Hi All,
It seems I forgot to check that the operation we're combing when masking the
predicated together are actually predicates types.
Without it we end up accidentally trying to combine a value and a mask.
Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
Ok for master?
Thanks,
Tamar
gcc/ChangeLog:
PR tree-optimization/103741
* tree-vect-stmts.c (vectorizable_operation): Check for boolean.
gcc/testsuite/ChangeLog:
PR tree-optimization/103741
* gcc.target/aarch64/pr103741.c: New test.
--- inline copy of patch --
diff --git a/gcc/testsuite/gcc.target/aarch64/pr103741.c
b/gcc/testsuite/gcc.target/aarch64/pr103741.c
new file mode 100644
index
0000000000000000000000000000000000000000..ef3ae66ebe5e5a44e7bea7be22b6378bc23cc538
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr103741.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8-a+sve -O1" } */
+
+long int m, n;
+
+int
+qux (int z)
+{
+ return 4 >> z ? z : 0;
+}
+
+int
+bar (long int y)
+{
+ return y ? 3 : 2;
+}
+
+__attribute__ ((simd)) int
+foo (int x)
+{
+ long int a = x & m;
+ int b = bar (x) / n;
+
+ return qux (b) == a;
+}
+
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index
8c427174b37e6c03c2f914c90332bcc4eac54130..ad90cdb0473a337207d6ba54c1dd0a2ecc50ab8d
100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -6361,7 +6361,9 @@ vectorizable_operation (vec_info *vinfo,
/* When combining two masks check if either of them is elsewhere
combined with a loop mask, if that's the case we can mark that the
new combined mask doesn't need to be combined with a loop mask. */
- if (masked_loop_p && code == BIT_AND_EXPR)
+ if (masked_loop_p
+ && code == BIT_AND_EXPR
+ && VECTOR_BOOLEAN_TYPE_P (vectype))
{
if (loop_vinfo->scalar_cond_masked_set.contains ({ op0,
ncopies}))
--
diff --git a/gcc/testsuite/gcc.target/aarch64/pr103741.c b/gcc/testsuite/gcc.target/aarch64/pr103741.c
new file mode 100644
index 0000000000000000000000000000000000000000..ef3ae66ebe5e5a44e7bea7be22b6378bc23cc538
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr103741.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8-a+sve -O1" } */
+
+long int m, n;
+
+int
+qux (int z)
+{
+ return 4 >> z ? z : 0;
+}
+
+int
+bar (long int y)
+{
+ return y ? 3 : 2;
+}
+
+__attribute__ ((simd)) int
+foo (int x)
+{
+ long int a = x & m;
+ int b = bar (x) / n;
+
+ return qux (b) == a;
+}
+
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 8c427174b37e6c03c2f914c90332bcc4eac54130..ad90cdb0473a337207d6ba54c1dd0a2ecc50ab8d 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -6361,7 +6361,9 @@ vectorizable_operation (vec_info *vinfo,
/* When combining two masks check if either of them is elsewhere
combined with a loop mask, if that's the case we can mark that the
new combined mask doesn't need to be combined with a loop mask. */
- if (masked_loop_p && code == BIT_AND_EXPR)
+ if (masked_loop_p
+ && code == BIT_AND_EXPR
+ && VECTOR_BOOLEAN_TYPE_P (vectype))
{
if (loop_vinfo->scalar_cond_masked_set.contains ({ op0,
ncopies}))