Follow-on patch to r197595 to complete the replacement of truncating divides in...

Follow-on patch to r197595 to complete the replacement of truncating divides
in profile scaling code with rounding divide equivalents using helper routines
in basic-block.h. 

In addition to bootstrap and profiledbootstrap builds and tests (with and
without LTO), I built and tested performance of the SPEC cpu2006 benchmarks
with FDO on a Nehalem system. I didn't see any performance changes that
looked significant.

2013-05-02  Teresa Johnson  <tejohnson@google.com>

	* loop-unswitch.c (unswitch_loop): Use helper routines with rounding
        divides.
	* cfg.c (update_bb_profile_for_threading): Ditto.
	* tree-inline.c (copy_bb): Ditto.
	(copy_edges_for_bb): Ditto.
	(initialize_cfun): Ditto.
	(copy_cfg_body): Ditto.
	(expand_call_inline): Ditto.
	* ipa-inline-analysis.c (estimate_edge_size_and_time): Ditto.
	(estimate_node_size_and_time): Ditto.
	(inline_merge_summary): Ditto.
	* cgraphclones.c (cgraph_clone_edge): Ditto.
	(cgraph_clone_node): Ditto.
	* sched-rgn.c (compute_dom_prob_ps): Ditto.
	(compute_trg_info): Ditto.

From-SVN: r198532

7 files changed, 40 insertions, 38 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index de05eeb..023c6b9 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,21 @@
+2013-05-02  Teresa Johnson  <tejohnson@google.com>
+
+	* loop-unswitch.c (unswitch_loop): Use helper routines with rounding
+	divides.
+	* cfg.c (update_bb_profile_for_threading): Ditto.
+	* tree-inline.c (copy_bb): Ditto.
+	(copy_edges_for_bb): Ditto.
+	(initialize_cfun): Ditto.
+	(copy_cfg_body): Ditto.
+	(expand_call_inline): Ditto.
+	* ipa-inline-analysis.c (estimate_edge_size_and_time): Ditto.
+	(estimate_node_size_and_time): Ditto.
+	(inline_merge_summary): Ditto.
+	* cgraphclones.c (cgraph_clone_edge): Ditto.
+	(cgraph_clone_node): Ditto.
+	* sched-rgn.c (compute_dom_prob_ps): Ditto.
+	(compute_trg_info): Ditto.
+
 2013-05-02  Ian Bolton  <ian.bolton@arm.com>
 
 	* config/aarch64/aarch64.md (movsi_aarch64): Only allow to/from
diff --git a/gcc/cfg.c b/gcc/cfg.c
index 6405f93..9c6c939 100644
--- a/gcc/cfg.c
+++ b/gcc/cfg.c
@@ -848,8 +848,7 @@ update_bb_profile_for_threading (basic_block bb, int edge_frequency,
   /* Compute the probability of TAKEN_EDGE being reached via threaded edge.
      Watch for overflows.  */
   if (bb->frequency)
-    /* Update to use GCOV_COMPUTE_SCALE.  */
-    prob = edge_frequency * REG_BR_PROB_BASE / bb->frequency;
+    prob = GCOV_COMPUTE_SCALE (edge_frequency, bb->frequency);
   else
     prob = 0;
   if (prob > taken_edge->probability)
diff --git a/gcc/cgraphclones.c b/gcc/cgraphclones.c
index fa6a911..f015f18 100644
--- a/gcc/cgraphclones.c
+++ b/gcc/cgraphclones.c
@@ -102,8 +102,7 @@ cgraph_clone_edge (struct cgraph_edge *e, struct cgraph_node *n,
 		   int freq_scale, bool update_original)
 {
   struct cgraph_edge *new_edge;
-  /* Update this to use GCOV_COMPUTE_SCALE.  */
-  gcov_type count = e->count * count_scale / REG_BR_PROB_BASE;
+  gcov_type count = apply_probability (e->count, count_scale);
   gcov_type freq;
 
