Mark omp thread functions as parallelized

2015-03-21  Tom de Vries  <tom@codesourcery.com>

	PR tree-optimization/65458
	* cgraph.c (cgraph_node::dump): Handle parallelized_function field.
	* cgraph.h (cgraph_node): Add parallelized_function field.
	* lto-cgraph.c (lto_output_node): Write parallelized_function field.
	(input_overwrite_node): Read parallelized_function field.
	* omp-low.c (expand_omp_taskreg, finalize_task_copyfn): Set
	parallelized_function on cgraph_node for child_fn.
	* tree-parloops.c: Add include of plugin-api.h, ipa-ref.h and cgraph.h.
	Remove include of gt-tree-parloops.h.
	(parallelized_functions): Remove static variable.
	(parallelized_function_p): Rewrite using parallelized_function field of
	cgraph_node.
	(create_loop_fn): Remove adding to parallelized_functions.
	* Makefile.in (GTFILES): Remove tree-parloops.c

From-SVN: r221551

gcc/ChangeLog

@@ -1,3 +1,20 @@
+2015-03-21  Tom de Vries  <tom@codesourcery.com>
+
+	PR tree-optimization/65458
+	* cgraph.c (cgraph_node::dump): Handle parallelized_function field.
+	* cgraph.h (cgraph_node): Add parallelized_function field.
+	* lto-cgraph.c (lto_output_node): Write parallelized_function field.
+	(input_overwrite_node): Read parallelized_function field.
+	* omp-low.c (expand_omp_taskreg, finalize_task_copyfn): Set
+	parallelized_function on cgraph_node for child_fn.
+	* tree-parloops.c: Add include of plugin-api.h, ipa-ref.h and cgraph.h.
+	Remove include of gt-tree-parloops.h.
+	(parallelized_functions): Remove static variable.
+	(parallelized_function_p): Rewrite using parallelized_function field of
+	cgraph_node.
+	(create_loop_fn): Remove adding to parallelized_functions.
+	* Makefile.in (GTFILES): Remove tree-parloops.c
+
 2015-03-20  Vladimir Makarov  <vmakarov@redhat.com>
 
 	PR rtl-optimization/64366

gcc/Makefile.in

@@ -2321,7 +2321,6 @@ GTFILES = $(CPP_ID_DATA_H) $(srcdir)/input.h $(srcdir)/coretypes.h \
   $(srcdir)/tree-scalar-evolution.c \
   $(srcdir)/tree-ssa-operands.h \
   $(srcdir)/tree-profile.c $(srcdir)/tree-nested.c \
-  $(srcdir)/tree-parloops.c \
   $(srcdir)/omp-low.c \
   $(srcdir)/omp-low.h \
   $(srcdir)/targhooks.c $(out_file) $(srcdir)/passes.c $(srcdir)/cgraphunit.c \

gcc/cgraph.c

@@ -2008,6 +2008,8 @@ cgraph_node::dump (FILE *f)
     fprintf (f, " only_called_at_exit");
   if (opt_for_fn (decl, optimize_size))
     fprintf (f, " optimize_size");
+  if (parallelized_function)
+    fprintf (f, " parallelized_function");
 
   fprintf (f, "\n");
 

gcc/cgraph.h

@@ -1317,6 +1317,8 @@ public:
   unsigned nonfreeing_fn : 1;
   /* True if there was multiple COMDAT bodies merged by lto-symtab.  */
   unsigned merged : 1;
+  /* True if function was created to be executed in parallel.  */
+  unsigned parallelized_function : 1;
 
