middle-end: don't keep .MEM guard nodes for PHI nodes who dominate loop [PR111860]

The previous patch tried to remove PHI nodes that dominated the first loop,
however the correct fix is to only remove .MEM nodes.

This patch thus makes the condition a bit stricter and only tries to remove
MEM phi nodes.

I couldn't figure out a way to easily determine if a particular PHI is vUSE
related, so the patch does:

1. check if the definition is a vDEF and not defined in main loop.
2. check if the definition is a PHI and not defined in main loop.
3. check if the definition is a default definition.

For no 2 and 3 we may misidentify the PHI, in both cases the value is defined
outside of the loop version block which also makes it ok to remove.

gcc/ChangeLog:

	PR tree-optimization/111860
	* tree-vect-loop-manip.cc (slpeel_tree_duplicate_loop_to_edge_cfg):
	Drop .MEM nodes only.

gcc/testsuite/ChangeLog:

	PR tree-optimization/111860
	* gcc.dg/vect/pr111860-2.c: New test.
	* gcc.dg/vect/pr111860-3.c: New test.

3 files changed, 54 insertions, 1 deletions

diff --git a/gcc/testsuite/gcc.dg/vect/pr111860-2.c b/gcc/testsuite/gcc.dg/vect/pr111860-2.c
new file mode 100644
index 0000000..07f64ff
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr111860-2.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O -fno-tree-sink -ftree-vectorize" } */
+int buffer_ctrl_ctx_0, buffer_ctrl_p1, buffer_ctrl_cmd;
+
+int
+buffer_ctrl (long ret, int i)
+{
+  switch (buffer_ctrl_cmd)
+    {
+    case 1:
+      buffer_ctrl_ctx_0 = 0;
+      for (; i; i++)
+	if (buffer_ctrl_p1)
+	  ret++;
+    }
+  return ret;
+}
diff --git a/gcc/testsuite/gcc.dg/vect/pr111860-3.c b/gcc/testsuite/gcc.dg/vect/pr111860-3.c
new file mode 100644
index 0000000..07f64ff
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr111860-3.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O -fno-tree-sink -ftree-vectorize" } */
+int buffer_ctrl_ctx_0, buffer_ctrl_p1, buffer_ctrl_cmd;
+
+int
+buffer_ctrl (long ret, int i)
+{
+  switch (buffer_ctrl_cmd)
+    {
+    case 1:
+      buffer_ctrl_ctx_0 = 0;
+      for (; i; i++)
+	if (buffer_ctrl_p1)
+	  ret++;
+    }
+  return ret;
+}
diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc
index d67c947..43ca985 100644
--- a/gcc/tree-vect-loop-manip.cc
+++ b/gcc/tree-vect-loop-manip.cc
@@ -1626,12 +1626,31 @@ slpeel_tree_duplicate_loop_to_edge_cfg (class loop *loop, edge loop_exit,
 	  edge temp_e = redirect_edge_and_branch (exit, new_preheader);
 	  flush_pending_stmts (temp_e);
 	}
-
       /* Record the new SSA names in the cache so that we can skip materializing
 	 them again when we fill in the rest of the LCSSA variables.  */
       for (auto phi : new_phis)
 	{
 	  tree new_arg = gimple_phi_arg (phi, 0)->def;
+
+	  if (!SSA_VAR_P (new_arg))
+	    continue;
+	  /* If the PHI MEM node dominates the loop then we shouldn't create
+	      a new LC-SSSA PHI for it in the intermediate block.   */
+	  /* A MEM phi that consitutes a new DEF for the vUSE chain can either
+	     be a .VDEF or a PHI that operates on MEM. And said definition
+	     must not be inside the main loop.  Or we must be a parameter.
+	     In the last two cases we may remove a non-MEM PHI node, but since
+	     they dominate both loops the removal is unlikely to cause trouble
+	     as the exits must already be using them.  */
+	  if (virtual_operand_p (new_arg)
+	      && (SSA_NAME_IS_DEFAULT_DEF (new_arg)
+		  || !flow_bb_inside_loop_p (loop,
+				gimple_bb (SSA_NAME_DEF_STMT (new_arg)))))
+	    {
+	      auto gsi = gsi_for_stmt (phi);
+	      remove_phi_node (&gsi, true);
+	      continue;
+	    }
 	  new_phi_args.put (new_arg, gimple_phi_result (phi));
 
 	  if (TREE_CODE (new_arg) != SSA_NAME)