invoke.texi (-fpeel-loops,-O3): Update documentation.

* doc/invoke.texi (-fpeel-loops,-O3): Update documentation.
	* opts.c (default_options): Enable peel loops at -O3.
	* tree-ssa-loop-ivcanon.c (peeled_loops): New static var.
	(try_peel_loop): Do not re-peel already peeled loops;
	use likely upper bounds; fix profile updating.
	(pass_complete_unroll::execute): Initialize peeled_loops.

	* gcc.dg/tree-ssa/peel1.c: New testcase.
	* gcc.dg/tree-ssa/pr61743-1.c: Disable loop peeling.
	* gcc.dg/tree-ssa/pr61743-2.c: Disable loop peeling.

From-SVN: r236892

gcc/ChangeLog

@@ -1,3 +1,12 @@
+2016-05-30  Jan Hubicka  <hubicka@ucw.cz>
+
+	* doc/invoke.texi (-fpeel-loops,-O3): Update documentation.
+	* opts.c (default_options): Enable peel loops at -O3.
+	* tree-ssa-loop-ivcanon.c (peeled_loops): New static var.
+	(try_peel_loop): Do not re-peel already peeled loops;
+	use likely upper bounds; fix profile updating.
+	(pass_complete_unroll::execute): Initialize peeled_loops.
+
 2016-05-30  Martin Liska  <mliska@suse.cz>
 
 	* tree-ssa-loop-ivopts.c (get_computation_cost_at): Scale

gcc/doc/invoke.texi

@@ -6338,7 +6338,8 @@ by @option{-O2} and also turns on the @option{-finline-functions},
 @option{-fgcse-after-reload}, @option{-ftree-loop-vectorize},
 @option{-ftree-loop-distribute-patterns}, @option{-fsplit-paths}
 @option{-ftree-slp-vectorize}, @option{-fvect-cost-model},
-@option{-ftree-partial-pre} and @option{-fipa-cp-clone} options.
+@option{-ftree-partial-pre}, @option{-fpeel-loops}
+and @option{-fipa-cp-clone} options.
 
 @item -O0
 @opindex O0
@@ -8661,10 +8662,11 @@ the loop is entered.  This usually makes programs run more slowly.
 @item -fpeel-loops
 @opindex fpeel-loops
 Peels loops for which there is enough information that they do not
-roll much (from profile feedback).  It also turns on complete loop peeling
-(i.e.@: complete removal of loops with small constant number of iterations).
+roll much (from profile feedback or static analysis).  It also turns on
+complete loop peeling (i.e.@: complete removal of loops with small constant
+number of iterations).
 
-Enabled with @option{-fprofile-use}.
+Enabled with @option{-O3} and/or @option{-fprofile-use}.
 
 @item -fmove-loop-invariants
 @opindex fmove-loop-invariants

gcc/opts.c

@@ -535,6 +535,7 @@ static const struct default_options default_options_table[] =
     { OPT_LEVELS_3_PLUS, OPT_fvect_cost_model_, NULL, VECT_COST_MODEL_DYNAMIC },
     { OPT_LEVELS_3_PLUS, OPT_fipa_cp_clone, NULL, 1 },
     { OPT_LEVELS_3_PLUS, OPT_ftree_partial_pre, NULL, 1 },
+    { OPT_LEVELS_3_PLUS, OPT_fpeel_loops, NULL, 1 },
 
     /* -Ofast adds optimizations to -O3.  */
     { OPT_LEVELS_FAST, OPT_ffast_math, NULL, 1 },

gcc/testsuite/ChangeLog

@@ -1,3 +1,9 @@
+2016-05-30  Jan Hubicka  <hubicka@ucw.cz>
+
+	* gcc.dg/tree-ssa/peel1.c: New testcase.
+	* gcc.dg/tree-ssa/pr61743-1.c: Disable loop peeling.
+	* gcc.dg/tree-ssa/pr61743-2.c: Disable loop peeling.
+
 2016-05-30  Tom de Vries  <tom@codesourcery.com>
 
 	* gcc.dg/graphite/pr69067.c (main): Remove superfluous argument in call

gcc/testsuite/gcc.dg/tree-ssa/peel1.c

@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-tree-cunroll-details" } */
+struct foo {int b; int a[3];} foo;
+void add(struct foo *a,int l)
+{
+  int i;
+  for (i=0;i<l;i++)
+    a->a[i]++;
+}
+/* { dg-final { scan-tree-dump "Loop 1 likely iterates at most 3 times." "cunroll"} } */
+/* { dg-final { scan-tree-dump "Peeled loop 1, 4 times." "cunroll"} } */

gcc/testsuite/gcc.dg/tree-ssa/pr61743-1.c

@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -funroll-loops -fno-tree-vectorize -fdump-tree-cunroll-details" } */
+/* { dg-options "-O3 -funroll-loops -fno-tree-vectorize -fdump-tree-cunroll-details -fno-peel-loops" } */
 
