Materialize clones on demand

this patch removes the pass to materialize all clones and instead this
is now done on demand.  The motivation is to reduce lifetime of function
bodies in ltrans that should noticeably reduce memory use for highly
parallel compilations of large programs (like Martin does) or with
partitioning reduced/disabled. For cc1 with one partition the memory use
seems to go down from 4gb to cca 1.5gb (seeing from top, so this is not
particularly accurate).

gcc/ChangeLog:

2020-10-22  Jan Hubicka  <hubicka@ucw.cz>

	* cgraph.c (cgraph_node::get_untransformed_body): Perform lazy
	clone materialization.
	* cgraph.h (cgraph_node::materialize_clone): Declare.
	(symbol_table::materialize_all_clones): Remove.
	* cgraphclones.c (cgraph_materialize_clone): Turn to ...
	(cgraph_node::materialize_clone): .. this one; move here
	dumping from symbol_table::materialize_all_clones.
	(symbol_table::materialize_all_clones): Remove.
	* cgraphunit.c (mark_functions_to_output): Clear stmt references.
	(cgraph_node::expand): Initialize bitmaps early;
	do not call execute_all_ipa_transforms if there are no transforms.
	* ipa-inline-transform.c (save_inline_function_body): Fix formating.
	(inline_transform): Materialize all clones before function is modified.
	* ipa-param-manipulation.c (ipa_param_adjustments::modify_call):
	Materialize clone if needed.
	* ipa.c (class pass_materialize_all_clones): Remove.
	(make_pass_materialize_all_clones): Remove.
	* passes.c (execute_all_ipa_transforms): Materialize all clones.
	* passes.def: Remove pass_materialize_all_clones.
	* tree-pass.h (make_pass_materialize_all_clones): Remove.
	* tree-ssa-structalias.c (ipa_pta_execute): Clear refs.

1 files changed, 40 insertions, 97 deletions

diff --git a/gcc/cgraphclones.c b/gcc/cgraphclones.c
index f920dcb..07a51a5 100644
--- a/gcc/cgraphclones.c
+++ b/gcc/cgraphclones.c
@@ -1083,114 +1083,57 @@ void cgraph_node::remove_from_clone_tree ()
 
