predict.c (drop_profile): New function.

2013-11-12  Teresa Johnson  <tejohnson@google.com>
	    Jan Hubicka  <jh@suse.cz>

	* predict.c (drop_profile): New function.
	(handle_missing_profiles): Ditto.
	(counts_to_freqs): Don't overwrite estimated frequencies
	when function has no profile counts.
	* predict.h (handle_missing_profiles): Declare.
	* tree-inline.c (freqs_to_counts): New function.
	(copy_cfg_body): Invoke freqs_to_counts as needed.
	* tree-profile.c (tree_profiling): Invoke handle_missing_profiles.

Co-Authored-By: Jan Hubicka <jh@suse.cz>

From-SVN: r204704

gcc/ChangeLog

@@ -1,3 +1,15 @@
+2013-11-12  Teresa Johnson  <tejohnson@google.com>
+	    Jan Hubicka  <jh@suse.cz>
+
+	* predict.c (drop_profile): New function.
+	(handle_missing_profiles): Ditto.
+	(counts_to_freqs): Don't overwrite estimated frequencies
+	when function has no profile counts.
+	* predict.h (handle_missing_profiles): Declare.
+	* tree-inline.c (freqs_to_counts): New function.
+	(copy_cfg_body): Invoke freqs_to_counts as needed.
+	* tree-profile.c (tree_profiling): Invoke handle_missing_profiles.
+
 2013-11-12  H.J. Lu  <hongjiu.lu@intel.com>
 
 	PR target/59088

gcc/predict.c

@@ -2765,6 +2765,116 @@ estimate_loops (void)
   BITMAP_FREE (tovisit);
 }
 
+/* Drop the profile for NODE to guessed, and update its frequency based on
+   whether it is expected to be HOT.  */
+
+static void
+drop_profile (struct cgraph_node *node, bool hot)
+{
+  struct function *fn = DECL_STRUCT_FUNCTION (node->decl);
+
+  if (dump_file)
+    fprintf (dump_file,
+             "Dropping 0 profile for %s/%i. %s based on calls.\n",
+             cgraph_node_name (node), node->order,
+             hot ? "Function is hot" : "Function is normal");
+  /* We only expect to miss profiles for functions that are reached
+     via non-zero call edges in cases where the function may have
+     been linked from another module or library (COMDATs and extern
+     templates). See the comments below for handle_missing_profiles.  */
+  if (!DECL_COMDAT (node->decl) && !DECL_EXTERNAL (node->decl))
+    {
+      if (flag_profile_correction)
+        {
+          if (dump_file)
+            fprintf (dump_file,
+                     "Missing counts for called function %s/%i\n",
+                     cgraph_node_name (node), node->order);
+        }
+      else
+        error ("Missing counts for called function %s/%i",
+               cgraph_node_name (node), node->order);
+    }
+
+  profile_status_for_function (fn)
+      = (flag_guess_branch_prob ? PROFILE_GUESSED : PROFILE_ABSENT);
+  node->frequency
+      = hot ? NODE_FREQUENCY_HOT : NODE_FREQUENCY_NORMAL;
+}
+
+/* In the case of COMDAT routines, multiple object files will contain the same
+   function and the linker will select one for the binary. In that case
+   all the other copies from the profile instrument binary will be missing
+   profile counts. Look for cases where this happened, due to non-zero
+   call counts going to 0-count functions, and drop the profile to guessed
+   so that we can use the estimated probabilities and avoid optimizing only
+   for size.
+   
+   The other case where the profile may be missing is when the routine
+   is not going to be emitted to the object file, e.g. for "extern template"
+   class methods. Those will be marked DECL_EXTERNAL. Emit a warning in
+   all other cases of non-zero calls to 0-count functions.  */
+
+void
+handle_missing_profiles (void)
+{
+  struct cgraph_node *node;
+  int unlikely_count_fraction = PARAM_VALUE (UNLIKELY_BB_COUNT_FRACTION);
+  vec<struct cgraph_node *> worklist;
+  worklist.create (64);
+
+  /* See if 0 count function has non-0 count callers.  In this case we
+     lost some profile.  Drop its function profile to PROFILE_GUESSED.  */
+  FOR_EACH_DEFINED_FUNCTION (node)
+    {
+      struct cgraph_edge *e;
+      gcov_type call_count = 0;
+      struct function *fn = DECL_STRUCT_FUNCTION (node->decl);
+
+      if (node->count)
+        continue;
+      for (e = node->callers; e; e = e->next_caller)
+        call_count += e->count;
+      if (call_count
+          && fn && fn->cfg
+          && (call_count * unlikely_count_fraction >= profile_info->runs))
+        {
+          bool maybe_hot = maybe_hot_count_p (NULL, call_count);
+
+          drop_profile (node, maybe_hot);
+          worklist.safe_push (node);
+        }
+    }
+
+  /* Propagate the profile dropping to other 0-count COMDATs that are
+     potentially called by COMDATs we already dropped the profile on.  */
+  while (worklist.length () > 0)
+    {
+      struct cgraph_edge *e;
+
+      node = worklist.pop ();
+      for (e = node->callees; e; e = e->next_caller)
+        {
+          struct cgraph_node *callee = e->callee;
+          struct function *fn = DECL_STRUCT_FUNCTION (callee->decl);
+
+          if (callee->count > 0)
+            continue;
+          if (DECL_COMDAT (callee->decl) && fn && fn->cfg
+              && profile_status_for_function (fn) == PROFILE_READ)
+            {
+              /* Since there are no non-0 call counts to this function,
+                 we don't know for sure whether it is hot. Indicate to
+                 the drop_profile routine that function should be marked
+                 normal, rather than hot.  */
+              drop_profile (node, false);
+              worklist.safe_push (callee);
+            }
+        }
+    }
+  worklist.release ();
+}
+
 /* Convert counts measured by profile driven feedback to frequencies.
    Return nonzero iff there was any nonzero execution count.  */
 