 #define N 8
 #define M 14

gcc/testsuite/gcc.dg/tree-ssa/pr61743-2.c

@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -funroll-loops -fno-tree-vectorize -fdump-tree-cunroll-details" } */
+/* { dg-options "-O3 -funroll-loops -fno-tree-vectorize -fdump-tree-cunroll-details -fno-peel-loops" } */
 
 #define N 8
 #define M 14

gcc/tree-ssa-loop-ivcanon.c

@@ -594,6 +594,8 @@ remove_redundant_iv_tests (struct loop *loop)
 /* Stores loops that will be unlooped after we process whole loop tree. */
 static vec<loop_p> loops_to_unloop;
 static vec<int> loops_to_unloop_nunroll;
+/* Stores loops that has been peeled.  */
+static bitmap peeled_loops;
 
 /* Cancel all fully unrolled loops by putting __builtin_unreachable
    on the latch edge.  
@@ -962,14 +964,17 @@ try_peel_loop (struct loop *loop,
   vec<edge> to_remove = vNULL;
   edge e;
 
-  /* If the iteration bound is known and large, then we can safely eliminate
-     the check in peeled copies.  */
-  if (TREE_CODE (niter) != INTEGER_CST)
-    exit = NULL;
-
-  if (!flag_peel_loops || PARAM_VALUE (PARAM_MAX_PEEL_TIMES) <= 0)
+  if (!flag_peel_loops || PARAM_VALUE (PARAM_MAX_PEEL_TIMES) <= 0
+      || !peeled_loops)
     return false;
 
+  if (bitmap_bit_p (peeled_loops, loop->num))
+    {
+      if (dump_file)
+        fprintf (dump_file, "Not peeling: loop is already peeled\n");
+      return false;
+    }
+
   /* Peel only innermost loops.
      While the code is perfectly capable of peeling non-innermost loops,
      the heuristics would probably need some improvements. */
@@ -989,6 +994,8 @@ try_peel_loop (struct loop *loop,
 
   /* Check if there is an estimate on the number of iterations.  */
   npeel = estimated_loop_iterations_int (loop);
+  if (npeel < 0)
+    npeel = likely_max_loop_iterations_int (loop);
   if (npeel < 0)
     {
       if (dump_file)
@@ -1036,8 +1043,7 @@ try_peel_loop (struct loop *loop,
       && wi::leu_p (npeel, wi::to_widest (niter)))
     {
       bitmap_ones (wont_exit);
-      if (wi::eq_p (wi::to_widest (niter), npeel))
-        bitmap_clear_bit (wont_exit, 0);
+      bitmap_clear_bit (wont_exit, 0);
     }
   else
     {
@@ -1074,14 +1080,14 @@ try_peel_loop (struct loop *loop,
     }
   if (loop->any_upper_bound)
     {
-      if (wi::ltu_p (npeel, loop->nb_iterations_estimate))
+      if (wi::ltu_p (npeel, loop->nb_iterations_upper_bound))
         loop->nb_iterations_upper_bound -= npeel;
       else
         loop->nb_iterations_upper_bound = 0;
     }
   if (loop->any_likely_upper_bound)
     {
-      if (wi::ltu_p (npeel, loop->nb_iterations_estimate))
+      if (wi::ltu_p (npeel, loop->nb_iterations_likely_upper_bound))
 	loop->nb_iterations_likely_upper_bound -= npeel;
       else
 	{
@@ -1107,6 +1113,7 @@ try_peel_loop (struct loop *loop,
   else if (loop->header->frequency)
     scale = RDIV (entry_freq * REG_BR_PROB_BASE, loop->header->frequency);
   scale_loop_profile (loop, scale, 0);
+  bitmap_set_bit (peeled_loops, loop->num);
   return true;
 }
 /* Adds a canonical induction variable to LOOP if suitable.
@@ -1519,9 +1526,20 @@ pass_complete_unroll::execute (function *fun)
   if (number_of_loops (fun) <= 1)
     return 0;
 
-  return tree_unroll_loops_completely (flag_unroll_loops
-				       || flag_peel_loops
-				       || optimize >= 3, true);
+  /* If we ever decide to run loop peeling more than once, we will need to
+     track loops already peeled in loop structures themselves to avoid
+     re-peeling the same loop multiple times.  */
+  if (flag_peel_loops)
+    peeled_loops = BITMAP_ALLOC (NULL);
+  int val = tree_unroll_loops_completely (flag_unroll_loops
+					  || flag_peel_loops
+					  || optimize >= 3, true);
+  if (peeled_loops)
+    {
+      BITMAP_FREE (peeled_loops);
+      peeled_loops = NULL;
+    }
+  return val;
 }
 
 } // anon namespace