re PR tree-optimization/58296 (ivopts is unable to handle some loops altered by the loop header copying pass)

PR tree-optimization/58296
	PR tree-optimization/41488
	* tree-scalar-evolution.c: Include necessary header files.
	(simplify_peeled_chrec): New function.
	(analyze_evolution_in_loop): New static variable.
	Call simplify_peeled_chrec.
	* tree-ssa-loop-ivopts.c (mark_bivs): Don't mark peeled IV as biv.
	(add_old_iv_candidates): Don't add candidate for peeled IV.
	* tree-affine.h (aff_combination_zero_p): New function.

	PR tree-optimization/58296
	PR tree-optimization/41488
	* gcc.dg/tree-ssa/scev-7.c: New test.
	* gcc.dg/pr41488.c: New test.
	* g++.dg/pr59445.C: New test.

From-SVN: r205959

gcc/ChangeLog

@@ -1,3 +1,15 @@
+2013-12-13  Bin Cheng  <bin.cheng@arm.com>
+
+	PR tree-optimization/58296
+	PR tree-optimization/41488
+	* tree-scalar-evolution.c: Include necessary header files.
+	(simplify_peeled_chrec): New function.
+	(analyze_evolution_in_loop): New static variable.
+	Call simplify_peeled_chrec.
+	* tree-ssa-loop-ivopts.c (mark_bivs): Don't mark peeled IV as biv.
+	(add_old_iv_candidates): Don't add candidate for peeled IV.
+	* tree-affine.h (aff_combination_zero_p): New function.
+
 2013-12-13  Nick Clifton  <nickc@redhat.com>
 
 	* config/msp430/msp430.c (is_wakeup_func): New function.  Returns

gcc/testsuite/ChangeLog

@@ -1,3 +1,11 @@
+2013-12-13  Bin Cheng  <bin.cheng@arm.com>
+
+	PR tree-optimization/58296
+	PR tree-optimization/41488
+	* gcc.dg/tree-ssa/scev-7.c: New test.
+	* gcc.dg/pr41488.c: New test.
+	* g++.dg/pr59445.C: New test.
+
 2013-12-12  Tobias Burnus  <burnus@net-b.de>
 
 	PR fortran/59440

gcc/testsuite/g++.dg/pr59445.C

@@ -0,0 +1,81 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+template <typename _Iterator> struct A;
+template <typename _Tp> struct A<_Tp *> {
+  typedef _Tp value_type;
+  typedef int difference_type;
+};
+template <typename _Compare> struct B {};
+template <typename _Compare> struct C {
+  _Compare _M_comp;
+  template <typename _Value, typename _Iterator>
+  int operator()(_Value &p1, _Iterator p2) {
+    return _M_comp(p1, *p2);
+  }
+};
+template <typename _Compare> C<_Compare> __val_comp_iter(B<_Compare>);
+template <typename _RandomAccessIterator, typename _Compare>
+void __unguarded_linear_insert(_RandomAccessIterator p1, _Compare p2) {
+  typename A<_RandomAccessIterator>::value_type a;
+  _RandomAccessIterator b = p1;
+  --b;
+  while (p2(a, b)) {
+    *p1 = 0;
+    p1 = b;
+    --b;
+  }
+}
+template <typename _RandomAccessIterator, typename _Compare>
+void __insertion_sort(_RandomAccessIterator, _Compare p2) {
+  for (_RandomAccessIterator c;; ++c)
+    __unguarded_linear_insert(c, __val_comp_iter(p2));
+}
+template <typename _RandomAccessIterator, typename _Distance, typename _Compare>
+void __chunk_insertion_sort(_RandomAccessIterator, _Distance, _Compare p3) {
+  _RandomAccessIterator d;
+  __insertion_sort(d, p3);
+}
+template <typename _RandomAccessIterator, typename _Pointer, typename _Compare>
+void __merge_sort_with_buffer(_RandomAccessIterator p1, _Pointer, _Compare p3) {
+  __chunk_insertion_sort(p1, 0, p3);
+}
+template <typename _RandomAccessIterator, typename _Pointer, typename _Distance,
+          typename _Compare>
+void __stable_sort_adaptive(_RandomAccessIterator, _Pointer, _Distance,
+                            _Compare p4) {
+  _RandomAccessIterator e;
+  __merge_sort_with_buffer(e, 0, p4);
+}
+template <typename _RandomAccessIterator, typename _Compare>
+void __stable_sort(_RandomAccessIterator p1, _Compare p2) {
+  __stable_sort_adaptive(
+      p1, 0, typename A<_RandomAccessIterator>::difference_type(), p2);
+}
+template <typename _RandomAccessIterator, typename _Compare>
+void stable_sort(_RandomAccessIterator, _RandomAccessIterator p2, _Compare) {
+  B<_Compare> f;
+  __stable_sort(p2, f);
+}
+class D {
+public:
+  void m_fn1();
+};
+class F {
+  struct G {
+    D MFI;
+    int operator()(int p1, int p2) {
+      if (p1)
+        return 0;
+      if (p2)
+        return 1;
+      MFI.m_fn1();
+    }
+  };
+  void m_fn1(int &p1) const;
+};
+void F::m_fn1(int &p1) const {
+  int *g, *h;
+  stable_sort(h, g, G());
+}
+