 private:
   /* Worker for call_for_symbol_and_aliases.  */

gcc/lto-cgraph.c

@@ -574,6 +574,7 @@ lto_output_node (struct lto_simple_output_block *ob, struct cgraph_node *node,
   bp_pack_value (&bp, node->icf_merged, 1);
   bp_pack_value (&bp, node->nonfreeing_fn, 1);
   bp_pack_value (&bp, node->thunk.thunk_p, 1);
+  bp_pack_value (&bp, node->parallelized_function, 1);
   bp_pack_enum (&bp, ld_plugin_symbol_resolution,
 	        LDPR_NUM_KNOWN, node->resolution);
   bp_pack_value (&bp, node->instrumentation_clone, 1);
@@ -1209,6 +1210,7 @@ input_overwrite_node (struct lto_file_decl_data *file_data,
   node->icf_merged = bp_unpack_value (bp, 1);
   node->nonfreeing_fn = bp_unpack_value (bp, 1);
   node->thunk.thunk_p = bp_unpack_value (bp, 1);
+  node->parallelized_function = bp_unpack_value (bp, 1);
   node->resolution = bp_unpack_enum (bp, ld_plugin_symbol_resolution,
 				     LDPR_NUM_KNOWN);
   node->instrumentation_clone = bp_unpack_value (bp, 1);

gcc/omp-low.c

@@ -1564,6 +1564,7 @@ finalize_task_copyfn (gomp_task *task_stmt)
 
   /* Inform the callgraph about the new function.  */
   cgraph_node::add_new_function (child_fn, false);
+  cgraph_node::get (child_fn)->parallelized_function = 1;
 }
 
 /* Destroy a omp_context data structures.  Called through the splay tree
@@ -5569,6 +5570,7 @@ expand_omp_taskreg (struct omp_region *region)
       /* Inform the callgraph about the new function.  */
       DECL_STRUCT_FUNCTION (child_fn)->curr_properties = cfun->curr_properties;
       cgraph_node::add_new_function (child_fn, true);
+      cgraph_node::get (child_fn)->parallelized_function = 1;
 
       /* Fix the callgraph edges for child_cfun.  Those for cfun will be
 	 fixed in a following pass.  */

gcc/tree-parloops.c

@@ -75,6 +75,9 @@ along with GCC; see the file COPYING3.  If not see
 #include "tree-parloops.h"
 #include "omp-low.h"
 #include "tree-nested.h"
+#include "plugin-api.h"
+#include "ipa-ref.h"
+#include "cgraph.h"
 
 /* This pass tries to distribute iterations of loops into several threads.
    The implementation is straightforward -- for each loop we test whether its
@@ -1422,21 +1425,14 @@ separate_decls_in_region (edge entry, edge exit,
     }
 }
 
-/* Bitmap containing uids of functions created by parallelization.  We cannot
-   allocate it from the default obstack, as it must live across compilation
-   of several functions; we make it gc allocated instead.  */
-
-static GTY(()) bitmap parallelized_functions;
-
-/* Returns true if FN was created by create_loop_fn.  */
+/* Returns true if FN was created to run in parallel.  */
 
 bool
-parallelized_function_p (tree fn)
+parallelized_function_p (tree fndecl)
 {
-  if (!parallelized_functions || !DECL_ARTIFICIAL (fn))
-    return false;
-
-  return bitmap_bit_p (parallelized_functions, DECL_UID (fn));
+  cgraph_node *node = cgraph_node::get (fndecl);
+  gcc_assert (node != NULL);
+  return node->parallelized_function;
 }
 
 /* Creates and returns an empty function that will receive the body of
@@ -1459,10 +1455,6 @@ create_loop_fn (location_t loc)
   type = build_function_type_list (void_type_node, ptr_type_node, NULL_TREE);
 
   decl = build_decl (loc, FUNCTION_DECL, name, type);
-  if (!parallelized_functions)
-    parallelized_functions = BITMAP_GGC_ALLOC ();
-  bitmap_set_bit (parallelized_functions, DECL_UID (decl));
-
   TREE_STATIC (decl) = 1;
   TREE_USED (decl) = 1;
   DECL_ARTIFICIAL (decl) = 1;
@@ -2314,6 +2306,3 @@ make_pass_parallelize_loops (gcc::context *ctxt)
 {
   return new pass_parallelize_loops (ctxt);
 }
-
-
-#include "gt-tree-parloops.h"