   /* We do not want to ignore loop nest after frequency drops to 0.  */
@@ -205,8 +204,7 @@ cgraph_clone_node (struct cgraph_node *n, tree decl, gcov_type count, int freq,
       if (new_node->count > n->count)
         count_scale = REG_BR_PROB_BASE;
       else
-        /* Update to use GCOV_COMPUTE_SCALE.  */
-        count_scale = new_node->count * REG_BR_PROB_BASE / n->count;
+        count_scale = GCOV_COMPUTE_SCALE (new_node->count, n->count);
     }
   else
     count_scale = 0;
diff --git a/gcc/ipa-inline-analysis.c b/gcc/ipa-inline-analysis.c
index 138433c..8d66325 100644
--- a/gcc/ipa-inline-analysis.c
+++ b/gcc/ipa-inline-analysis.c
@@ -2790,8 +2790,7 @@ estimate_edge_size_and_time (struct cgraph_edge *e, int *size, int *time,
       && hints && cgraph_maybe_hot_edge_p (e))
     *hints |= INLINE_HINT_indirect_call;
   *size += call_size * INLINE_SIZE_SCALE;
-  /* Update to use apply_probability().  */
-  *time += call_time * prob / REG_BR_PROB_BASE
+  *time += apply_probability ((gcov_type) call_time, prob)
     * e->frequency * (INLINE_TIME_SCALE / CGRAPH_FREQ_BASE);
   if (*time > MAX_TIME * INLINE_TIME_SCALE)
     *time = MAX_TIME * INLINE_TIME_SCALE;
@@ -2901,8 +2900,7 @@ estimate_node_size_and_time (struct cgraph_node *node,
 					      inline_param_summary);
 	    gcc_checking_assert (prob >= 0);
 	    gcc_checking_assert (prob <= REG_BR_PROB_BASE);
-            /* Update to use apply_probability().  */
-	    time += ((gcov_type) e->time * prob) / REG_BR_PROB_BASE;
+	    time += apply_probability ((gcov_type) e->time, prob);
 	  }
 	if (time > MAX_TIME * INLINE_TIME_SCALE)
 	  time = MAX_TIME * INLINE_TIME_SCALE;
@@ -3311,8 +3309,7 @@ inline_merge_summary (struct cgraph_edge *edge)
 	  int prob = predicate_probability (callee_info->conds,
 					    &e->predicate,
 					    clause, es->param);
-          /* Update to use apply_probability().  */
-	  add_time = ((gcov_type) add_time * prob) / REG_BR_PROB_BASE;
+	  add_time = apply_probability ((gcov_type) add_time, prob);
 	  if (add_time > MAX_TIME * INLINE_TIME_SCALE)
 	    add_time = MAX_TIME * INLINE_TIME_SCALE;
 	  if (prob != REG_BR_PROB_BASE
diff --git a/gcc/loop-unswitch.c b/gcc/loop-unswitch.c
index e5f1bdc..213e74d 100644
--- a/gcc/loop-unswitch.c
+++ b/gcc/loop-unswitch.c
@@ -436,12 +436,10 @@ unswitch_loop (struct loop *loop, basic_block unswitch_on, rtx cond, rtx cinsn)
   emit_insn_after (seq, BB_END (switch_bb));
   e = make_edge (switch_bb, true_edge->dest, 0);
   e->probability = prob;
-  /* Update to use apply_probability().  */
-  e->count = latch_edge->count * prob / REG_BR_PROB_BASE;
+  e->count = apply_probability (latch_edge->count, prob);
   e = make_edge (switch_bb, FALLTHRU_EDGE (unswitch_on)->dest, EDGE_FALLTHRU);
   e->probability = false_edge->probability;
-  /* Update to use apply_probability().  */
-  e->count = latch_edge->count * (false_edge->probability) / REG_BR_PROB_BASE;
+  e->count = apply_probability (latch_edge->count, false_edge->probability);
 
   if (irred_flag)
     {
diff --git a/gcc/sched-rgn.c b/gcc/sched-rgn.c
index 6eb00e9..3f5b4ba1 100644
--- a/gcc/sched-rgn.c
+++ b/gcc/sched-rgn.c
@@ -1441,8 +1441,7 @@ compute_dom_prob_ps (int bb)
       FOR_EACH_EDGE (out_edge, out_ei, in_edge->src->succs)
 	bitmap_set_bit (pot_split[bb], EDGE_TO_BIT (out_edge));
 
-      /* Update to use apply_probability().  */
-      prob[bb] += ((prob[pred_bb] * in_edge->probability) / REG_BR_PROB_BASE);
+      prob[bb] += combine_probabilities (prob[pred_bb], in_edge->probability);
     }
 
   bitmap_set_bit (dom[bb], bb);
@@ -1515,8 +1514,7 @@ compute_trg_info (int trg)
 	  int tf = prob[trg], cf = prob[i];
 
 	  /* In CFGs with low probability edges TF can possibly be zero.  */
-          /* Update to use GCOV_COMPUTE_SCALE.  */
-	  sp->src_prob = (tf ? ((cf * REG_BR_PROB_BASE) / tf) : 0);
+	  sp->src_prob = (tf ? GCOV_COMPUTE_SCALE (cf, tf) : 0);
 	  sp->is_valid = (sp->src_prob >= min_spec_prob);
 	}
 
diff --git a/gcc/tree-inline.c b/gcc/tree-inline.c
index 3abaadc..a650f0d 100644
--- a/gcc/tree-inline.c
+++ b/gcc/tree-inline.c
@@ -1519,13 +1519,11 @@ copy_bb (copy_body_data *id, basic_block bb, int frequency_scale,
      basic_block_info automatically.  */
   copy_basic_block = create_basic_block (NULL, (void *) 0,
                                          (basic_block) prev->aux);
-  /* Update to use apply_scale().  */
-  copy_basic_block->count = bb->count * count_scale / REG_BR_PROB_BASE;
+  copy_basic_block->count = apply_scale (bb->count, count_scale);
 