gcc/testsuite/gcc.dg/pr41488.c

@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-sccp-scev" } */
+
+struct struct_t
+{
+  int* data;
+};
+
+void foo (struct struct_t* sp, int start, int end)
+{
+  int i;
+
+  for (i = 0; i+start < end; i++)
+    sp->data[i+start] = 0;
+}
+
+/* { dg-final { scan-tree-dump-times "Simplify PEELED_CHREC into POLYNOMIAL_CHREC" 1 "sccp" } } */
+/* { dg-final { cleanup-tree-dump "sccp" } } */

gcc/testsuite/gcc.dg/tree-ssa/scev-7.c

@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-sccp-scev" } */
+
+struct struct_t
+{
+  int* data;
+};
+
+void foo (struct struct_t* sp, int start, int end)
+{
+  int i;
+
+  for (i = 1000; i+start > end; i--)
+    sp->data[i+start] = 0;
+}
+
+/* { dg-final { scan-tree-dump-times "Simplify PEELED_CHREC into POLYNOMIAL_CHREC" 1 "sccp" } } */
+/* { dg-final { cleanup-tree-dump "sccp" } } */

gcc/tree-affine.h

@@ -80,3 +80,16 @@ bool aff_comb_cannot_overlap_p (aff_tree *, double_int, double_int);
 
 /* Debugging functions.  */
 void debug_aff (aff_tree *);
+
+/* Return true if AFF is actually ZERO.  */
+static inline bool
+aff_combination_zero_p (aff_tree *aff)
+{
+  if (!aff)
+    return true;
+
+  if (aff->n == 0 && aff->offset.is_zero ())
+    return true;
+
+  return false;
+}

gcc/tree-scalar-evolution.c

@@ -280,6 +280,8 @@ along with GCC; see the file COPYING3.  If not see
 #include "tree-ssa.h"
 #include "cfgloop.h"
 #include "tree-chrec.h"
+#include "pointer-set.h"
+#include "tree-affine.h"
 #include "tree-scalar-evolution.h"
 #include "dumpfile.h"
 #include "params.h"
@@ -1380,6 +1382,64 @@ follow_ssa_edge (struct loop *loop, gimple def, gimple halting_phi,
 }
 
 
+/* Simplify PEELED_CHREC represented by (init_cond, arg) in LOOP.
+   Handle below case and return the corresponding POLYNOMIAL_CHREC:
+
+   # i_17 = PHI <i_13(5), 0(3)>
+   # _20 = PHI <_5(5), start_4(D)(3)>
+   ...
+   i_13 = i_17 + 1;
+   _5 = start_4(D) + i_13;
+
+   Though variable _20 appears as a PEELED_CHREC in the form of
+   (start_4, _5)_LOOP, it's a POLYNOMIAL_CHREC like {start_4, 1}_LOOP.
+
+   See PR41488.  */
+
+static tree
+simplify_peeled_chrec (struct loop *loop, tree arg, tree init_cond)
+{
+  aff_tree aff1, aff2;
+  tree ev, left, right, type, step_val;
+  pointer_map_t *peeled_chrec_map = NULL;
+
+  ev = instantiate_parameters (loop, analyze_scalar_evolution (loop, arg));
+  if (ev == NULL_TREE || TREE_CODE (ev) != POLYNOMIAL_CHREC)
+    return chrec_dont_know;
+
+  left = CHREC_LEFT (ev);
+  right = CHREC_RIGHT (ev);
+  type = TREE_TYPE (left);
+  step_val = chrec_fold_plus (type, init_cond, right);
+
+  /* Transform (init, {left, right}_LOOP)_LOOP to {init, right}_LOOP
+     if "left" equals to "init + right".  */
+  if (operand_equal_p (left, step_val, 0))
+    {
+      if (dump_file && (dump_flags & TDF_SCEV))
+	fprintf (dump_file, "Simplify PEELED_CHREC into POLYNOMIAL_CHREC.\n");
+
+      return build_polynomial_chrec (loop->num, init_cond, right);
+    }
+
+  /* Try harder to check if they are equal.  */
+  tree_to_aff_combination_expand (left, type, &aff1, &peeled_chrec_map);
+  tree_to_aff_combination_expand (step_val, type, &aff2, &peeled_chrec_map);
+  free_affine_expand_cache (&peeled_chrec_map);
+  aff_combination_scale (&aff2, double_int_minus_one);
+  aff_combination_add (&aff1, &aff2);
+
+  /* Transform (init, {left, right}_LOOP)_LOOP to {init, right}_LOOP
+     if "left" equals to "init + right".  */
+  if (aff_combination_zero_p (&aff1))
+    {
+      if (dump_file && (dump_flags & TDF_SCEV))
+	fprintf (dump_file, "Simplify PEELED_CHREC into POLYNOMIAL_CHREC.\n");
+
+      return build_polynomial_chrec (loop->num, init_cond, right);
+    }
+  return chrec_dont_know;
+}
 
