From: Karl Meakin <karl.meakin@arm.com>
Date: Wed, 1 Jul 2026 12:16:40 +0000 (+0000)
Subject: aarch64: Relax type-checking assert [PR126064]
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=9bfc05c8a91f3f89d579afa3a79cce1c0da34184;p=thirdparty%2Fgcc.git

aarch64: Relax type-checking assert [PR126064]

Comparing `arg_type` and `TREE_TYPE (b)` by pointer address causes an
assertion failure when one type is a `typedef` for the other (eg
`uint32x2_t` and `__Uint32x2_t`. Fix by using a more relaxed comparison.

gcc/ChangeLog:

	PR target/126064
	* config/aarch64/aarch64-neon-builtins-base.cc: Compare
	`arg_type` and `TREE_TYPE (b)` using `types_compatible_p` rather
	than comparing their pointer addresses.

gcc/testsuite/ChangeLog:

	PR target/126064
	* gcc.target/aarch64/pr126064.c: New test.
---

diff --git a/gcc/config/aarch64/aarch64-neon-builtins-base.cc b/gcc/config/aarch64/aarch64-neon-builtins-base.cc
index 9e61ba7688c..d8fae81388e 100644
--- a/gcc/config/aarch64/aarch64-neon-builtins-base.cc
+++ b/gcc/config/aarch64/aarch64-neon-builtins-base.cc
@@ -562,7 +562,7 @@ public:
       std::swap (a, b);
 
     auto arg_type = TREE_TYPE (a);
-    gcc_assert (arg_type == TREE_TYPE (b));
+    gcc_assert (types_compatible_p (arg_type, TREE_TYPE (b)));
 
     auto tuple_type = TREE_TYPE (f.lhs);
     auto tuple = create_tmp_var (tuple_type);
diff --git a/gcc/testsuite/gcc.target/aarch64/pr126064.c b/gcc/testsuite/gcc.target/aarch64/pr126064.c
new file mode 100644
index 00000000000..9d792588781
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr126064.c
@@ -0,0 +1,28 @@
+/* { dg-options "-std=c99" } */
+
+/* Check that `gimple_permute_pair::fold()` does not trip an assert when the LHS
+   type is `uint32x2_t` and the RHS type is `__Uint32x2_t`.  */
+
+#include <arm_neon.h>
+
+void
+repro (uint8_t *dst, uint8x8_t a, uint8x8_t b)
+{
+  uint32x2x2_t t;
+  uint32x2_t r;
+  uint8x8_t c;
+
+  r = vrev64_u32 (vreinterpret_u32_u8 (b));
+  t = vtrn_u32 (vreinterpret_u32_u8 (a), r);
+  c = vreinterpret_u8_u32 (t.val[1]);
+  t = vtrn_u32 (t.val[0], vreinterpret_u32_u8 (c));
+  t.val[1] = vrev64_u32 (t.val[1]);
+
+  vst1_u8 (dst, vreinterpret_u8_u32 (t.val[1]));
+}
+
+uint32x2_t
+minimized_repro (uint32x2_t a, uint32x2_t b)
+{
+  return vtrn_u32 (a, vrev64_u32 (b)).val[1];
+}