> Can you format it the same as the FFS pattern though:
Changed, use 1 space for indent, not 2 spaces
> And add a comment saying:
> `popcount (X ^ (X - 1))` is the same as ffs(x) when x is nonzero. and
> using ctz+1 will generate better code.
Added.
> Please add a generic testcase and not just a x86_64 specific one.
> In this case you can use ctz target supports which checks if ctz will
> cause a call or not.
Added a new testcase under gcc.dg
Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
Ok for trunk?
When X is nonzero, X ^ (X - 1) produces a mask of trailing zeros plus
the lowest set bit, so popcount of that expression equals ctz(X) + 1.
gcc/ChangeLog:
PR middle-end/124630
* match.pd (popcount (x ^ (x - 1))): Fold to ctz (x) + 1 when
x is nonzero and CTZ is directly supported.
gcc/testsuite/ChangeLog:
PR middle-end/124630
* gcc.dg/pr124630.c: New test.
* gcc.target/i386/pr124630.c: New test.
---
gcc/match.pd | 10 ++++++++++
gcc/testsuite/gcc.dg/pr124630.c | 16 ++++++++++++++++
gcc/testsuite/gcc.target/i386/pr124630.c | 12 ++++++++++++
3 files changed, 38 insertions(+)
create mode 100644 gcc/testsuite/gcc.dg/pr124630.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr124630.c
diff --git a/gcc/match.pd b/gcc/match.pd
index b037b1a2876..298b769fcc0 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -10377,6 +10377,16 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(BUILT_IN_POPCOUNT (convert:type0 @0))
(if (cfn == CFN_BUILT_IN_POPCOUNTLL)
(BUILT_IN_POPCOUNTLL (convert:type0 @0))))))))
+
+/* popcount (X ^ (X - 1)) is the same as ffs(x) when x is nonzero, and
+ using ctz+1 will generate better code. */
+(simplify
+ (POPCOUNT (bit_xor:c tree_expr_nonzero_p@0 (plus @0 integer_minus_onep)))
+ (if (INTEGRAL_TYPE_P (TREE_TYPE (@0))
+ && direct_internal_fn_supported_p (IFN_CTZ, TREE_TYPE (@0),
+ OPTIMIZE_FOR_SPEED))
+ (with { tree utype = unsigned_type_for (TREE_TYPE (@0)); }
+ (plus (CTZ:type (convert:utype @0)) { build_one_cst (type); }))))
#endif
/* PARITY simplifications. */
diff --git a/gcc/testsuite/gcc.dg/pr124630.c b/gcc/testsuite/gcc.dg/pr124630.c
new file mode 100644
index 00000000000..fde8ce97c67
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr124630.c
@@ -0,0 +1,16 @@
+/* PR middle-end/124630 */
+/* { dg-do compile } */
+/* { dg-require-effective-target ctz } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+unsigned
+foo (unsigned a)
+{
+ if (a != 0)
+ return __builtin_popcount (a ^ (a - 1)) - 1;
+ else
+ return __CHAR_BIT__ * __SIZEOF_INT__;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_ctz|\\.CTZ" 1 "optimized" } }
*/
+/* { dg-final { scan-tree-dump-not "__builtin_popcount|\\.POPCOUNT"
"optimized" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr124630.c
b/gcc/testsuite/gcc.target/i386/pr124630.c
new file mode 100644
index 00000000000..440aede39fa
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr124630.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mbmi" } */
+/* { dg-final { scan-assembler-not "blsmsk" } } */
+/* { dg-final { scan-assembler-not "cmove" } } */
+
+unsigned foo (unsigned a)
+{
+ if (a != 0)
+ return __builtin_popcount (a ^ (a - 1)) - 1;
+ else
+ return 32;
+}
--
2.34.1
