---
 gcc/config/rs6000/rs6000.c | 88 +++++++++++++++++++++++++++++++++-----
 1 file changed, 77 insertions(+), 11 deletions(-)

diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index ffdf10098a9..5ae40d6f4ce 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -5245,12 +5245,16 @@ rs6000_density_test (rs6000_cost_data *data)
   const int DENSITY_PCT_THRESHOLD = 85;
   const int DENSITY_SIZE_THRESHOLD = 70;
   const int DENSITY_PENALTY = 10;
+  const int DENSITY_LOAD_PCT_THRESHOLD = 80;
+  const int DENSITY_LOAD_FOR_CTOR_PCT_THRESHOLD = 65;
+  const int DENSITY_LOAD_SIZE_THRESHOLD = 20;
   struct loop *loop = data->loop_info;
   basic_block *bbs = get_loop_body (loop);
   int nbbs = loop->num_nodes;
   loop_vec_info loop_vinfo = loop_vec_info_for_loop (data->loop_info);
   int vec_cost = data->cost[vect_body], not_vec_cost = 0;
   int i, density_pct;
+  unsigned int nload_total = 0, nctor_for_strided = 0, nload_for_ctor = 0;
 
   /* Only care about cost of vector version, so exclude scalar version here.  */
   if (LOOP_VINFO_TARGET_COST_DATA (loop_vinfo) != (void *) data)
@@ -5272,21 +5276,83 @@ rs6000_density_test (rs6000_cost_data *data)
 	  if (!STMT_VINFO_RELEVANT_P (stmt_info)
 	      && !STMT_VINFO_IN_PATTERN_P (stmt_info))
 	    not_vec_cost++;
+	  else
+	    {
+	      stmt_vec_info vstmt_info = vect_stmt_to_vectorize (stmt_info);
+	      if (STMT_VINFO_DATA_REF (vstmt_info)
+		  && DR_IS_READ (STMT_VINFO_DATA_REF (vstmt_info)))
+		{
+		  if (STMT_VINFO_STRIDED_P (vstmt_info))
+		    {
+		      unsigned int ncopies = 1;
+		      unsigned int nunits = 1;
+		      /* TODO: For VMAT_STRIDED_SLP, the total CTOR can be
+			 fewer due to group access.  Simply handle it here
+			 for now.  */
+		      if (!STMT_SLP_TYPE (vstmt_info))
+			{
+			  tree vectype = STMT_VINFO_VECTYPE (vstmt_info);
+			  ncopies = vect_get_num_copies (loop_vinfo, vectype);
+			  nunits = vect_nunits_for_cost (vectype);
+			}
+		      unsigned int nloads = ncopies * nunits;
+		      nload_for_ctor += nloads;
+		      nload_total += nloads;
+		      nctor_for_strided += ncopies;
+		    }
+		  else
+		    nload_total++;
+		}
+	    }
 	}
     }
-
   free (bbs);
-  density_pct = (vec_cost * 100) / (vec_cost + not_vec_cost);
 
-  if (density_pct > DENSITY_PCT_THRESHOLD
-      && vec_cost + not_vec_cost > DENSITY_SIZE_THRESHOLD)
-    {
-      data->cost[vect_body] = vec_cost * (100 + DENSITY_PENALTY) / 100;
-      if (dump_enabled_p ())
-	dump_printf_loc (MSG_NOTE, vect_location,
-			 "density %d%%, cost %d exceeds threshold, penalizing "
-			 "loop body cost by %d%%", density_pct,
-			 vec_cost + not_vec_cost, DENSITY_PENALTY);
+  if (vec_cost + not_vec_cost > DENSITY_SIZE_THRESHOLD)
+    {
+      density_pct = (vec_cost * 100) / (vec_cost + not_vec_cost);
+      if (density_pct > DENSITY_PCT_THRESHOLD)
+	{
+	  data->cost[vect_body] = vec_cost * (100 + DENSITY_PENALTY) / 100;
+	  if (dump_enabled_p ())
+	    dump_printf_loc (MSG_NOTE, vect_location,
+			     "density %d%%, cost %d exceeds threshold, "
+			     "penalizing loop body cost by %d%%.\n",
+			     density_pct, vec_cost + not_vec_cost,
+			     DENSITY_PENALTY);
+	}
+      /* For one loop which has a large proportion scalar loads of all
+	 loads fed into vector construction, if the density is high,
+	 the loads will have more stalls than usual, further affect
+	 the vector construction.  One typical case is the innermost
+	 loop of the hotspot of spec2017 503.bwaves_r without loop
+	 interchange.  Here we price more on the related vector
+	 construction and penalize the body cost.  */
+      else if (density_pct > DENSITY_LOAD_PCT_THRESHOLD
+	       && nload_total > DENSITY_LOAD_SIZE_THRESHOLD)
+	{
+	  int load_for_ctor_pct = (nload_for_ctor * 100) / nload_total;
+	  /* Large proportion of scalar loads fed to vector CTOR.  */
+	  if (load_for_ctor_pct > DENSITY_LOAD_FOR_CTOR_PCT_THRESHOLD)
+	    {
+	      vec_cost += nctor_for_strided;
+	      if (dump_enabled_p ())
+		dump_printf_loc (MSG_NOTE, vect_location,
+				 "Found high density loop with a large "
+				 "proportion %d%% of scalar loads fed to "
+				 "vector ctor, add cost %d.\n",
+				 load_for_ctor_pct, nctor_for_strided);
+
+	      data->cost[vect_body] = vec_cost * (100 + DENSITY_PENALTY) / 100;
+	      if (dump_enabled_p ())
+		dump_printf_loc (MSG_NOTE, vect_location,
+				 "density %d%%, cost %d exceeds threshold, "
+				 "penalizing loop body cost by %d%% for "
+				 "load.\n",
+				 density_pct, vec_cost + not_vec_cost,
+				 DENSITY_PENALTY);
+	    }
+	}
     }
 }
 
-- 
2.17.1