Improve LTO streaming dumps

this patch cleans up dumping of streaming so it is clear how dump is organized
and how much space individual components needs.

Compiling:

int a=1;
main()
{
  return a;
}

The output is now:

Creating output block for function_body
    Streaming tree  <result_decl 0x7ffff7457a50 D.1931>
     Start of LTO_trees of size 1
      Encoding indexable  <integer_type 0x7ffff7463000 sizetype>  as 0
     10 bytes

^^^ I do not think we should need 10 bytes to stream single indexable reference
to 0 :)

     Start of LTO_trees of size 1
      Encoding indexable  <integer_type 0x7ffff74630a8 bitsizetype>  as 1
     10 bytes
      Streaming header of  <result_decl 0x7ffff7457a50 D.1931>  to function_body
      Streaming body of  <result_decl 0x7ffff7457a50 D.1931>  to function_body
      Encoding indexable  <integer_type 0x7ffff74635e8 int>  as 2
      Encoding indexable  <function_decl 0x7ffff757b500 main>  as 0
      Streaming ref to  <integer_cst 0x7ffff744af18 32>
      Streaming ref to  <integer_cst 0x7ffff744af30 4>
    52 bytes

^^^ Instead of having multiple LTO_trees sections followed by the final tree
it would make a lot of sense to have only one LTO_trees where the first tree
is one lto_input_tree should return.  This is easy to arrange in DFS walk -
one does not need to pop after every SCC component but pop once at the end of
walk.  However this breaks handling of integer_csts because they may now
become of LTO_trees block and streamed as header + body.
This bypasses the separate code for shared integer_cst streaming.  I think
I want to stream everything into header and materialize the tree since it is not
part of SCC anyway.

    Streaming tree  <block 0x7ffff757e420>
      Streaming header of  <block 0x7ffff757e420>  to function_body
      Streaming body of  <block 0x7ffff757e420>  to function_body
    8 bytes
  Streaming gimple stmt _2 = a;
    Streaming ref to  <block 0x7ffff757e420>
    4 bytes
    Streaming tree  <mem_ref 0x7ffff7576f78>
     Start of LTO_trees of size 1
      Encoding indexable  <pointer_type 0x7ffff746b9d8>  as 3
     10 bytes
     Start of LTO_trees of size 1
      Streaming header of  <addr_expr 0x7ffff75893c0>  to function_body
      Streaming body of  <addr_expr 0x7ffff75893c0>  to function_body
      Encoding indexable  <var_decl 0x7ffff7fcfb40 a>  as 0
     15 bytes
      Streaming header of  <mem_ref 0x7ffff7576f78>  to function_body
      Streaming body of  <mem_ref 0x7ffff7576f78>  to function_body
      Streaming ref to  <addr_expr 0x7ffff75893c0>
      Streaming ref to  <integer_cst 0x7ffff75a3240 0>
    42 bytes
  Streaming gimple stmt return _2;