 /* Given a LOOP_PHI_NODE, this function determines the evolution
    function from LOOP_PHI_NODE to LOOP_PHI_NODE in the loop.  */
@@ -1392,6 +1452,7 @@ analyze_evolution_in_loop (gimple loop_phi_node,
   tree evolution_function = chrec_not_analyzed_yet;
   struct loop *loop = loop_containing_stmt (loop_phi_node);
   basic_block bb;
+  static bool simplify_peeled_chrec_p = true;
 
   if (dump_file && (dump_flags & TDF_SCEV))
     {
@@ -1442,7 +1503,19 @@ analyze_evolution_in_loop (gimple loop_phi_node,
 	 all the other iterations it has the value of ARG.
 	 For the moment, PEELED_CHREC nodes are not built.  */
       if (res != t_true)
-	ev_fn = chrec_dont_know;
+	{
+	  ev_fn = chrec_dont_know;
+	  /* Try to recognize POLYNOMIAL_CHREC which appears in
+	     the form of PEELED_CHREC, but guard the process with
+	     a bool variable to keep the analyzer from infinite
+	     recurrence for real PEELED_RECs.  */
+	  if (simplify_peeled_chrec_p && TREE_CODE (arg) == SSA_NAME)
+	    {
+	      simplify_peeled_chrec_p = false;
+	      ev_fn = simplify_peeled_chrec (loop, arg, init_cond);
+	      simplify_peeled_chrec_p = true;
+	    }
+	}
 
       /* When there are multiple back edges of the loop (which in fact never
 	 happens currently, but nevertheless), merge their evolutions.  */

gcc/tree-ssa-loop-ivopts.c

@@ -1074,7 +1074,7 @@ find_bivs (struct ivopts_data *data)
 static void
 mark_bivs (struct ivopts_data *data)
 {
-  gimple phi;
+  gimple phi, def;
   tree var;
   struct iv *iv, *incr_iv;
   struct loop *loop = data->current_loop;
@@ -1090,6 +1090,13 @@ mark_bivs (struct ivopts_data *data)
 	continue;
 
       var = PHI_ARG_DEF_FROM_EDGE (phi, loop_latch_edge (loop));
+      def = SSA_NAME_DEF_STMT (var);
+      /* Don't mark iv peeled from other one as biv.  */
+      if (def
+	  && gimple_code (def) == GIMPLE_PHI
+	  && gimple_bb (def) == loop->header)
+	continue;
+
       incr_iv = get_iv (data, var);
       if (!incr_iv)
 	continue;
@@ -2526,11 +2533,19 @@ add_old_iv_candidates (struct ivopts_data *data, struct iv *iv)
       /* Additionally record the possibility of leaving the original iv
 	 untouched.  */
       def = PHI_ARG_DEF_FROM_EDGE (phi, loop_latch_edge (data->current_loop));
-      cand = add_candidate_1 (data,
-			      iv->base, iv->step, true, IP_ORIGINAL, NULL,
-			      SSA_NAME_DEF_STMT (def));
-      cand->var_before = iv->ssa_name;
-      cand->var_after = def;
+      /* Don't add candidate if it's from another PHI node because
+	 it's an affine iv appearing in the form of PEELED_CHREC.  */
+      phi = SSA_NAME_DEF_STMT (def);
+      if (gimple_code (phi) != GIMPLE_PHI)
+	{
+	  cand = add_candidate_1 (data,
+				  iv->base, iv->step, true, IP_ORIGINAL, NULL,
+				  SSA_NAME_DEF_STMT (def));
+	  cand->var_before = iv->ssa_name;
+	  cand->var_after = def;
+	}
+      else
+	gcc_assert (gimple_bb (phi) == data->current_loop->header);
     }
 }