re PR tree-optimization/90078 (ICE with deep templates caused by overflow)

	PR tree-optimization/90078
	* tree-ssa-loop-ivopts.c (INFTY): Increase value for infinite cost.
	(struct comp_cost): Promote type of members to int64_t.
	(infinite_cost): Don't set complexity in initialization.
	(comp_cost::operator +,-,+=,-+,/=,*=): Assert when cost computation
	overflows to infinite_cost.
	(adjust_setup_cost): Promote type of parameter and cost computation
	to int64_t.
	(struct ainc_cost_data, struct iv_ca): Promote type of member to
	int64_t.
	(get_scaled_computation_cost_at, determine_iv_cost): Promote type of
	cost computation to int64_t.
	(determine_group_iv_costs, iv_ca_dump, find_optimal_iv_set): Use
	int64_t's format specifier in dump.

	gcc/testsuite
	* g++.dg/tree-ssa/pr90078.C: New test.

From-SVN: r271008

gcc/ChangeLog

 2019-05-08  Bin Cheng  <bin.cheng@linux.alibaba.com>
 
+	PR tree-optimization/90078
+	* tree-ssa-loop-ivopts.c (inttypes.h): Include new header file.
+	(INFTY): Increase the value for infinite cost.
+	(struct comp_cost): Promote type of members to int64_t.
+	(infinite_cost): Don't set complexity in initialization.
+	(comp_cost::operator +,-,+=,-+,/=,*=): Assert when cost computation
+	overflows to infinite_cost.
+	(adjust_setup_cost): Promote type of parameter and cost computation
+	to int64_t.
+	(struct ainc_cost_data, struct iv_ca): Promote type of member to
+	int64_t.
+	(get_scaled_computation_cost_at, determine_iv_cost): Promote type of
+	cost computation to int64_t.
+	(determine_group_iv_costs, iv_ca_dump, find_optimal_iv_set): Use
+	int64_t's format specifier in dump.
+
+2019-05-08  Bin Cheng  <bin.cheng@linux.alibaba.com>
+
 	PR tree-optimization/90240
 	* tree-ssa-loop-ivopts.c (get_scaled_computation_cost_at): Scale cost
 	with respect to scaling factor pre-computed for each basic block.

gcc/testsuite/ChangeLog

 2018-05-08  Bin Cheng  <bin.cheng@linux.alibaba.com>
 
+	PR tree-optimization/90078
+	* g++.dg/tree-ssa/pr90078.C: New test.
+
+2018-05-08  Bin Cheng  <bin.cheng@linux.alibaba.com>
+
 	PR tree-optimization/90240
 	* gfortran.dg/graphite/pr90240.f: New test.
 