Outputting global stream
 0:  <function_decl 0x7ffff757b500 main>
    Streaming tree  <function_decl 0x7ffff757b500 main>
     Start of LTO_tree_scc of size 1
      Streaming header of  <optimization_node 0x7ffff744b000>  to decls
      Streaming body of  <optimization_node 0x7ffff744b000>  to decls
     576 bytes
     Start of LTO_tree_scc of size 1
      Streaming header of  <target_option_node 0x7ffff744a018>  to decls
      Streaming body of  <target_option_node 0x7ffff744a018>  to decls
     68 bytes
     Streaming single tree
      Streaming header of  <identifier_node 0x7ffff7577aa0 main>  to decls
      Streaming body of  <identifier_node 0x7ffff7577aa0 main>  to decls
     3 bytes
     Streaming single tree
      Streaming header of  <identifier_node 0x7ffff758a8c0 t.c>  to decls
      Streaming body of  <identifier_node 0x7ffff758a8c0 t.c>  to decls
     3 bytes
     Streaming single tree
      Streaming header of  <translation_unit_decl 0x7ffff7457ac8 t.c>  to decls
      Streaming body of  <translation_unit_decl 0x7ffff7457ac8 t.c>  to decls
      Streaming ref to  <identifier_node 0x7ffff758a8c0 t.c>
     22 bytes
     Start of LTO_tree_scc of size 1
      Streaming header of  <function_type 0x7ffff74717e0>  to decls
      Streaming body of  <function_type 0x7ffff74717e0>  to decls
      Streaming ref to  <integer_type 0x7ffff74635e8 int>
      Streaming ref to  <integer_cst 0x7ffff744adc8 8>
      Streaming ref to  <integer_cst 0x7ffff744ade0 1>
      Streaming ref to  <function_type 0x7ffff74717e0>
     38 bytes
     Start of LTO_tree_scc of size 1
      Streaming header of  <function_type 0x7ffff75832a0>  to decls
      Streaming body of  <function_type 0x7ffff75832a0>  to decls
      Streaming ref to  <integer_type 0x7ffff74635e8 int>
      Streaming ref to  <integer_cst 0x7ffff744adc8 8>
      Streaming ref to  <integer_cst 0x7ffff744ade0 1>
      Streaming ref to  <function_type 0x7ffff74717e0>
     38 bytes
     Start of LTO_tree_scc of size 1
      Streaming header of  <function_decl 0x7ffff757b500 main>  to decls
      Streaming body of  <function_decl 0x7ffff757b500 main>  to decls
      Streaming ref to  <function_type 0x7ffff75832a0>
      Streaming ref to  <identifier_node 0x7ffff7577aa0 main>
      Streaming ref to  <translation_unit_decl 0x7ffff7457ac8 t.c>
      Streaming ref to  <identifier_node 0x7ffff7577aa0 main>
      Streaming ref to  <target_option_node 0x7ffff744a018>
      Streaming ref to  <optimization_node 0x7ffff744b000>
     58 bytes
    806 bytes
 0:  <var_decl 0x7ffff7fcfb40 a>
    Streaming tree  <var_decl 0x7ffff7fcfb40 a>
     Streaming single tree
      Streaming header of  <identifier_node 0x7ffff758a870 a>  to decls
      Streaming body of  <identifier_node 0x7ffff758a870 a>  to decls
     3 bytes
     Streaming single tree
      Streaming ref to  <integer_type 0x7ffff7463000 sizetype>
     7 bytes
     Streaming single tree
      Streaming ref to  <integer_type 0x7ffff74630a8 bitsizetype>
     7 bytes
     Start of LTO_tree_scc of size 1
      Streaming header of  <var_decl 0x7ffff7fcfb40 a>  to decls
      Streaming body of  <var_decl 0x7ffff7fcfb40 a>  to decls
      Streaming ref to  <integer_type 0x7ffff74635e8 int>
      Streaming ref to  <identifier_node 0x7ffff758a870 a>
      Streaming ref to  <translation_unit_decl 0x7ffff7457ac8 t.c>
      Streaming ref to  <integer_cst 0x7ffff744af18 32>
      Streaming ref to  <integer_cst 0x7ffff744af30 4>
      Streaming ref to  <identifier_node 0x7ffff758a870 a>
      Streaming ref to  <integer_cst 0x7ffff7468090 1>
     49 bytes
    66 bytes

gcc/ChangeLog:

2020-05-22  Jan Hubicka  <hubicka@ucw.cz>

	* lto-section-out.c (lto_output_decl_index): Adjust dump indentation.
	* lto-streamer-out.c (create_output_block): Fix whitespace
	(lto_write_tree_1): Add (debug) dump.
	(DFS::DFS): Add dump.
	(DFS::DFS_write_tree_body): Do not dump here.
	(lto_output_tree): Improve dumping; do not stream ref when not needed.
	(produce_asm_for_decls): Fix whitespace.
	* tree-streamer-out.c (streamer_write_tree_header): Add dump.

