Re: Use separate sections to stream non-trivial constructors

[Jan Hubicka <hubicka@ucw.cz>]

Hi
this is patch i am going to commit after testing.  It removes DECL_INIT_IO
timevar that guards only one variable set (so hardly measure anything) and
moves GIMPLE_IN to proper place. It also adds CTORS_IN and CTORS_OUT.
I get:
 ipa lto gimple out      :   0.37 ( 0%) usr   0.21 ( 3%) sys   0.64 ( 1%) wall       0 kB ( 0%) ggc
 ipa lto decl in         :  23.56 (26%) usr   1.24 (15%) sys  24.81 (23%) wall 2429174 kB (60%) ggc
 ipa lto decl out        :   5.58 ( 6%) usr   0.34 ( 4%) sys   5.94 ( 5%) wall       0 kB ( 0%) ggc
 ipa lto constructors in :   0.34 ( 0%) usr   0.10 ( 1%) sys   0.47 ( 0%) wall   14864 kB ( 0%) ggc
 ipa lto constructors out:   0.06 ( 0%) usr   0.01 ( 0%) sys   0.01 ( 0%) wall       0 kB ( 0%) ggc
 ipa lto cgraph I/O      :   1.20 ( 1%) usr   0.25 ( 3%) sys   1.45 ( 1%) wall  437317 kB (11%) ggc

for Firefox WPA that is surprisingly good. We traded about 400MB for 14MB. So perhaps I do not
need to care about not bringing in all vtables needed for devirt machinery.

honza

	* lto.c (read_cgraph_and_symbols): Do not push DECL_INIT_IO
	timevar
	(materialize_cgraph): Do not push GIMPLE_IN timevar.

	* timevar.def (TV_IPA_LTO_DECL_INIT_IO): Remove.
	(TV_IPA_LTO_CTORS_IN, TV_IPA_LTO_CTORS_OUT): New timevar.
	* cgraph.c (cgraph_get_body): Push GIMPLE_IN timevar.
	(varpool_get_constructor): Push CTORS_IN timevar.
	* lto-streamer-out.c (lto_output): Push TV_IPA_LTO_CTORS_OUT
	timevar.
Index: lto/lto.c
===================================================================
--- lto/lto.c	(revision 212467)
+++ lto/lto.c	(working copy)
@@ -3094,12 +3094,9 @@ read_cgraph_and_symbols (unsigned nfiles
 
   timevar_pop (TV_IPA_LTO_CGRAPH_MERGE);
 
-  timevar_push (TV_IPA_LTO_DECL_INIT_IO);
-
   /* Indicate that the cgraph is built and ready.  */
   cgraph_function_flags_ready = true;
 
-  timevar_pop (TV_IPA_LTO_DECL_INIT_IO);
   ggc_free (all_file_decl_data);
   all_file_decl_data = NULL;
 }
@@ -3117,9 +3114,6 @@ materialize_cgraph (void)
     fprintf (stderr,
 	     flag_wpa ? "Materializing decls:" : "Reading function bodies:");
 
-  /* Now that we have input the cgraph, we need to clear all of the aux
-     nodes and read the functions if we are not running in WPA mode.  */
-  timevar_push (TV_IPA_LTO_GIMPLE_IN);
 
   FOR_EACH_FUNCTION (node)
     {
@@ -3130,7 +3124,6 @@ materialize_cgraph (void)
 	}
     }
 
-  timevar_pop (TV_IPA_LTO_GIMPLE_IN);
 
   /* Start the appropriate timer depending on the mode that we are
      operating in.  */
Index: timevar.def
===================================================================
--- timevar.def	(revision 212457)
+++ timevar.def	(working copy)
@@ -77,7 +77,8 @@ DEFTIMEVAR (TV_IPA_LTO_GIMPLE_IN     , "
 DEFTIMEVAR (TV_IPA_LTO_GIMPLE_OUT    , "ipa lto gimple out")
 DEFTIMEVAR (TV_IPA_LTO_DECL_IN       , "ipa lto decl in")
 DEFTIMEVAR (TV_IPA_LTO_DECL_OUT      , "ipa lto decl out")
-DEFTIMEVAR (TV_IPA_LTO_DECL_INIT_IO  , "ipa lto decl init I/O")
+DEFTIMEVAR (TV_IPA_LTO_CTORS_IN      , "ipa lto constructors in")
+DEFTIMEVAR (TV_IPA_LTO_CTORS_OUT     , "ipa lto constructors out")
 DEFTIMEVAR (TV_IPA_LTO_CGRAPH_IO     , "ipa lto cgraph I/O")
 DEFTIMEVAR (TV_IPA_LTO_DECL_MERGE    , "ipa lto decl merge")
 DEFTIMEVAR (TV_IPA_LTO_CGRAPH_MERGE  , "ipa lto cgraph merge")
Index: cgraph.c
===================================================================
--- cgraph.c	(revision 212457)
+++ cgraph.c	(working copy)
@@ -3053,6 +3053,8 @@ cgraph_get_body (struct cgraph_node *nod
 
   gcc_assert (in_lto_p);
 
+  timevar_push (TV_IPA_LTO_GIMPLE_IN);
+
   file_data = node->lto_file_data;
   name = IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl));
 
@@ -3076,6 +3078,9 @@ cgraph_get_body (struct cgraph_node *nod
   lto_free_section_data (file_data, LTO_section_function_body, name,
 			 data, len);
   lto_free_function_in_decl_state_for_node (node);
+
+  timevar_pop (TV_IPA_LTO_GIMPLE_IN);
+
   return true;
 }
 
Index: varpool.c
===================================================================
--- varpool.c	(revision 212467)
+++ varpool.c	(working copy)
@@ -268,6 +268,8 @@ varpool_get_constructor (struct varpool_
       || !in_lto_p)
     return DECL_INITIAL (node->decl);
 
+  timevar_push (TV_IPA_LTO_CTORS_IN);
+
   file_data = node->lto_file_data;
   name = IDENTIFIER_POINTER (DECL_ASSEMBLER_NAME (decl));
 
@@ -286,6 +288,7 @@ varpool_get_constructor (struct varpool_
   lto_free_section_data (file_data, LTO_section_function_body, name,
 			 data, len);
   lto_free_function_in_decl_state_for_node (node);
+  timevar_pop (TV_IPA_LTO_CTORS_IN);
   return DECL_INITIAL (node->decl);
 }
 
Index: lto-streamer-out.c
===================================================================
--- lto-streamer-out.c	(revision 212467)
+++ lto-streamer-out.c	(working copy)
@@ -2115,6 +2115,7 @@ lto_output (void)
 	      && lto_symtab_encoder_encode_initializer_p (encoder, node)
 	      && !node->alias)
 	    {
+	      timevar_push (TV_IPA_LTO_CTORS_OUT);
 #ifdef ENABLE_CHECKING
 	      gcc_assert (!bitmap_bit_p (output, DECL_UID (node->decl)));
 	      bitmap_set_bit (output, DECL_UID (node->decl));
@@ -2129,6 +2130,7 @@ lto_output (void)
 	      gcc_assert (lto_get_out_decl_state () == decl_state);
 	      lto_pop_out_decl_state ();
 	      lto_record_function_out_decl_state (node->decl, decl_state);
+	      timevar_pop (TV_IPA_LTO_CTORS_OUT);
 	    }
 	}
     }