gcc/testsuite/g++.dg/tree-ssa/pr90078.C

+// { dg-do compile }
+// { dg-options "-std=c++14 -O2 -ftemplate-depth=1000000" }
+
+template <class T, int Dim0, int Dim1, int Dim2> struct Tensor3;
+template <class A, class T, int Dim0, int Dim1, int Dim2, char i, char j,
+          char k>
+struct Tensor3_Expr;
+
+template <class T, int Dim0, int Dim1, int Dim2, int Dim3> struct Tensor4;
+template <class A, class T, int Dim0, int Dim1, int Dim2, int Dim3, char i,
+          char j, char k, char l>
+struct Tensor4_Expr;
+
+template <char i, int Dim> struct Index
+{};
+template <const int N> struct Number
+{
+  Number(){};
+  operator int() const { return N; }
+};
+
+template <class T, int Tensor_Dim0, int Tensor_Dim1, int Tensor_Dim2>
+struct Tensor3
+{
+  T data[Tensor_Dim0][Tensor_Dim1][Tensor_Dim2];
+
+  T operator()(const int N1, const int N2, const int N3) const
+  {
+    return data[N1][N2][N3];
+  }
+
+  template <char i, char j, char k, int Dim0, int Dim1, int Dim2>
+  Tensor3_Expr<const Tensor3<T, Tensor_Dim0, Tensor_Dim1, Tensor_Dim2>, T,
+               Dim0, Dim1, Dim2, i, j, k>
+  operator()(const Index<i, Dim0>, const Index<j, Dim1>,
+             const Index<k, Dim2>) const
+  {
+    return Tensor3_Expr<const Tensor3<T, Tensor_Dim0, Tensor_Dim1, Tensor_Dim2>,
+                        T, Dim0, Dim1, Dim2, i, j, k>(*this);
+  }
+};
+
+template <class A, class T, int Dim0, int Dim1, int Dim2, char i, char j,
+          char k>
+struct Tensor3_Expr
+{
+  A iter;
+
+  Tensor3_Expr(const A &a) : iter(a) {}
+  T operator()(const int N1, const int N2, const int N3) const
+  {
+    return iter(N1, N2, N3);
+  }
+};
+
+template <class A, class T, int Tensor_Dim0, int Tensor_Dim1, int Tensor_Dim2,
+          int Dim0, int Dim1, int Dim2, char i, char j, char k>
+struct Tensor3_Expr<Tensor3<A, Tensor_Dim0, Tensor_Dim1, Tensor_Dim2>, T, Dim0,
+                   Dim1, Dim2, i, j, k>
+{
+  Tensor3<A, Tensor_Dim0, Tensor_Dim1, Tensor_Dim2> &iter;
+
+  Tensor3_Expr(Tensor3<A, Tensor_Dim0, Tensor_Dim1, Tensor_Dim2> &a) : iter(a)
+  {}
+  T operator()(const int N1, const int N2, const int N3) const
+  {
+    return iter(N1, N2, N3);
+  }
+};
+
+template <class A, class B, class T, class U, int Dim0, int Dim1, int Dim23,
+          int Dim4, int Dim5, char i, char j, char k, char l, char m>
+struct Tensor3_times_Tensor3_21
+{
+  Tensor3_Expr<A, T, Dim0, Dim1, Dim23, i, j, k> iterA;
+  Tensor3_Expr<B, U, Dim23, Dim4, Dim5, k, l, m> iterB;
+
+  template <int CurrentDim>
+  T eval(const int N1, const int N2, const int N3, const int N4,
+         const Number<CurrentDim> &) const
+  {
+    return iterA(N1, N2, CurrentDim - 1) * iterB(CurrentDim - 1, N3, N4)
+           + eval(N1, N2, N3, N4, Number<CurrentDim - 1>());
+  }
+  T eval(const int N1, const int N2, const int N3, const int N4,
+         const Number<1> &) const
+  {
+    return iterA(N1, N2, 0) * iterB(0, N3, N4);
+  }
+
+  Tensor3_times_Tensor3_21(
+    const Tensor3_Expr<A, T, Dim0, Dim1, Dim23, i, j, k> &a,
+    const Tensor3_Expr<B, U, Dim23, Dim4, Dim5, k, l, m> &b)
+      : iterA(a), iterB(b)
+  {}
+  T operator()(const int &N1, const int &N2, const int &N3,
+               const int &N4) const
+  {
+    return eval(N1, N2, N3, N4, Number<Dim23>());