4 files changed, 88 insertions, 29 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 4049ac3..48a9a5f 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,14 @@
+2020-05-22  Jan Hubicka  <hubicka@ucw.cz>
+
+	* lto-section-out.c (lto_output_decl_index): Adjust dump indentation.
+	* lto-streamer-out.c (create_output_block): Fix whitespace
+	(lto_write_tree_1): Add (debug) dump.
+	(DFS::DFS): Add dump.
+	(DFS::DFS_write_tree_body): Do not dump here.
+	(lto_output_tree): Improve dumping; do not stream ref when not needed.
+	(produce_asm_for_decls): Fix whitespace.
+	* tree-streamer-out.c (streamer_write_tree_header): Add dump.
+
 2020-05-22  Hongtao.liu  <hongtao.liu@intel.com>
 
 	PR target/92658
diff --git a/gcc/lto-section-out.c b/gcc/lto-section-out.c
index 8eda3b5..0182cd6 100644
--- a/gcc/lto-section-out.c
+++ b/gcc/lto-section-out.c
@@ -170,7 +170,7 @@ lto_output_decl_index (struct lto_output_stream *obs,
       index = encoder->trees.length ();
       if (streamer_dump_file)
 	{
-	  print_node_brief (streamer_dump_file, "    Encoding indexable ",
+	  print_node_brief (streamer_dump_file, "     Encoding indexable ",
 			    name, 4);
 	  fprintf (streamer_dump_file, "  as %i \n", index);
 	}
diff --git a/gcc/lto-streamer-out.c b/gcc/lto-streamer-out.c
index 09a2e82..f5daadc 100644
--- a/gcc/lto-streamer-out.c
+++ b/gcc/lto-streamer-out.c
@@ -72,7 +72,7 @@ create_output_block (enum lto_section_type section_type)
   struct output_block *ob = XCNEW (struct output_block);
   if (streamer_dump_file)
     fprintf (streamer_dump_file, "Creating output block for %s\n",
-	     lto_section_name [section_type]);
+	     lto_section_name[section_type]);
 
   ob->section_type = section_type;
   ob->decl_state = lto_get_out_decl_state ();
@@ -417,6 +417,14 @@ get_symbol_initial_value (lto_symtab_encoder_t encoder, tree expr)
 static void
 lto_write_tree_1 (struct output_block *ob, tree expr, bool ref_p)
 {
+  if (streamer_dump_file)
+    {
+      print_node_brief (streamer_dump_file, "     Streaming body of ",
+			expr, 4);
+      fprintf (streamer_dump_file, "  to %s\n",
+	       lto_section_name[ob->section_type]);
+    }
+
   /* Pack all the non-pointer fields in EXPR into a bitpack and write
      the resulting bitpack.  */
   streamer_write_tree_bitfields (ob, expr);
@@ -737,6 +745,8 @@ DFS::DFS (struct output_block *ob, tree expr, bool ref_p, bool this_ref_p,
 
 	  worklist_vec.pop ();
 
+	  unsigned int prev_size = ob->main_stream->total_size;
+
 	  /* Only global decl sections are considered by tree merging.  */
 	  if (ob->section_type != LTO_section_decls)
 	    {
@@ -744,6 +754,11 @@ DFS::DFS (struct output_block *ob, tree expr, bool ref_p, bool this_ref_p,
 		 by itself then we do not need to stream SCC at all.  */
 	      if (worklist_vec.is_empty () && first == 0 && size == 1)
 		 return;
+	      if (streamer_dump_file)
+		{
+		  fprintf (streamer_dump_file,
+			   "     Start of LTO_trees of size %i\n", size);
+		}
 	      streamer_write_record_start (ob, LTO_trees);
 	      streamer_write_uhwi (ob, size);
 	    }
@@ -760,6 +775,11 @@ DFS::DFS (struct output_block *ob, tree expr, bool ref_p, bool this_ref_p,
 
