AArch64: div-by-255, ensure that arguments are registers. [PR107988]

At -O0 (as opposed to e.g. volatile) we can get into the situation where the
in0 and result RTL arguments passed to the division function are memory
locations instead of registers.  I think we could reject these early on by
checking that the gimple values are GIMPLE registers, but I think it's better to
handle it.

As such I force them to registers and emit a move to the memory locations and
leave it up to reload to handle.  This fixes the ICE and still allows the
optimization in these cases,  which improves the code quality a lot.

gcc/ChangeLog:

	PR target/107988
	* config/aarch64/aarch64.cc
	(aarch64_vectorize_can_special_div_by_constant): Ensure input and output
	RTL are registers.

gcc/testsuite/ChangeLog:

	PR target/107988
	* gcc.target/aarch64/pr107988-1.c: New test.

2 files changed, 18 insertions, 8 deletions

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 73515c1..9a79a9e 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -24395,7 +24395,8 @@ aarch64_vectorize_can_special_div_by_constant (enum tree_code code,
       || !TYPE_UNSIGNED (vectype))
     return false;
 
-  unsigned int flags = aarch64_classify_vector_mode (TYPE_MODE (vectype));
+  machine_mode mode = TYPE_MODE (vectype);
+  unsigned int flags = aarch64_classify_vector_mode (mode);
   if ((flags & VEC_ANY_SVE) && !TARGET_SVE2)
     return false;
 
@@ -24411,15 +24412,14 @@ aarch64_vectorize_can_special_div_by_constant (enum tree_code code,
   if (in0 == NULL_RTX && in1 == NULL_RTX)
     return true;
 
-  if (!VECTOR_TYPE_P (vectype))
-   return false;
-
   gcc_assert (output);
 
-  if (!*output)
-    *output = gen_reg_rtx (TYPE_MODE (vectype));
-
-  emit_insn (gen_aarch64_bitmask_udiv3 (TYPE_MODE (vectype), *output, in0, in1));
+  expand_operand ops[3];
+  create_output_operand (&ops[0], *output, mode);
+  create_input_operand (&ops[1], in0, mode);
+  create_fixed_operand (&ops[2], in1);
+  expand_insn (insn_code, 3, ops);
+  *output = ops[0].value;
   return true;
 }
 
diff --git a/gcc/testsuite/gcc.target/aarch64/pr107988-1.c b/gcc/testsuite/gcc.target/aarch64/pr107988-1.c
new file mode 100644
index 0000000..c4fd290
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr107988-1.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O0" } */
+typedef unsigned short __attribute__((__vector_size__ (16))) V;
+
+V
+foo (V v)
+{
+  v /= 255;
+  return v;
+}