[gcc r17-2215] match.pd: Fold SAD_EXPR with identical inputs

https://gcc.gnu.org/g:79c77e1642030361a17b3c892a00092d8285a3b2

commit r17-2215-g79c77e1642030361a17b3c892a00092d8285a3b2
Author: Pengfei Li <[email protected]>
Date:   Mon Jul 6 13:11:32 2026 +0000

    match.pd: Fold SAD_EXPR with identical inputs
    
    Normally, SAD_EXPRs with identical first and second operands are not
    constructed, since the absolute difference value is zero. However, this
    can still appear when vectorizing small iteration-count reduction loops
    with an absolute difference operation.
    
    This patch adds a match.pd rule to fold the redundant SAD_EXPR to its
    accumulator operand.
    
    Bootstrapped and tested on aarch64-linux-gnu and x86_64-linux-gnu.
    
    gcc/ChangeLog:
    
            * match.pd: Simplify SAD(x, x, acc) into acc.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/aarch64/sve/sad_2.c: New test.

Diff:
---
 gcc/match.pd                                 |  7 +++++++
 gcc/testsuite/gcc.target/aarch64/sve/sad_2.c | 16 ++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/gcc/match.pd b/gcc/match.pd
index a7cec25dbad8..4520a23a026b 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -1229,6 +1229,13 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
  (mult (absu@1 @0) @1)
  (mult (convert@2 @0) @2))
 
+#if GIMPLE
+/* Simplify SAD(x, x, acc) -> acc since the absolute difference is zero.  */
+(simplify
+ (sad @0 @0 @1)
+ @1)
+#endif
+
 /* cos(copysign(x, y)) -> cos(x).  Similarly for cosh.  */
 (for coss (COS COSH)
  (for copysigns (COPYSIGN)
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/sad_2.c b/gcc/testsuite/gcc.target/aarch64/sve/sad_2.c
new file mode 100644
index 000000000000..d46517f10d86
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/sad_2.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -msve-vector-bits=128 -mtune=neoverse-v2" } */
+
+#include <stdint.h>
+
+int foo (uint8_t *pix1, uint8_t *pix2)
+{
+    int sum = 0;
+    for (int x = 0; x < 48; x++)
+    {
+        sum += __builtin_abs (pix1[x] - pix2[x]);
+    }
+    return sum;
+}
+
+/* { dg-final { scan-assembler-times {\tudot\t} 3 } } */