re PR tree-optimization/82220 (SPEC CPU2006 482.sphinx3 ~10% performance…

re PR tree-optimization/82220 (SPEC CPU2006 482.sphinx3 ~10% performance regression with trunk@250416)

2017-09-18  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/82220
	* tree-vect-loop.c (vect_estimate_min_profitable_iters): Exclude
	epilogue niters from the min_profitable_iters compute.

From-SVN: r252917

gcc/ChangeLog

+2017-09-18  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/82220
+	* tree-vect-loop.c (vect_estimate_min_profitable_iters): Exclude
+	epilogue niters from the min_profitable_iters compute.
+
 2017-09-18  Jakub Jelinek  <jakub@redhat.com>
 
 	PR target/82145

gcc/tree-vect-loop.c

@@ -3663,8 +3663,8 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo,
 	       min_profitable_iters);
 
   /* We want the vectorized loop to execute at least once.  */
-  if (min_profitable_iters < (vf + peel_iters_prologue + peel_iters_epilogue))
-    min_profitable_iters = vf + peel_iters_prologue + peel_iters_epilogue;
+  if (min_profitable_iters < (vf + peel_iters_prologue))
+    min_profitable_iters = vf + peel_iters_prologue;
 
   if (dump_enabled_p ())
     dump_printf_loc (MSG_NOTE, vect_location,