@@ -2774,6 +2884,12 @@ counts_to_freqs (void)
   gcov_type count_max, true_count_max = 0;
   basic_block bb;
 
+  /* Don't overwrite the estimated frequencies when the profile for
+     the function is missing.  We may drop this function PROFILE_GUESSED
+     later in drop_profile ().  */
+  if (!ENTRY_BLOCK_PTR->count)
+    return 0;
+
   FOR_BB_BETWEEN (bb, ENTRY_BLOCK_PTR, NULL, next_bb)
     true_count_max = MAX (bb->count, true_count_max);
 

gcc/predict.h

@@ -37,6 +37,7 @@ enum prediction
 
 extern void predict_insn_def (rtx, enum br_predictor, enum prediction);
 extern int counts_to_freqs (void);
+extern void handle_missing_profiles (void);
 extern void estimate_bb_frequencies (bool);
 extern const char *predictor_name (enum br_predictor);
 extern tree build_predict_expr (enum br_predictor, enum prediction);

gcc/tree-inline.c

@@ -2353,6 +2353,29 @@ redirect_all_calls (copy_body_data * id, basic_block bb)
     }
 }
 
+/* Convert estimated frequencies into counts for NODE, scaling COUNT
+   with each bb's frequency. Used when NODE has a 0-weight entry
+   but we are about to inline it into a non-zero count call bb.
+   See the comments for handle_missing_profiles() in predict.c for
+   when this can happen for COMDATs.  */
+
+void
+freqs_to_counts (struct cgraph_node *node, gcov_type count)
+{
+  basic_block bb;
+  edge_iterator ei;
+  edge e;
+  struct function *fn = DECL_STRUCT_FUNCTION (node->decl);
+
+  FOR_ALL_BB_FN(bb, fn)
+    {
+      bb->count = apply_scale (count,
+                               GCOV_COMPUTE_SCALE (bb->frequency, BB_FREQ_MAX));
+      FOR_EACH_EDGE (e, ei, bb->succs)
+        e->count = apply_probability (e->src->count, e->probability);
+    }
+}
+
 /* Make a copy of the body of FN so that it can be inserted inline in
    another function.  Walks FN via CFG, returns new fndecl.  */
 
@@ -2373,6 +2396,24 @@ copy_cfg_body (copy_body_data * id, gcov_type count, int frequency_scale,
   int incoming_frequency = 0;
   gcov_type incoming_count = 0;
 
+  /* This can happen for COMDAT routines that end up with 0 counts
+     despite being called (see the comments for handle_missing_profiles()
+     in predict.c as to why). Apply counts to the blocks in the callee
+     before inlining, using the guessed edge frequencies, so that we don't
+     end up with a 0-count inline body which can confuse downstream
+     optimizations such as function splitting.  */
+  if (!ENTRY_BLOCK_PTR_FOR_FUNCTION (src_cfun)->count && count)
+    {
+      /* Apply the larger of the call bb count and the total incoming
+         call edge count to the callee.  */
+      gcov_type in_count = 0;
+      struct cgraph_edge *in_edge;
+      for (in_edge = id->src_node->callers; in_edge;
+           in_edge = in_edge->next_caller)
+        in_count += in_edge->count;
+      freqs_to_counts (id->src_node, count > in_count ? count : in_count);
+    }
+
   if (ENTRY_BLOCK_PTR_FOR_FUNCTION (src_cfun)->count)
     count_scale
         = GCOV_COMPUTE_SCALE (count,

gcc/tree-profile.c

@@ -645,6 +645,8 @@ tree_profiling (void)
       pop_cfun ();
     }
 
+  handle_missing_profiles ();
+
   del_node_map ();
   return 0;
 }