tree-optimization/113126 - vector extension compare optimization
Checks
Commit Message
The following makes sure the resulting boolean type is the same
when eliding a float extension.
Bootstrapped and tested on x86_64-unknown-linux-gnu, pushed.
PR tree-optimization/113126
* match.pd ((double)float CMP (double)float -> float CMP float):
Make sure the boolean type is the same.
* fold-const.cc (fold_binary_loc): Likewise.
* gcc.dg/torture/pr113126.c: New testcase.
---
gcc/fold-const.cc | 3 ++-
gcc/match.pd | 9 +++++----
gcc/testsuite/gcc.dg/torture/pr113126.c | 15 +++++++++++++++
3 files changed, 22 insertions(+), 5 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/torture/pr113126.c
@@ -12900,7 +12900,8 @@ fold_binary_loc (location_t loc, enum tree_code code, tree type,
if (element_precision (TREE_TYPE (targ1)) > element_precision (newtype))
newtype = TREE_TYPE (targ1);
- if (element_precision (newtype) < element_precision (TREE_TYPE (arg0)))
+ if (element_precision (newtype) < element_precision (TREE_TYPE (arg0))
+ && is_truth_type_for (newtype, type))
return fold_build2_loc (loc, code, type,
fold_convert_loc (loc, newtype, targ0),
fold_convert_loc (loc, newtype, targ1));
@@ -6792,11 +6792,12 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
&& exact_real_truncate (TYPE_MODE (double_type_node), &orig))
type1 = double_type_node;
}
- tree newtype
- = (element_precision (TREE_TYPE (@00)) > element_precision (type1)
- ? TREE_TYPE (@00) : type1);
+ tree newtype
+ = (element_precision (TREE_TYPE (@00)) > element_precision (type1)
+ ? TREE_TYPE (@00) : type1);
}
- (if (element_precision (TREE_TYPE (@0)) > element_precision (newtype))
+ (if (element_precision (TREE_TYPE (@0)) > element_precision (newtype)
+ && is_truth_type_for (newtype, type))
(cmp (convert:newtype @00) (convert:newtype @10))))))))
new file mode 100644
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+
+typedef float __attribute__((__vector_size__ (8))) F;
+typedef double __attribute__((__vector_size__ (16))) G;
+
+F f;
+G g;
+
+F
+foo (void)
+{
+ G h = __builtin_convertvector (f, G);
+ g = h <= h;
+ return f;
+}