tree-optimization/113026 - avoid vector epilog in more cases

The following avoids creating a niter peeling epilog more consistently,
matching what peeling later uses for the skip_vector condition, in
particular when versioning is required which then also ensures the
vector loop is entered unless the epilog is vectorized.  This should
ideally match LOOP_VINFO_VERSIONING_THRESHOLD which is only computed
later, some refactoring could make that better matching.

The patch also makes sure to adjust the upper bound of the epilogues
when we do not have a skip edge around the vector loop.

	PR tree-optimization/113026
	* tree-vect-loop.cc (vect_need_peeling_or_partial_vectors_p):
	Avoid an epilog in more cases.
	* tree-vect-loop-manip.cc (vect_do_peeling): Adjust the
	epilogues niter upper bounds and estimates.

	* gcc.dg/torture/pr113026-1.c: New testcase.
	* gcc.dg/torture/pr113026-2.c: Likewise.

gcc/testsuite/gcc.dg/torture/pr113026-1.c

@@ -0,0 +1,11 @@
+/* { dg-do compile } */ 
+/* { dg-additional-options "-Wall" } */
+
+char dst[16];
+
+void
+foo (char *src, long n)
+{
+  for (long i = 0; i < n; i++)
+    dst[i] = src[i]; /* { dg-bogus "" } */
+}

gcc/testsuite/gcc.dg/torture/pr113026-2.c

@@ -0,0 +1,18 @@
+/* { dg-do compile } */ 
+/* { dg-additional-options "-Wall" } */
+
+char dst1[17];
+void
+foo1 (char *src, long n)
+{
+  for (long i = 0; i < n; i++)
+    dst1[i] = src[i]; /* { dg-bogus "" } */
+}
+
+char dst2[18];
+void
+foo2 (char *src, long n)
+{
+  for (long i = 0; i < n; i++)
+    dst2[i] = src[i]; /* { dg-bogus "" } */
+}

gcc/tree-vect-loop-manip.cc

@@ -3364,6 +3364,38 @@ vect_do_peeling (loop_vec_info loop_vinfo, tree niters, tree nitersm1,
 	    bb_before_epilog->count = single_pred_edge (bb_before_epilog)->count ();
 	  bb_before_epilog = loop_preheader_edge (epilog)->src;
 	}
+      else
+	{
+	  /* When we do not have a loop-around edge to the epilog we know
+	     the vector loop covered at least VF scalar iterations unless
+	     we have early breaks and the epilog will cover at most
+	     VF - 1 + gap peeling iterations.
+	     Update any known upper bound with this knowledge.  */
+	  if (! LOOP_VINFO_EARLY_BREAKS (loop_vinfo))
+	    {
+	      if (epilog->any_upper_bound)
+		epilog->nb_iterations_upper_bound -= lowest_vf;
+	      if (epilog->any_likely_upper_bound)
+		epilog->nb_iterations_likely_upper_bound -= lowest_vf;
+	      if (epilog->any_estimate)
+		epilog->nb_iterations_estimate -= lowest_vf;
+	    }
+	  unsigned HOST_WIDE_INT const_vf;
+	  if (vf.is_constant (&const_vf))
+	    {
+	      const_vf += LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo) - 1;
+	      if (epilog->any_upper_bound)
+		epilog->nb_iterations_upper_bound
+		  = wi::umin (epilog->nb_iterations_upper_bound, const_vf);
+	      if (epilog->any_likely_upper_bound)
+		epilog->nb_iterations_likely_upper_bound
+		  = wi::umin (epilog->nb_iterations_likely_upper_bound,
+			      const_vf);
+	      if (epilog->any_estimate)
+		epilog->nb_iterations_estimate
+		  = wi::umin (epilog->nb_iterations_estimate, const_vf);
+	    }
+	}
 
       /* If loop is peeled for non-zero constant times, now niters refers to
 	 orig_niters - prolog_peeling, it won't overflow even the orig_niters

gcc/tree-vect-loop.cc

@@ -1261,7 +1261,11 @@ vect_need_peeling_or_partial_vectors_p (loop_vec_info loop_vinfo)
 	     the epilogue is unnecessary.  */
 	  && (!LOOP_REQUIRES_VERSIONING (loop_vinfo)
 	      || ((unsigned HOST_WIDE_INT) max_niter
-		  > (th / const_vf) * const_vf))))
+		  /* We'd like to use LOOP_VINFO_VERSIONING_THRESHOLD
+		     but that's only computed later based on our result.
+		     The following is the most conservative approximation.  */
+		  > (std::max ((unsigned HOST_WIDE_INT) th,
+			       const_vf) / const_vf) * const_vf))))
     return true;
 
   return false;