https://gcc.gnu.org/g:5e363ffefaceb9ff8fdeeead247c8337538e01db
commit r16-400-g5e363ffefaceb9ff8fdeeead247c8337538e01db
Author: Richard Biener <rguent...@suse.de>
Date: Tue May 6 08:36:01 2025 +0200
tree-optimization/120031 - CTZ pattern matching fails a case
This PR is about the pattern matching in tree-ssa-forwprop.cc not
working for the fallback implementation in ZSTD which uses a cast
aroud the negation of the value to be tested. There's a pattern
eliding casts in (T')-(T)x already but that only covered an
inner widening conversion. The following extends this to other
conversions given the negation will then be carried out in an
unsigned type.
PR tree-optimization/120031
* match.pd ((nop_outer_cast)-(inner_cast)var -> -(outer_cast)(var)):
Allow inner conversions that are not widenings when the outer
type is unsigned.
* gcc.target/i386/pr120031.c: New testcase.
Diff:
---
gcc/match.pd | 9 +++++----
gcc/testsuite/gcc.target/i386/pr120031.c | 15 +++++++++++++++
2 files changed, 20 insertions(+), 4 deletions(-)
diff --git a/gcc/match.pd b/gcc/match.pd
index a150de5184f6..ab496d923cc0 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -1123,9 +1123,9 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
#endif
/* (nop_outer_cast)-(inner_cast)var -> -(outer_cast)(var)
- if var is smaller in precision.
- This is always safe for both doing the negative in signed or unsigned
- as the value for undefined will not show up.
+ If var is smaller in precision this is always safe for both doing
+ the negative in signed or unsigned as the value for undefined will not
+ show up. Else it is safe if the negation is done in an unsigned type.
Note the outer cast cannot be a boolean type as the only valid values
are 0,-1/1 (depending on the signedness of the boolean) and the negative
is there to get the correct value. */
@@ -1133,7 +1133,8 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(convert (negate:s@1 (convert:s @0)))
(if (INTEGRAL_TYPE_P (type)
&& tree_nop_conversion_p (type, TREE_TYPE (@1))
- && TYPE_PRECISION (type) > TYPE_PRECISION (TREE_TYPE (@0))
+ && (TYPE_PRECISION (type) > TYPE_PRECISION (TREE_TYPE (@0))
+ || TYPE_UNSIGNED (type))
&& TREE_CODE (type) != BOOLEAN_TYPE)
(negate (convert @0))))
diff --git a/gcc/testsuite/gcc.target/i386/pr120031.c
b/gcc/testsuite/gcc.target/i386/pr120031.c
new file mode 100644
index 000000000000..e329cbc2f543
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr120031.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mbmi" } */
+
+unsigned int
+ZSTD_countTrailingZeros32_fallback (unsigned int val)
+{
+ static const unsigned int DeBruijn[32]
+ = { 0, 1, 28, 2, 29, 14, 24, 3,
+ 30, 22, 20, 15, 25, 17, 4, 8,
+ 31, 27, 13, 23, 21, 19, 16, 7,
+ 26, 12, 18, 6, 11, 5, 10, 9};
+ return DeBruijn[((unsigned int) ((val & -(int) val) * 0x077CB531U)) >> 27];
+}
+
+/* { dg-final { scan-assembler "tzcnt" } } */
