Add two match.pd patterns that simplify COND_ADD when the mask is
a strict greater-than comparison against zero and the else value equals
one of the addition operands:
COND_ADD (a > 0, b, a, b) -> b + MAX_EXPR <a, 0>
COND_ADD (a > 0, a, b, b) -> b + MAX_EXPR <a, 0>
PR 124097
gcc/ChangeLog:
* match.pd (COND_ADD (a > 0, a, b, b) -> b + MAX_EXPR <a, 0>): New
pattern.
gcc/testsuite/ChangeLog:
* gcc.dg/tree-ssa/pr124097.c: New test.
Signed-off-by: Eikansh Gupta <[email protected]>
---
gcc/match.pd | 15 +++++++++++++++
gcc/testsuite/gcc.dg/tree-ssa/pr124097.c | 17 +++++++++++++++++
2 files changed, 32 insertions(+)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr124097.c
diff --git a/gcc/match.pd b/gcc/match.pd
index 7f16fd4e081..2bb4f425895 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -11323,6 +11323,21 @@ and,
&& fold_real_zero_addition_p (type, NULL_TREE, @4, 0)))
(IFN_COND_ADD (bit_and @0 @2) @1 @3 @1)))
+/* COND_ADD (a > 0, b, a, b) -> b + max (a, 0)
+ COND_ADD (a > 0, a, b, b) -> b + max (a, 0) */
+(simplify
+ (IFN_COND_ADD (gt @0 zerop@1) @2 @0 @2)
+ (if (FLOAT_TYPE_P (type)
+ && !HONOR_NANS (type)
+ && !HONOR_SIGNED_ZEROS (type))
+ (plus @2 (max @0 @1))))
+(simplify
+ (IFN_COND_ADD (gt @0 zerop@1) @0 @2 @2)
+ (if (FLOAT_TYPE_P (type)
+ && !HONOR_NANS (type)
+ && !HONOR_SIGNED_ZEROS (type))
+ (plus @2 (max @0 @1))))
+
/* Detect simplication for a conditional length reduction where
a = mask ? b : 0
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr124097.c
b/gcc/testsuite/gcc.dg/tree-ssa/pr124097.c
new file mode 100644
index 00000000000..5769a2ca5d0
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr124097.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -ffast-math -march=armv9-a -fdump-tree-optimized" } */
+
+float __attribute__ ((noipa))
+foo (float *a)
+{
+ float sum = 0.;
+ for (int i = 0; i < 32000; i++)
+ if (a[i] > (float) 0.)
+ sum += a[i];
+ return sum;
+}
+
+/* The main vectorized loop should have COND_ADD simplified to MAX_EXPR + plus.
+ The SVE epilogue retains COND_ADD */
+/* { dg-final { scan-tree-dump-times { MAX_EXPR } 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times { \.COND_ADD } 2 "optimized" } } */
--
2.34.1