+  }
+};
+
+template <class A, class B, class T, class U, int Dim0, int Dim1, int Dim23,
+          int Dim4, int Dim5, char i, char j, char k, char l, char m>
+Tensor4_Expr<Tensor3_times_Tensor3_21<A, B, T, U, Dim0, Dim1, Dim23, Dim4,
+                                      Dim5, i, j, k, l, m>,
+             T, Dim0, Dim1, Dim4, Dim5, i, j, l, m>
+operator*(const Tensor3_Expr<A, T, Dim0, Dim1, Dim23, i, j, k> &a,
+          const Tensor3_Expr<B, U, Dim23, Dim4, Dim5, k, l, m> &b)
+{
+  using TensorExpr = Tensor3_times_Tensor3_21<A, B, T, U, Dim0, Dim1, Dim23,
+                                              Dim4, Dim5, i, j, k, l, m>;
+  return Tensor4_Expr<TensorExpr, T, Dim0, Dim1, Dim4, Dim5, i, j, l, m>(
+    TensorExpr(a, b));
+};
+
+template <class T, int Tensor_Dim0, int Tensor_Dim1, int Tensor_Dim2,
+          int Tensor_Dim3>
+struct Tensor4
+{
+  T data[Tensor_Dim0][Tensor_Dim1][Tensor_Dim2][Tensor_Dim3];
+
+  Tensor4() {}
+  T &operator()(const int N1, const int N2, const int N3, const int N4)
+  {
+    return data[N1][N2][N3][N4];
+  }
+
+  template <char i, char j, char k, char l, int Dim0, int Dim1, int Dim2,
+            int Dim3>
+  Tensor4_Expr<Tensor4<T, Tensor_Dim0, Tensor_Dim1, Tensor_Dim2, Tensor_Dim3>,
+               T, Dim0, Dim1, Dim2, Dim3, i, j, k, l>
+  operator()(const Index<i, Dim0>, const Index<j, Dim1>, const Index<k, Dim2>,
+             const Index<l, Dim3>)
+  {
+    return Tensor4_Expr<
+      Tensor4<T, Tensor_Dim0, Tensor_Dim1, Tensor_Dim2, Tensor_Dim3>, T, Dim0,
+      Dim1, Dim2, Dim3, i, j, k, l>(*this);
+  };
+};
+
+template <class A, class T, int Dim0, int Dim1, int Dim2, int Dim3, char i,
+          char j, char k, char l>
+struct Tensor4_Expr
+{
+  A iter;
+
+  Tensor4_Expr(const A &a) : iter(a) {}
+  T operator()(const int N1, const int N2, const int N3, const int N4) const
+  {
+    return iter(N1, N2, N3, N4);
+  }
+};
+
+template <class A, class T, int Dim0, int Dim1, int Dim2, int Dim3, char i,
+          char j, char k, char l>
+struct Tensor4_Expr<Tensor4<A, Dim0, Dim1, Dim2, Dim3>, T, Dim0, Dim1, Dim2,
+                   Dim3, i, j, k, l>
+{
+  Tensor4<A, Dim0, Dim1, Dim2, Dim3> &iter;
+
+  Tensor4_Expr(Tensor4<A, Dim0, Dim1, Dim2, Dim3> &a) : iter(a) {}
+  T operator()(const int N1, const int N2, const int N3, const int N4) const
+  {
+    return iter(N1, N2, N3, N4);
+  }
+
+  template <class B, class U, int Dim1_0, int Dim1_1, int Dim1_2, int Dim1_3,
+            char i_1, char j_1, char k_1, char l_1>
+  auto &operator=(const Tensor4_Expr<B, U, Dim1_0, Dim1_1, Dim1_2, Dim1_3, i_1,
+                                     j_1, k_1, l_1> &rhs)
+  {
+    for(int ii = 0; ii < Dim0; ++ii)
+      for(int jj = 0; jj < Dim1; ++jj)
+        for(int kk = 0; kk < Dim2; ++kk)
+          for(int ll = 0; ll < Dim3; ++ll)
+            {
+              iter(ii, jj, kk, ll) = rhs(ii, jj, kk, ll);
+            }
+    return *this;
+  }
+};
+
+int main()
+{
+  Tensor3<float, 100, 100, 1000> t1;
+  Tensor3<float, 1000, 100, 100> t2;
+
+  Index<'l', 100> l;
+  Index<'m', 100> m;
+  Index<'k', 1000> k;
+  Index<'n', 100> n;
+  Index<'o', 100> o;
+
+  Tensor4<float, 100, 100, 100, 100> res;
+  res(l, m, n, o) = t1(l, m, k) * t2(k, n, o);
+  return 0;
+}
+