 	    {
 	      gcc_checking_assert (ob->section_type == LTO_section_decls);
+	      if (streamer_dump_file)
+		{
+		  fprintf (streamer_dump_file,
+			   "     Start of LTO_tree_scc of size %i\n", size);
+		}
 	      streamer_write_record_start (ob, LTO_tree_scc);
 	      /* In wast majority of cases scc_entry_len is 1 and size is small
 		 integer.  Use extra bit of size to stream info about
@@ -773,8 +793,18 @@ DFS::DFS (struct output_block *ob, tree expr, bool ref_p, bool this_ref_p,
 	     references work correctly.  */
 	  else if (size != 1)
 	    {
-	       streamer_write_record_start (ob, LTO_trees);
-	       streamer_write_uhwi (ob, size);
+	      if (streamer_dump_file)
+		{
+		  fprintf (streamer_dump_file,
+			   "     Start of LTO_trees of size %i\n", size);
+		}
+	      streamer_write_record_start (ob, LTO_trees);
+	      streamer_write_uhwi (ob, size);
+	    }
+	  else if (streamer_dump_file)
+	    {
+	      fprintf (streamer_dump_file,
+		       "     Streaming single tree\n", size);
 	    }
 
 	  /* Write size-1 SCCs without wrapping them inside SCC bundles.
@@ -809,6 +839,9 @@ DFS::DFS (struct output_block *ob, tree expr, bool ref_p, bool this_ref_p,
 	      for (unsigned i = 0; i < size; ++i)
 		lto_write_tree_1 (ob, sccstack[first+i].t, ref_p);
 	    }
+	  if (streamer_dump_file)
+	    fprintf (streamer_dump_file, "     %u bytes\n",
+		     ob->main_stream->total_size - prev_size);
 
 	  /* Finally truncate the vector.  */
 	  sccstack.truncate (first);
@@ -845,14 +878,6 @@ DFS::DFS_write_tree_body (struct output_block *ob,
 
   enum tree_code code;
 
-  if (streamer_dump_file)
-    {
-      print_node_brief (streamer_dump_file, "    Streaming ",
-	 		expr, 4);
-      fprintf (streamer_dump_file, "  to %s\n",
-	       lto_section_name [ob->section_type]);
-    }
-
   code = TREE_CODE (expr);
 
   if (CODE_CONTAINS_STRUCT (code, TS_TYPED))
@@ -1246,7 +1271,7 @@ hash_tree (struct streamer_tree_cache_d *cache, hash_map<tree, hashval_t> *map,
     {
       hstate.add_hwi (TYPE_MODE (t));
       /* TYPE_NO_FORCE_BLK is private to stor-layout and need
- 	 no streaming.  */
+	 no streaming.  */
       hstate.add_flag (TYPE_PACKED (t));
       hstate.add_flag (TYPE_RESTRICT (t));
       hstate.add_flag (TYPE_USER_ALIGN (t));
@@ -1689,6 +1714,10 @@ lto_output_tree (struct output_block *ob, tree expr,
 {
   unsigned ix;
   bool existed_p;
+  unsigned int size = ob->main_stream->total_size;
+  /* This is the first time we see EXPR, write all reachable
+     trees to OB.  */
+  static bool in_dfs_walk;
 
   if (expr == NULL_TREE)
     {
@@ -1705,6 +1734,16 @@ lto_output_tree (struct output_block *ob, tree expr,
   existed_p = streamer_tree_cache_lookup (ob->writer_cache, expr, &ix);
   if (existed_p)
     {
+      if (streamer_dump_file)
+	{
+	  if (in_dfs_walk)
+	    print_node_brief (streamer_dump_file, "     Streaming ref to ",
+			      expr, 4);
+	  else
+	    print_node_brief (streamer_dump_file, "   Streaming ref to ",
+			      expr, 4);
+	  fprintf (streamer_dump_file, "\n");
+	}
       /* If a node has already been streamed out, make sure that
 	 we don't write it more than once.  Otherwise, the reader
 	 will instantiate two different nodes for the same object.  */
@@ -1716,20 +1755,16 @@ lto_output_tree (struct output_block *ob, tree expr,
     }
   else
     {
-      /* This is the first time we see EXPR, write all reachable
-	 trees to OB.  */
-      static bool in_dfs_walk;
-
       /* Protect against recursion which means disconnect between
-         what tree edges we walk in the DFS walk and what edges
+	 what tree edges we walk in the DFS walk and what edges
 	 we stream out.  */
       gcc_assert (!in_dfs_walk);
 
       if (streamer_dump_file)
 	{
-	  print_node_brief (streamer_dump_file, "   Streaming SCC of ",
+	  print_node_brief (streamer_dump_file, "   Streaming tree ",
 			    expr, 4);
-          fprintf (streamer_dump_file, "\n");
+	  fprintf (streamer_dump_file, "\n");
 	}
 
