EXPR <a, b, NEW_VCST>; */
(simplify
- (vec_perm (vec_perm@0 @1 @2 VECTOR_CST@3) @0 VECTOR_CST@4)
+ (vec_perm (view_convert?@0 (vec_perm@1 @2 @3 VECTOR_CST@4)) @0 VECTOR_CST@5)
(if (TYPE_VECTOR_SUBPARTS (type).is_constant ())
(with
{
machine_mode result_mode = TYPE_MODE (type);
- machine_mode op_mode = TYPE_MODE (TREE_TYPE (@1));
+ machine_mode op_mode = TYPE_MODE (TREE_TYPE (@2));
int nelts = TYPE_VECTOR_SUBPARTS (type).to_constant ();
vec_perm_builder builder0;
vec_perm_builder builder1;
vec_perm_builder builder2 (nelts, nelts, 1);
}
- (if (tree_to_vec_perm_builder (&builder0, @3)
- && tree_to_vec_perm_builder (&builder1, @4))
+ (if (tree_to_vec_perm_builder (&builder0, @4)
+ && tree_to_vec_perm_builder (&builder1, @5)
+ && TYPE_SIZE (TREE_TYPE (TREE_TYPE (@0)))
+ == TYPE_SIZE (TREE_TYPE (TREE_TYPE (@1))))
(with
{
vec_perm_indices sel0 (builder0, 2, nelts);
@@ -10116,10 +10118,10 @@ and,
? (!can_vec_perm_const_p (result_mode, op_mode, sel0, false)
|| !can_vec_perm_const_p (result_mode, op_mode, sel1, false))
: !can_vec_perm_const_p (result_mode, op_mode, sel1, false)))
- op0 = vec_perm_indices_to_tree (TREE_TYPE (@4), sel2);
+ op0 = vec_perm_indices_to_tree (TREE_TYPE (@5), sel2);
}
(if (op0)
- (vec_perm @1 @2 { op0; })))))))
+ (view_convert (vec_perm @2 @3 { op0; }))))))))
/* Merge
c = VEC_PERM_EXPR <a, b, VCST0>;
diff --git a/gcc/testsuite/gcc.dg/fold-perm-2.c b/gcc/testsuite/gcc.dg/fold-perm-2.c
new file mode 100644
index 0000000..1a4ab40
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/fold-perm-2.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O -fdump-tree-fre1" } */
+
+typedef int veci __attribute__ ((vector_size (4 * sizeof (int))));
+typedef unsigned int vecu __attribute__ ((vector_size (4 * sizeof (unsigned int))));
+
+void fun (veci *a, veci *b, veci *c)
+{
+ veci r1 = __builtin_shufflevector (*a, *b, 0, 5, 2, 7);
+ vecu r2 = __builtin_convertvector (r1, vecu);
+ vecu r3 = __builtin_shufflevector (r2, r2, 2, 3, 1, 0);
+ *c = __builtin_convertvector (r3, veci);
+}
+
+/* { dg-final { scan-tree-dump "VEC_PERM_EXPR.*{ 2, 7, 5, 0 }" "fre1" } } */
+/* { dg-final { scan-tree-dump-times "VEC_PERM_EXPR" 1 "fre1" } } */