gcc/tree-ssa-loop-ivopts.c

@@ -114,7 +114,7 @@ along with GCC; see the file COPYING3.  If not see
    interface between the GIMPLE and RTL worlds.  */
 
 /* The infinite cost.  */
-#define INFTY 10000000
+#define INFTY 1000000000
 
 /* Returns the expected number of loop iterations for LOOP.
    The average trip count is computed from profile data if it
@@ -180,7 +180,7 @@ struct comp_cost
   comp_cost (): cost (0), complexity (0), scratch (0)
   {}
 
-  comp_cost (int cost, unsigned complexity, int scratch = 0)
+  comp_cost (int64_t cost, unsigned complexity, int64_t scratch = 0)
     : cost (cost), complexity (complexity), scratch (scratch)
   {}
 
@@ -220,16 +220,16 @@ struct comp_cost
   /* Returns true if COST1 is smaller or equal than COST2.  */
   friend bool operator<= (comp_cost cost1, comp_cost cost2);
 
-  int cost;		/* The runtime cost.  */
+  int64_t cost;		/* The runtime cost.  */
   unsigned complexity;  /* The estimate of the complexity of the code for
 			   the computation (in no concrete units --
 			   complexity field should be larger for more
 			   complex expressions and addressing modes).  */
-  int scratch;		/* Scratch used during cost computation.  */
+  int64_t scratch;	/* Scratch used during cost computation.  */
 };
 
 static const comp_cost no_cost;
-static const comp_cost infinite_cost (INFTY, INFTY, INFTY);
+static const comp_cost infinite_cost (INFTY, 0, INFTY);
 
 bool
 comp_cost::infinite_cost_p ()
@@ -243,6 +243,7 @@ operator+ (comp_cost cost1, comp_cost cost2)
   if (cost1.infinite_cost_p () || cost2.infinite_cost_p ())
     return infinite_cost;
 
+  gcc_assert (cost1.cost + cost2.cost < infinite_cost.cost);
   cost1.cost += cost2.cost;
   cost1.complexity += cost2.complexity;
 
@@ -256,6 +257,7 @@ operator- (comp_cost cost1, comp_cost cost2)
     return infinite_cost;
 
   gcc_assert (!cost2.infinite_cost_p ());
+  gcc_assert (cost1.cost - cost2.cost < infinite_cost.cost);
 
   cost1.cost -= cost2.cost;
   cost1.complexity -= cost2.complexity;
@@ -276,6 +278,7 @@ comp_cost::operator+= (HOST_WIDE_INT c)
   if (infinite_cost_p ())
     return *this;
 
+  gcc_assert (this->cost + c < infinite_cost.cost);
   this->cost += c;
 
   return *this;
@@ -287,6 +290,7 @@ comp_cost::operator-= (HOST_WIDE_INT c)
   if (infinite_cost_p ())
     return *this;
 
+  gcc_assert (this->cost - c < infinite_cost.cost);
   this->cost -= c;
 
   return *this;
@@ -295,6 +299,7 @@ comp_cost::operator-= (HOST_WIDE_INT c)
 comp_cost
 comp_cost::operator/= (HOST_WIDE_INT c)
 {
+  gcc_assert (c != 0);
   if (infinite_cost_p ())
     return *this;
 
@@ -309,6 +314,7 @@ comp_cost::operator*= (HOST_WIDE_INT c)
   if (infinite_cost_p ())
     return *this;
 
+  gcc_assert (this->cost * c < infinite_cost.cost);
   this->cost *= c;
 
   return *this;
@@ -638,7 +644,7 @@ struct iv_ca
   comp_cost cand_use_cost;
 
   /* Total cost of candidates.  */
-  unsigned cand_cost;
+  int64_t cand_cost;
 
   /* Number of times each invariant variable is used.  */
   unsigned *n_inv_var_uses;
@@ -4025,16 +4031,16 @@ get_computation_at (struct loop *loop, gimple *at,
    if we're optimizing for speed, amortize it over the per-iteration cost.
    If ROUND_UP_P is true, the result is round up rather than to zero when
    optimizing for speed.  */
-static unsigned
-adjust_setup_cost (struct ivopts_data *data, unsigned cost,
+static int64_t
+adjust_setup_cost (struct ivopts_data *data, int64_t cost,
 		   bool round_up_p = false)
 {
   if (cost == INFTY)
     return cost;
   else if (optimize_loop_for_speed_p (data->current_loop))
     {
-      HOST_WIDE_INT niters = avg_loop_niter (data->current_loop);
-      return ((HOST_WIDE_INT) cost + (round_up_p ? niters - 1 : 0)) / niters;
+      int64_t niters = (int64_t) avg_loop_niter (data->current_loop);
+      return (cost + (round_up_p ? niters - 1 : 0)) / niters;
     }
   else
     return cost;
@@ -4305,7 +4311,7 @@ enum ainc_type
 
 struct ainc_cost_data
 {
-  unsigned costs[AINC_NONE];
+  int64_t costs[AINC_NONE];
 };
 
 static comp_cost
@@ -4566,12 +4572,12 @@ get_scaled_computation_cost_at (ivopts_data *data, gimple *at, comp_cost cost)
       if (scale_factor == 1)
 	return cost;
 