   /* We are going to rebuild frequencies from scratch.  These values
      have just small importance to drive canonicalize_loop_headers.  */
-  /* Update to use EDGE_FREQUENCY.  */
-  freq = ((gcov_type)bb->frequency * frequency_scale / REG_BR_PROB_BASE);
+  freq = apply_scale ((gcov_type)bb->frequency, frequency_scale);
 
   /* We recompute frequencies after inlining, so this is quite safe.  */
   if (freq > BB_FREQ_MAX)
@@ -1891,8 +1889,7 @@ copy_edges_for_bb (basic_block bb, gcov_type count_scale, basic_block ret_bb,
 	    && old_edge->dest->aux != EXIT_BLOCK_PTR)
 	  flags |= EDGE_FALLTHRU;
 	new_edge = make_edge (new_bb, (basic_block) old_edge->dest->aux, flags);
-        /* Update to use apply_scale().  */
-	new_edge->count = old_edge->count * count_scale / REG_BR_PROB_BASE;
+	new_edge->count = apply_scale (old_edge->count, count_scale);
 	new_edge->probability = old_edge->probability;
       }
 
@@ -2066,10 +2063,10 @@ initialize_cfun (tree new_fndecl, tree callee_fndecl, gcov_type count)
   struct function *src_cfun = DECL_STRUCT_FUNCTION (callee_fndecl);
   gcov_type count_scale;
 
-  /* Update to use GCOV_COMPUTE_SCALE.  */
   if (ENTRY_BLOCK_PTR_FOR_FUNCTION (src_cfun)->count)
-    count_scale = (REG_BR_PROB_BASE * count
-		   / ENTRY_BLOCK_PTR_FOR_FUNCTION (src_cfun)->count);
+    count_scale
+        = GCOV_COMPUTE_SCALE (count,
+                              ENTRY_BLOCK_PTR_FOR_FUNCTION (src_cfun)->count);
   else
     count_scale = REG_BR_PROB_BASE;
 
@@ -2253,10 +2250,10 @@ copy_cfg_body (copy_body_data * id, gcov_type count, int frequency_scale,
   int incoming_frequency = 0;
   gcov_type incoming_count = 0;
 
-  /* Update to use GCOV_COMPUTE_SCALE.  */
   if (ENTRY_BLOCK_PTR_FOR_FUNCTION (src_cfun)->count)
-    count_scale = (REG_BR_PROB_BASE * count
-		   / ENTRY_BLOCK_PTR_FOR_FUNCTION (src_cfun)->count);
+    count_scale
+        = GCOV_COMPUTE_SCALE (count,
+                              ENTRY_BLOCK_PTR_FOR_FUNCTION (src_cfun)->count);
   else
     count_scale = REG_BR_PROB_BASE;
 
@@ -2278,11 +2275,9 @@ copy_cfg_body (copy_body_data * id, gcov_type count, int frequency_scale,
 	    incoming_frequency += EDGE_FREQUENCY (e);
 	    incoming_count += e->count;
 	  }
-      /* Update to use apply_scale().  */
-      incoming_count = incoming_count * count_scale / REG_BR_PROB_BASE;
-      /* Update to use EDGE_FREQUENCY.  */
+      incoming_count = apply_scale (incoming_count, count_scale);
       incoming_frequency
-	= incoming_frequency * frequency_scale / REG_BR_PROB_BASE;
+	= apply_scale ((gcov_type)incoming_frequency, frequency_scale);
       ENTRY_BLOCK_PTR->count = incoming_count;
       ENTRY_BLOCK_PTR->frequency = incoming_frequency;
     }
@@ -4114,8 +4109,7 @@ expand_call_inline (basic_block bb, gimple stmt, copy_body_data *id)
      a self-referential call; if we're calling ourselves, we need to
      duplicate our body before altering anything.  */
   copy_body (id, bb->count,
-             /* Update to use GCOV_COMPUTE_SCALE.  */
-  	     cg_edge->frequency * REG_BR_PROB_BASE / CGRAPH_FREQ_BASE,
+  	     GCOV_COMPUTE_SCALE (cg_edge->frequency, CGRAPH_FREQ_BASE),
 	     bb, return_block, NULL, NULL);
 
   /* Reset the escaped solution.  */