sve2: Fix expansion of division [PR107830]

SVE has an actual division optab, and when using -Os we don't
optimize the division away.  This means that we need to distinguish
between a div which we can optimize and one we cannot even during
expansion.

gcc/ChangeLog:

	PR target/107830
	* config/aarch64/aarch64.cc
	(aarch64_vectorize_can_special_div_by_constant): Check validity during
	codegen phase as well.

gcc/testsuite/ChangeLog:

	PR target/107830
	* gcc.target/aarch64/sve2/pr107830-1.c: New test.
	* gcc.target/aarch64/sve2/pr107830-2.c: New test.

gcc/config/aarch64/aarch64.cc

@@ -24351,12 +24351,17 @@ aarch64_vectorize_can_special_div_by_constant (enum tree_code code,
   if ((flags & VEC_ANY_SVE) && !TARGET_SVE2)
     return false;
 
+  int pow = wi::exact_log2 (cst + 1);
+  auto insn_code = maybe_code_for_aarch64_bitmask_udiv3 (TYPE_MODE (vectype));
+  /* SVE actually has a div operator, we may have gotten here through
+     that route.  */
+  if (pow != (int) (element_precision (vectype) / 2)
+      || insn_code == CODE_FOR_nothing)
+    return false;
+
+  /* We can use the optimized pattern.  */
   if (in0 == NULL_RTX && in1 == NULL_RTX)
-    {
-      wide_int val = wi::add (cst, 1);
-      int pow = wi::exact_log2 (val);
-      return pow == (int)(element_precision (vectype) / 2);
-    }
+    return true;
 
   if (!VECTOR_TYPE_P (vectype))
    return false;

gcc/testsuite/gcc.target/aarch64/sve2/pr107830-1.c

@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target fopenmp } */
+/* { dg-additional-options "-Os -fopenmp" } */
+
+void
+f2 (int *a)
+{
+  unsigned int i;
+
+#pragma omp simd
+  for (i = 0; i < 4; ++i)
+    a[i / 3] -= 4;
+}

gcc/testsuite/gcc.target/aarch64/sve2/pr107830-2.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3 -msve-vector-bits=512" } */
+
+void f(unsigned short *restrict p1, unsigned int *restrict p2)
+{
+    for (int i = 0; i < 16; ++i)
+      {
+        p1[i] /= 0xff;
+        p2[i] += 1;
+      }
+}
+