[PATCH] aarch64: Canonicalize halving-add builtins [PR122715]

From de17c2eac59fb4642f6eacac3884d8018d5dc131 Mon Sep 17 00:00:00 2001
From: Odysseas Georgoudis <[email protected]>
Date: Sat, 15 Aug 2026 01:20:17 +0100
Subject: [PATCH] aarch64: Canonicalize halving-add builtins [PR122715]

Advanced SIMD halving-add intrinsics remain target builtins in GIMPLE,
preventing generic average simplifications from seeing them.  Canonicalize
SHADD and UHADD to IFN_AVG_FLOOR, and SRHADD and URHADD to
IFN_AVG_CEIL.

This allows equal operands to be folded by the existing match.pd rule
while retaining optab-based instruction selection for other operands.

	PR target/122715

gcc/ChangeLog:

	* config/aarch64/aarch64-builtins.cc
	(aarch64_general_gimple_fold_builtin): Canonicalize halving-add
	builtins to IFN_AVG_FLOOR and IFN_AVG_CEIL.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/avg-pr122715.c: New test.
	* gcc.target/aarch64/avg-pr122715-2.c: New test.

Signed-off-by: Odysseas Georgoudis <[email protected]>
---
 gcc/config/aarch64/aarch64-builtins.cc        |  14 ++
 .../gcc.target/aarch64/avg-pr122715-2.c       |  33 +++++
 .../gcc.target/aarch64/avg-pr122715.c         | 129 ++++++++++++++++++
 3 files changed, 176 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/avg-pr122715-2.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/avg-pr122715.c

diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index 8cd1bc4b1a2..bb0a1c978f2 100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -5065,6 +5065,20 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode, gcall *stmt,
 					       1, args[0]);
 	gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
 	break;
+      /* Lower Advanced SIMD halving-add builtins to average internal
+	 functions.  */
+      BUILTIN_VDQ_BHSI (BINOP, shadd, 0, DEFAULT)
+      BUILTIN_VDQ_BHSI (BINOPU, uhadd, 0, DEFAULT)
+	new_stmt = gimple_build_call_internal (IFN_AVG_FLOOR, 2,
+					       args[0], args[1]);
+	gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
+	break;
+      BUILTIN_VDQ_BHSI (BINOP, srhadd, 0, DEFAULT)
+      BUILTIN_VDQ_BHSI (BINOPU, urhadd, 0, DEFAULT)
+	new_stmt = gimple_build_call_internal (IFN_AVG_CEIL, 2,
+					       args[0], args[1]);
+	gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
+	break;
       BUILTIN_VSDQ_I_DI (BINOP, ashl, 3, DEFAULT)
 	if (TREE_CODE (args[1]) == INTEGER_CST
 	    && wi::ltu_p (wi::to_wide (args[1]), element_precision (args[0])))
diff --git a/gcc/testsuite/gcc.target/aarch64/avg-pr122715-2.c b/gcc/testsuite/gcc.target/aarch64/avg-pr122715-2.c
new file mode 100644
index 00000000000..c088c1327d0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/avg-pr122715-2.c
@@ -0,0 +1,33 @@
+/* PR target/122715 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+#include <arm_neon.h>
+
+int32x4_t avg_floor_s32(int32x4_t x, int32x4_t y)
+{
+  return vhaddq_s32 (x, y);
+}
+
+uint32x4_t avg_floor_u32(uint32x4_t x, uint32x4_t y)
+{
+  return vhaddq_u32 (x, y);
+}
+
+int32x4_t avg_ceil_s32(int32x4_t x, int32x4_t y)
+{
+  return vrhaddq_s32 (x, y);
+}
+
+uint32x4_t avg_ceil_u32(uint32x4_t x, uint32x4_t y)
+{
+  return vrhaddq_u32 (x, y);
+}
+
+/* { dg-final { scan-tree-dump-times {\.AVG_FLOOR} 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times {\.AVG_CEIL} 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-not {__builtin_aarch64_} "optimized" } } */
+/* { dg-final { scan-assembler-times {\tshadd\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tuhadd\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tsrhadd\t} 1 } } */
+/* { dg-final { scan-assembler-times {\turhadd\t} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/avg-pr122715.c b/gcc/testsuite/gcc.target/aarch64/avg-pr122715.c
new file mode 100644
index 00000000000..aa46df3ffd7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/avg-pr122715.c
@@ -0,0 +1,129 @@
+/* PR target/122715 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+#include <arm_neon.h>
+
+int8x8_t avg_floor_s8_64(int8x8_t x)
+{
+  return vhadd_s8 (x, x);
+}
+
+int16x4_t avg_floor_s16_64(int16x4_t x)
+{
+  return vhadd_s16 (x, x);
+}
+
+int32x2_t avg_floor_s32_64(int32x2_t x)
+{
+  return vhadd_s32 (x, x);
+}
+
+uint8x8_t avg_floor_u8_64(uint8x8_t x)
+{
+  return vhadd_u8 (x, x);
+}
+
+uint16x4_t avg_floor_u16_64(uint16x4_t x)
+{
+  return vhadd_u16 (x, x);
+}
+
+uint32x2_t avg_floor_u32_64(uint32x2_t x)
+{
+  return vhadd_u32 (x, x);
+}
+
+int8x16_t avg_floor_s8_128(int8x16_t x)
+{
+  return vhaddq_s8 (x, x);
+}
+
+int16x8_t avg_floor_s16_128(int16x8_t x)
+{
+  return vhaddq_s16 (x, x);
+}
+
+int32x4_t avg_floor_s32_128(int32x4_t x)
+{
+  return vhaddq_s32 (x, x);
+}
+
+uint8x16_t avg_floor_u8_128(uint8x16_t x)
+{
+  return vhaddq_u8 (x, x);
+}
+
+uint16x8_t avg_floor_u16_128(uint16x8_t x)
+{
+  return vhaddq_u16 (x, x);
+}
+
+uint32x4_t avg_floor_u32_128(uint32x4_t x)
+{
+  return vhaddq_u32 (x, x);
+}
+
+int8x8_t avg_ceil_s8_64(int8x8_t x)
+{
+  return vrhadd_s8 (x, x);
+}
+
+int16x4_t avg_ceil_s16_64(int16x4_t x)
+{
+  return vrhadd_s16 (x, x);
+}
+
+int32x2_t avg_ceil_s32_64(int32x2_t x)
+{
+  return vrhadd_s32 (x, x);
+}
+
+uint8x8_t avg_ceil_u8_64(uint8x8_t x)
+{
+  return vrhadd_u8 (x, x);
+}
+
+uint16x4_t avg_ceil_u16_64(uint16x4_t x)
+{
+  return vrhadd_u16 (x, x);
+}
+
+uint32x2_t avg_ceil_u32_64(uint32x2_t x)
+{
+  return vrhadd_u32 (x, x);
+}
+
+int8x16_t avg_ceil_s8_128(int8x16_t x)
+{
+  return vrhaddq_s8 (x, x);
+}
+
+int16x8_t avg_ceil_s16_128(int16x8_t x)
+{
+  return vrhaddq_s16 (x, x);
+}
+
+int32x4_t avg_ceil_s32_128(int32x4_t x)
+{
+  return vrhaddq_s32 (x, x);
+}
+
+uint8x16_t avg_ceil_u8_128(uint8x16_t x)
+{
+  return vrhaddq_u8 (x, x);
+}
+
+uint16x8_t avg_ceil_u16_128(uint16x8_t x)
+{
+  return vrhaddq_u16 (x, x);
+}
+
+uint32x4_t avg_ceil_u32_128(uint32x4_t x)
+{
+  return vrhaddq_u32 (x, x);
+}
+
+/* { dg-final { scan-tree-dump-not {__builtin_aarch64_} "optimized" } } */
+/* { dg-final { scan-tree-dump-times {return x_} 24 "optimized" } } */
+/* { dg-final { scan-assembler-not {\t[su]r?hadd\t} } } */
-- 
2.43.5