aarch64: [PR101529] Fix vector shuffle insertion expansion

The function aarch64_evpc_ins would reuse the target even though
it might be the same register as the two inputs.
Instead of checking to see if we can reuse the target, just use the
original input directly.

Committed as approved after bootstrapped and tested on
aarch64-linux-gnu with no regressions.

	PR target/101529

gcc/ChangeLog:

	* config/aarch64/aarch64.c (aarch64_evpc_ins): Don't use target
	as an input, use original one.

gcc/testsuite/ChangeLog:

	* c-c++-common/torture/builtin-convertvector-2.c: New test.
	* c-c++-common/torture/builtin-shufflevector-2.c: New test.

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 19f674152343db1e8e5163e44b9313d274f1f3eb..e23d7cf3d8fa361f2b732c95e773a059769e8215 100644 (file)
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -23102,11 +23102,10 @@ aarch64_evpc_ins (struct expand_vec_perm_d *d)
     }
   gcc_assert (extractindex < nelt);
 
-  emit_move_insn (d->target, insv);
   insn_code icode = code_for_aarch64_simd_vec_copy_lane (mode);
   expand_operand ops[5];
   create_output_operand (&ops[0], d->target, mode);
-  create_input_operand (&ops[1], d->target, mode);
+  create_input_operand (&ops[1], insv, mode);
   create_integer_operand (&ops[2], 1 << idx);
   create_input_operand (&ops[3], extractv, mode);
   create_integer_operand (&ops[4], extractindex);

diff --git a/gcc/testsuite/c-c++-common/torture/builtin-convertvector-2.c b/gcc/testsuite/c-c++-common/torture/builtin-convertvector-2.c
new file mode 100644 (file)
index 0000000..d88f6a7
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/torture/builtin-convertvector-2.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+/* PR target/101529 */
+
+typedef unsigned char __attribute__((__vector_size__ (1))) W;
+typedef unsigned char __attribute__((__vector_size__ (8))) V;
+typedef unsigned short __attribute__((__vector_size__ (16))) U;
+
+unsigned short us;
+
+/* aarch64 used to miscompile foo to just return 0. */
+W
+foo (unsigned char uc)
+{
+  V v = __builtin_convertvector ((U){ } >= us, V);
+  return __builtin_shufflevector ((W){ }, v, 4) & uc;
+}
+
+int
+main (void)
+{
+  W x = foo (5);
+  if (x[0] != 5)
+    __builtin_abort();
+  return 0;
+}
+

diff --git a/gcc/testsuite/c-c++-common/torture/builtin-shufflevector-2.c b/gcc/testsuite/c-c++-common/torture/builtin-shufflevector-2.c
new file mode 100644 (file)
index 0000000..7c4999e
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/torture/builtin-shufflevector-2.c
@@ -0,0 +1,26 @@
+/* { dg-do run}  */
+/* PR target/101529 */
+typedef unsigned char C;
+typedef unsigned char __attribute__((__vector_size__ (8))) V;
+typedef unsigned char __attribute__((__vector_size__ (32))) U;
+
+C c;
+
+/* aarch64 used to miscompile foo to just return a vector of 0s */
+V
+foo (V v)
+{
+  v |= __builtin_shufflevector (c * v, (U) (0 == (U){ }),
+                               0, 1, 8, 32, 8, 20, 36, 36);
+  return v;
+}
+
+int
+main (void)
+{
+  V v = foo ((V) { });
+  for (unsigned i = 0; i < sizeof (v); i++)
+    if (v[i] != (i >= 2 ? 0xff : 0))
+      __builtin_abort ();
+  return 0;
+}