Enable loop peeling at -O3

[Jan Hubicka <hubicka at ucw dot cz>]

Hi,
this patch enabled -fpeel-loops by default at -O3 and makes it to use likely
upper bound estimates.  The patch also adds -fpeel-all-loops flag that is
symmetric to -funroll-all-loops.  Long time ago we used to interpret
-fpeel-loops this way and blindly peel every loop but this behaviour got lost
and now we only peel loop we have some evidence for.

Bootstrapped/regtested x86_64-linux, I am retesting after last minute change
(adding of the testcase). OK?

Honza

	* common.opt (flag_peel_all_loops): New option.
	* doc/invoke.texi: (-fpeel-loops): Update documentation.
	(-fpeel-all-loops): Document.
	* opts.c (default_options): Add OPT_fpeel_loops to -O3+.
	* toplev.c (process_options): flag_peel_all_loops implies
	flag_peel_loops.
	* tree-ssa-lop-ivcanon.c (try_peel_loop): Update comment; handle
	-fpeel-all-loops, use likely estimates.

	* gcc.dg/tree-ssa/peel1.c: New testcase.
	* gcc.dg/tree-ssa/peel2.c: New testcase.
Index: common.opt
===================================================================
--- common.opt	(revision 236815)
+++ common.opt	(working copy)
@@ -1840,6 +1840,10 @@ fpeel-loops
 Common Report Var(flag_peel_loops) Optimization
 Perform loop peeling.
 
+fpeel-all-loops
+Common Report Var(flag_peel_all_loops) Optimization
+Perform loop peeling of all loops.
+
 fpeephole
 Common Report Var(flag_no_peephole,0) Optimization
 Enable machine specific peephole optimizations.
Index: doc/invoke.texi
===================================================================
--- doc/invoke.texi	(revision 236815)
+++ doc/invoke.texi	(working copy)
@@ -8661,10 +8661,17 @@ the loop is entered.  This usually makes
 @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 @option{-fprofile-use}.
+
+@item -fpeel-all-loops
+@opindex fpeel-all-loops
+Peel all loops, even if their number of iterations is uncertain when
+the loop is entered.  For loops with large number of iterations this leads
+to wasted code size.
 
 @item -fmove-loop-invariants
 @opindex fmove-loop-invariants
Index: opts.c
===================================================================
--- opts.c	(revision 236815)
+++ opts.c	(working copy)
@@ -535,6 +535,7 @@ static const struct default_options defa
     { 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 },
Index: testsuite/gcc.dg/tree-ssa/peel1.c
===================================================================
--- testsuite/gcc.dg/tree-ssa/peel1.c	(revision 0)
+++ testsuite/gcc.dg/tree-ssa/peel1.c	(working copy)
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-tree-loop-ivcanon" } */
+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 likely 1 iterates at most 3 times." 1 "ivcanon"} } */
+/* { dg-final { scan-tree-dump "Peeled loop 1, 4 times." 1 "ivcanon"} } */
Index: testsuite/gcc.dg/tree-ssa/peel2.c
===================================================================
--- testsuite/gcc.dg/tree-ssa/peel2.c	(revision 0)
+++ testsuite/gcc.dg/tree-ssa/peel2.c	(working copy)
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fpeel-all-loops -fdump-tree-loop-ivcanon" } */
+void add(int *a,int l)
+{
+  int i;
+  for (i=0;i<l;i++)
+    a[i]++;
+}
+/* { dg-final { scan-tree-dump "Loop likely 1 iterates at most 3 times." 1 "ivcanon"} } */
+/* { dg-final { scan-tree-dump "Peeled loop 1, 4 times." 1 "ivcanon"} } */
Index: toplev.c
===================================================================
--- toplev.c	(revision 236815)
+++ toplev.c	(working copy)
@@ -1294,6 +1294,9 @@ process_options (void)
   if (flag_unroll_all_loops)
     flag_unroll_loops = 1;
 
+  if (flag_peel_all_loops)
+    flag_peel_loops = 1;
+
   /* web and rename-registers help when run after loop unrolling.  */
   if (flag_web == AUTODETECT_VALUE)
     flag_web = flag_unroll_loops || flag_peel_loops;
Index: tree-ssa-loop-ivcanon.c
===================================================================
--- tree-ssa-loop-ivcanon.c	(revision 236816)
+++ tree-ssa-loop-ivcanon.c	(working copy)
@@ -951,7 +951,9 @@ try_peel_loop (struct loop *loop,
   if (!flag_peel_loops || PARAM_VALUE (PARAM_MAX_PEEL_TIMES) <= 0)
     return false;
 
-  /* Peel only innermost loops.  */
+  /* Peel only innermost loops.
+     While the code is perfectly capable of peeling non-innermost loops,
+     the heuristics would probably need some improvements. */
   if (loop->inner)
     {
       if (dump_file)
@@ -969,12 +971,16 @@ 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 && flag_peel_all_loops)
+    npeel = PARAM_VALUE (PARAM_MAX_PEEL_TIMES) - 1;
+  if (npeel < 0)
     {
       if (dump_file)
         fprintf (dump_file, "Not peeling: number of iterations is not "
 	         "estimated\n");
       return false;
     }
   if (maxiter >= 0 && maxiter <= npeel)
     {
       if (dump_file)