-      int scaled_cost
+      int64_t scaled_cost
 	= cost.scratch + (cost.cost - cost.scratch) * scale_factor;
 
       if (dump_file && (dump_flags & TDF_DETAILS))
-	fprintf (dump_file, "Scaling cost based on bb prob "
-		 "by %2.2f: %d (scratch: %d) -> %d\n",
+	fprintf (dump_file, "Scaling cost based on bb prob by %2.2f: "
+		 "%" PRId64 " (scratch: %" PRId64 ") -> %" PRId64 "\n",
 		 1.0f * scale_factor, cost.cost, cost.scratch, scaled_cost);
 
       cost.cost = scaled_cost;
@@ -5539,7 +5545,7 @@ determine_group_iv_costs (struct ivopts_data *data)
 		  || group->cost_map[j].cost.infinite_cost_p ())
 		continue;
 
-	      fprintf (dump_file, "  %d\t%d\t%d\t",
+	      fprintf (dump_file, "  %d\t%" PRId64 "\t%d\t",
 		       group->cost_map[j].cand->id,
 		       group->cost_map[j].cost.cost,
 		       group->cost_map[j].cost.complexity);
@@ -5569,7 +5575,7 @@ static void
 determine_iv_cost (struct ivopts_data *data, struct iv_cand *cand)
 {
   comp_cost cost_base;
-  unsigned cost, cost_step;
+  int64_t cost, cost_step;
   tree base;
 
   gcc_assert (cand->iv != NULL);
@@ -6139,11 +6145,11 @@ iv_ca_dump (struct ivopts_data *data, FILE *file, struct iv_ca *ivs)
   unsigned i;
   comp_cost cost = iv_ca_cost (ivs);
 
-  fprintf (file, "  cost: %d (complexity %d)\n", cost.cost,
+  fprintf (file, "  cost: %" PRId64 " (complexity %d)\n", cost.cost,
 	   cost.complexity);
-  fprintf (file, "  cand_cost: %d\n  cand_group_cost: %d (complexity %d)\n",
-	   ivs->cand_cost, ivs->cand_use_cost.cost,
-	   ivs->cand_use_cost.complexity);
+  fprintf (file, "  cand_cost: %" PRId64 "\n  cand_group_cost: "
+	   "%" PRId64 " (complexity %d)\n", ivs->cand_cost,
+	   ivs->cand_use_cost.cost, ivs->cand_use_cost.complexity);
   bitmap_print (file, ivs->cands, "  candidates: ","\n");
 
   for (i = 0; i < ivs->upto; i++)
@@ -6151,9 +6157,9 @@ iv_ca_dump (struct ivopts_data *data, FILE *file, struct iv_ca *ivs)
       struct iv_group *group = data->vgroups[i];
       struct cost_pair *cp = iv_ca_cand_for_group (ivs, group);
       if (cp)
-        fprintf (file, "   group:%d --> iv_cand:%d, cost=(%d,%d)\n",
-		 group->id, cp->cand->id, cp->cost.cost,
-		 cp->cost.complexity);
+        fprintf (file, "   group:%d --> iv_cand:%d, cost=("
+		 "%" PRId64 ",%d)\n", group->id, cp->cand->id,
+		 cp->cost.cost, cp->cost.complexity);
       else
 	fprintf (file, "   group:%d --> ??\n", group->id);
     }
@@ -6751,9 +6757,9 @@ find_optimal_iv_set (struct ivopts_data *data)
 
   if (dump_file && (dump_flags & TDF_DETAILS))
     {
-      fprintf (dump_file, "Original cost %d (complexity %d)\n\n",
+      fprintf (dump_file, "Original cost %" PRId64 " (complexity %d)\n\n",
 	       origcost.cost, origcost.complexity);
-      fprintf (dump_file, "Final cost %d (complexity %d)\n\n",
+      fprintf (dump_file, "Final cost %" PRId64 " (complexity %d)\n\n",
 	       cost.cost, cost.complexity);
     }