From: Kyrylo Tkachov <[email protected]>
For operands known to be in the range [0, 1], multiplying a 0/1 value by a
negated 0/1 value is the negation of their bitwise AND:
x * -y == -(x & y) when x, y are in { 0, 1 }.
This complements the existing "{ 0, 1 } * { 0, 1 } -> { 0, 1 } & { 0, 1 }"
simplification, which does not handle a negated operand. Besides removing the
multiply, for the comparison-derived 0/1 masks produced by if-conversion this
exposes a plain bitwise AND of the original conditions to later passes.
This triggers a few times in astcenc in SPEC2026 where it simplifies the
codegen of one of the hot kernels and gives a ~2.4% improvement on
aarch64, though the real winners for that kernel are described in
PR125750. This is just a small cleanup.
Bootstrapped and tested on aarch64-none-linux-gnu.
Signed-off-by: Kyrylo Tkachov <[email protected]>
gcc/ChangeLog:
PR tree-optimization/125750
* match.pd (mult of a 0/1 value by a negated 0/1 value): New
simplification.
gcc/testsuite/ChangeLog:
PR tree-optimization/125750
* gcc.dg/tree-ssa/mult-negate-zeroone-1.c: New test.
* gcc.dg/tree-ssa/mult-negate-zeroone-2.c: New test.
---
gcc/match.pd | 6 +++++
.../gcc.dg/tree-ssa/mult-negate-zeroone-1.c | 25 +++++++++++++++++++
.../gcc.dg/tree-ssa/mult-negate-zeroone-2.c | 19 ++++++++++++++
3 files changed, 50 insertions(+)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/mult-negate-zeroone-1.c
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/mult-negate-zeroone-2.c
diff --git a/gcc/match.pd b/gcc/match.pd
index e0d7ef80e14..bad6d2ec14d 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -2518,6 +2518,12 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(if (INTEGRAL_TYPE_P (type))
(bit_and @0 @1)))
+/* Transform { 0 or 1 } * -{ 0 or 1 } into -({ 0 or 1 } & { 0 or 1 }). */
+(simplify
+ (mult zero_one_valued_p@0 (negate zero_one_valued_p@1))
+ (if (INTEGRAL_TYPE_P (type))
+ (negate (bit_and @0 @1))))
+
/* Fold `(a ? b : 0) | (a ? 0 : c)` into (a ? b : c).
Handle also ^ and + in replacement of `|`. */
(for cnd (cond vec_cond)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/mult-negate-zeroone-1.c
b/gcc/testsuite/gcc.dg/tree-ssa/mult-negate-zeroone-1.c
new file mode 100644
index 00000000000..3c66db986ea
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/mult-negate-zeroone-1.c
@@ -0,0 +1,25 @@
+/* Test that { 0, 1 } * -{ 0, 1 } folds to -({ 0, 1 } & { 0, 1 }) and does not
+ keep a multiply. */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+int
+f1 (int x, int y)
+{
+ return (x > 5) * -(y > 5);
+}
+
+long
+f2 (long x, long y)
+{
+ return (long) (x > 5) * -(long) (y > 5);
+}
+
+unsigned
+f3 (unsigned x, unsigned y)
+{
+ return (x > 5u) * -(unsigned) (y > 5u);
+}
+
+/* { dg-final { scan-tree-dump-not " \\* " "optimized" } } */
+/* { dg-final { scan-tree-dump-times " & " 3 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/mult-negate-zeroone-2.c
b/gcc/testsuite/gcc.dg/tree-ssa/mult-negate-zeroone-2.c
new file mode 100644
index 00000000000..be9ab02e30e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/mult-negate-zeroone-2.c
@@ -0,0 +1,19 @@
+/* Verify { 0, 1 } * -{ 0, 1 } == -({ 0, 1 } & { 0, 1 }) at runtime. */
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+
+int __attribute__((noipa))
+f (int x, int y)
+{
+ return (x > 5) * -(y > 5);
+}
+
+int
+main (void)
+{
+ for (int x = -3; x < 12; x++)
+ for (int y = -3; y < 12; y++)
+ if (f (x, y) != -((x > 5) & (y > 5)))
+ __builtin_abort ();
+ return 0;
+}
--
2.50.1 (Apple Git-155)