       /* Start the DFS walk.  */
@@ -1737,7 +1772,6 @@ lto_output_tree (struct output_block *ob, tree expr,
       /* let's see ... */
       in_dfs_walk = true;
       DFS (ob, expr, ref_p, this_ref_p, false);
-      in_dfs_walk = false;
 
       /* Finally append a reference to the tree we were writing.  */
       existed_p = streamer_tree_cache_lookup (ob->writer_cache, expr, &ix);
@@ -1748,19 +1782,24 @@ lto_output_tree (struct output_block *ob, tree expr,
 	lto_output_tree_1 (ob, expr, 0, ref_p, this_ref_p);
       else
 	{
+	  if (streamer_dump_file)
+	    {
+	      print_node_brief (streamer_dump_file,
+				"   Streaming final ref to ",
+				expr, 4);
+	      fprintf (streamer_dump_file, "\n");
+	    }
 	  streamer_write_record_start (ob, LTO_tree_pickle_reference);
 	  streamer_write_uhwi (ob, ix);
 	  streamer_write_enum (ob->main_stream, LTO_tags, LTO_NUM_TAGS,
 			       lto_tree_code_to_tag (TREE_CODE (expr)));
 	}
-      if (streamer_dump_file)
-	{
-	  print_node_brief (streamer_dump_file, "   Finished SCC of ",
-			    expr, 4);
-          fprintf (streamer_dump_file, "\n\n");
-	}
+      in_dfs_walk = false;
       lto_stats.num_pickle_refs_output++;
     }
+  if (streamer_dump_file && !in_dfs_walk)
+    fprintf (streamer_dump_file, "    %u bytes\n",
+	     ob->main_stream->total_size - size);
 }
 
 
@@ -2700,7 +2739,7 @@ write_global_stream (struct output_block *ob,
 
 static void
 write_global_references (struct output_block *ob,
- 			 struct lto_tree_ref_encoder *encoder)
+			 struct lto_tree_ref_encoder *encoder)
 {
   tree t;
   uint32_t index;
@@ -3136,7 +3175,7 @@ produce_asm_for_decls (void)
       fn_out_state =
 	lto_function_decl_states[idx];
       if (streamer_dump_file)
-        fprintf (streamer_dump_file, "Outputting stream for %s\n",
+	fprintf (streamer_dump_file, "Outputting stream for %s\n",
 		 IDENTIFIER_POINTER
 		    (DECL_ASSEMBLER_NAME (fn_out_state->fn_decl)));
       lto_output_decl_state_streams (ob, fn_out_state);
diff --git a/gcc/tree-streamer-out.c b/gcc/tree-streamer-out.c
index 127a3d8..724eaf5 100644
--- a/gcc/tree-streamer-out.c
+++ b/gcc/tree-streamer-out.c
@@ -31,6 +31,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "alias.h"
 #include "stor-layout.h"
 #include "gomp-constants.h"
+#include "print-tree.h"
 
 
 /* Output the STRING constant to the string
@@ -967,6 +968,14 @@ streamer_write_tree_header (struct output_block *ob, tree expr)
   enum LTO_tags tag;
   enum tree_code code;
 
+  if (streamer_dump_file)
+    {
+      print_node_brief (streamer_dump_file, "     Streaming header of ",
+	 		expr, 4);
+      fprintf (streamer_dump_file, "  to %s\n",
+	       lto_section_name[ob->section_type]);
+    }
+
   /* We should not see any tree nodes not handled by the streamer.  */
   code = TREE_CODE (expr);