 /* Given virtual clone, turn it into actual clone.  */
 
-static void
-cgraph_materialize_clone (cgraph_node *node)
-{
-  bitmap_obstack_initialize (NULL);
-  node->former_clone_of = node->clone_of->decl;
-  if (node->clone_of->former_clone_of)
-    node->former_clone_of = node->clone_of->former_clone_of;
-  /* Copy the OLD_VERSION_NODE function tree to the new version.  */
-  tree_function_versioning (node->clone_of->decl, node->decl,
-			    node->clone.tree_map, node->clone.param_adjustments,
-			    true, NULL, NULL);
-  if (symtab->dump_file)
-    {
-      dump_function_to_file (node->clone_of->decl, symtab->dump_file,
-			     dump_flags);
-      dump_function_to_file (node->decl, symtab->dump_file, dump_flags);
-    }
-
-  cgraph_node *clone_of = node->clone_of;
-  /* Function is no longer clone.  */
-  node->remove_from_clone_tree ();
-  if (!clone_of->analyzed && !clone_of->clones)
-    {
-      clone_of->release_body ();
-      clone_of->remove_callees ();
-      clone_of->remove_all_references ();
-    }
-  bitmap_obstack_release (NULL);
-}
-
-/* Once all functions from compilation unit are in memory, produce all clones
-   and update all calls.  We might also do this on demand if we don't want to
-   bring all functions to memory prior compilation, but current WHOPR
-   implementation does that and it is a bit easier to keep everything right in
-   this order.  */
-
 void
-symbol_table::materialize_all_clones (void)
+cgraph_node::materialize_clone ()
 {
-  cgraph_node *node;
-  bool stabilized = false;
-  
-
+  clone_of->get_untransformed_body ();
+  former_clone_of = clone_of->decl;
+  if (clone_of->former_clone_of)
+    former_clone_of = clone_of->former_clone_of;
   if (symtab->dump_file)
-    fprintf (symtab->dump_file, "Materializing clones\n");
-
-  cgraph_node::checking_verify_cgraph_nodes ();
-
-  /* We can also do topological order, but number of iterations should be
-     bounded by number of IPA passes since single IPA pass is probably not
-     going to create clones of clones it created itself.  */
-  while (!stabilized)
     {
-      stabilized = true;
-      FOR_EACH_FUNCTION (node)
+      fprintf (symtab->dump_file, "cloning %s to %s\n",
+	       clone_of->dump_name (),
+	       dump_name ());
+      if (clone.tree_map)
         {
-	  if (node->clone_of && node->decl != node->clone_of->decl
-	      && !gimple_has_body_p (node->decl))
+	  fprintf (symtab->dump_file, "    replace map:");
+	  for (unsigned int i = 0;
+	       i < vec_safe_length (clone.tree_map);
+	       i++)
 	    {
-	      if (!node->clone_of->clone_of)
-		node->clone_of->get_untransformed_body ();
-	      if (gimple_has_body_p (node->clone_of->decl))
-	        {
-		  if (symtab->dump_file)
-		    {
-		      fprintf (symtab->dump_file, "cloning %s to %s\n",
-			       node->clone_of->dump_name (),
-			       node->dump_name ());
-		      if (node->clone.tree_map)
-		        {
-			  unsigned int i;
-			  fprintf (symtab->dump_file, "    replace map:");
-			  for (i = 0;
-			       i < vec_safe_length (node->clone.tree_map);
-			       i++)
-			    {
-			      ipa_replace_map *replace_info;
-			      replace_info = (*node->clone.tree_map)[i];
-			      fprintf (symtab->dump_file, "%s %i -> ",
-				       i ? "," : "", replace_info->parm_num);
-			      print_generic_expr (symtab->dump_file,
-						  replace_info->new_tree);
-			    }
-			  fprintf (symtab->dump_file, "\n");
-			}
-		      if (node->clone.param_adjustments)
-			node->clone.param_adjustments->dump (symtab->dump_file);
-		    }
-		  cgraph_materialize_clone (node);
-		  stabilized = false;
-	        }
+	      ipa_replace_map *replace_info;
+	      replace_info = (*clone.tree_map)[i];
+	      fprintf (symtab->dump_file, "%s %i -> ",
+		       i ? "," : "", replace_info->parm_num);
+	      print_generic_expr (symtab->dump_file,
+				  replace_info->new_tree);
 	    }
+	  fprintf (symtab->dump_file, "\n");
 	}
+      if (clone.param_adjustments)
+	clone.param_adjustments->dump (symtab->dump_file);
     }
-  FOR_EACH_FUNCTION (node)
-    if (!node->analyzed && node->callees)
-      {
-	node->remove_callees ();
-	node->remove_all_references ();
-      }
-    else
-      node->clear_stmts_in_references ();
+  /* Copy the OLD_VERSION_NODE function tree to the new version.  */
+  tree_function_versioning (clone_of->decl, decl,
+			    clone.tree_map, clone.param_adjustments,
+			    true, NULL, NULL);
   if (symtab->dump_file)
-    fprintf (symtab->dump_file, "Materialization Call site updates done.\n");
-
-  cgraph_node::checking_verify_cgraph_nodes ();
+    {
+      dump_function_to_file (clone_of->decl, symtab->dump_file,
+			     dump_flags);
+      dump_function_to_file (decl, symtab->dump_file, dump_flags);
+    }
 
-  symtab->remove_unreachable_nodes (symtab->dump_file);
+  cgraph_node *this_clone_of = clone_of;
+  /* Function is no longer clone.  */
+  remove_from_clone_tree ();
+  if (!this_clone_of->analyzed && !this_clone_of->clones)
+    {
+      this_clone_of->release_body ();
+      this_clone_of->remove_callees ();
+      this_clone_of->remove_all_references ();
+    }
 }
 
 #include "gt-cgraphclones.h"