2015-12-14 Richard Biener <rguenther@suse.de>

	PR tree-optimization/68852
	* tree-vectorizer.h (struct _slp_tree): Add def_type member.
	(SLP_TREE_DEF_TYPE): New accessor.
	* tree-vect-stmts.c (vect_is_simple_use): Remove BB vectorization
	hack.
	* tree-vect-slp.c (vect_create_new_slp_node): Initialize
	SLP_TREE_DEF_TYPE.
	(vect_build_slp_tree): When a node is to be built up from scalars
	do not push a NULL as child but instead set its def_type to
	vect_external_def.
	(vect_analyze_slp_cost_1): Check for child def-type instead
	of NULL.
	(vect_detect_hybrid_slp_stmts): Likewise.
	(vect_bb_slp_scalar_cost): Likewise.
	(vect_get_slp_defs): Likewise.
	(vect_slp_analyze_node_operations): Likewise.  Before
	processing node push the children def-types to the underlying
	stmts vinfo and restore it afterwards.
	(vect_schedule_slp_instance): Likewise.
	(vect_slp_analyze_bb_1): Do not mark stmts not in SLP instances
	as not vectorizable.

	* g++.dg/torture/pr68852.C: New testcase.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@231619 138bc75d-0d04-0410-961f-82ee72b054a4

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index abffbd7..35a0586 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,29 @@
 2015-12-14  Richard Biener  <rguenther@suse.de>
 
+       PR tree-optimization/68852
+       * tree-vectorizer.h (struct _slp_tree): Add def_type member.
+       (SLP_TREE_DEF_TYPE): New accessor.
+       * tree-vect-stmts.c (vect_is_simple_use): Remove BB vectorization
+       hack.
+       * tree-vect-slp.c (vect_create_new_slp_node): Initialize
+       SLP_TREE_DEF_TYPE.
+       (vect_build_slp_tree): When a node is to be built up from scalars
+       do not push a NULL as child but instead set its def_type to
+       vect_external_def.
+       (vect_analyze_slp_cost_1): Check for child def-type instead
+       of NULL.
+       (vect_detect_hybrid_slp_stmts): Likewise.
+       (vect_bb_slp_scalar_cost): Likewise.
+       (vect_get_slp_defs): Likewise.
+       (vect_slp_analyze_node_operations): Likewise.  Before
+       processing node push the children def-types to the underlying
+       stmts vinfo and restore it afterwards.
+       (vect_schedule_slp_instance): Likewise.
+       (vect_slp_analyze_bb_1): Do not mark stmts not in SLP instances
+       as not vectorizable.
+
+2015-12-14  Richard Biener  <rguenther@suse.de>
+
        PR tree-optimization/68775
        * tree-vect-slp.c (vect_build_slp_tree): Make sure to apply
        a operand swapping even if replacing the op with scalars.

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 9eb3efc..45db39a 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2015-12-14  Richard Biener  <rguenther@suse.de>
+
+       PR tree-optimization/68852
+       * g++.dg/torture/pr68852.C: New testcase.
+
 2015-12-14  Alexander Monakov  <amonakov@ispras.ru>
 
        * gcc.dg/builtin-return-1.c: Correct effective-target test.

diff --git a/gcc/testsuite/g++.dg/torture/pr68852.C b/gcc/testsuite/g++.dg/torture/pr68852.C
new file mode 100644 (file)
index 0000000..4172751
--- /dev/null
+++ b/gcc/testsuite/g++.dg/torture/pr68852.C
@@ -0,0 +1,51 @@
+/* { dg-do compile } */
+
+struct A {
+    double x, y, z, w;
+    A() {}
+    A(double, double p2, double p3, double) : y(p2), z(p3) {}
+    void m_fn1();
+};
+
+struct B {
+    double x, y;
+};
+struct D : A {
+    D() {}
+    D(double p1, double p2, double p3, double p4) : A(p1, p2, p3, p4) {}
+};
+
+class C {
+public:
+    float _11, _12, _13, _14;
+    float _21, _22, _23, _24;
+    float _31, _32, _33, _34;
+    float _41, _42, _43, _44;
+    D m_fn2(B p1) {
+       double z(p1.x + _43);
+       return *this * D(p1.x, p1.y, z, 1);
+    }
+    int ProjectRectBounds_next;
+    B __trans_tmp_3;
+    int m_fn3(int) {
+       B a, b;
+       D c[1];
+       b = __trans_tmp_3;
+       c[2] = m_fn2(b);
+       c[3] = m_fn2(a);
+       c[ProjectRectBounds_next].m_fn1();
+    }
+    D operator*(D p1) {
+       D d;
+       d.x = p1.x * _11 + p1.y * _21 + p1.z * _31 + _41;
+       d.y = p1.x * _12 + p1.y * _22 + p1.z * _32 + _42;
+       d.z = p1.x * _13 + p1.y * _23 + p1.z * _33 + _43;
+       d.w = p1.x * _14 + p1.y * _24 + p1.z * _34 + _44;
+       return d;
+    }
+};
+
+void fn1() {
+    C e;
+    int f = e.m_fn3(f);
+}

diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index d355919..b87b3d4 100644 (file)
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -51,9 +51,6 @@ vect_free_slp_tree (slp_tree node)
   int i;
   slp_tree child;
 
-  if (!node)
-    return;
-
   FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
     vect_free_slp_tree (child);
 
@@ -103,6 +100,7 @@ vect_create_new_slp_node (vec<gimple *> scalar_stmts)
   SLP_TREE_CHILDREN (node).create (nops);
   SLP_TREE_LOAD_PERMUTATION (node) = vNULL;
   SLP_TREE_TWO_OPERATORS (node) = false;
+  SLP_TREE_DEF_TYPE (node) = vect_internal_def;
 
   return node;
 }
@@ -938,7 +936,7 @@ vect_build_slp_tree (vec_info *vinfo,
              slp_tree grandchild;
 
              FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (child), j, grandchild)
-               if (grandchild != NULL)
+               if (SLP_TREE_DEF_TYPE (grandchild) == vect_internal_def)
                  break;
              if (!grandchild)
                {
@@ -946,15 +944,15 @@ vect_build_slp_tree (vec_info *vinfo,
                  *max_nunits = old_max_nunits;
                  loads->truncate (old_nloads);
                  FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (child), j, grandchild)
-                     vect_free_slp_tree (grandchild);
+                   vect_free_slp_tree (grandchild);
                  SLP_TREE_CHILDREN (child).truncate (0);
 
                  dump_printf_loc (MSG_NOTE, vect_location,
                                   "Building parent vector operands from "
                                   "scalars instead\n");
                  oprnd_info->def_stmts = vNULL;
-                 vect_free_slp_tree (child);
-                 SLP_TREE_CHILDREN (*node).quick_push (NULL);
+                 SLP_TREE_DEF_TYPE (child) = vect_external_def;
+                 SLP_TREE_CHILDREN (*node).quick_push (child);
                  continue;
                }
            }
@@ -992,8 +990,8 @@ vect_build_slp_tree (vec_info *vinfo,
          dump_printf_loc (MSG_NOTE, vect_location,
                           "Building vector operands from scalars\n");
          oprnd_info->def_stmts = vNULL;
-         vect_free_slp_tree (child);
-         SLP_TREE_CHILDREN (*node).quick_push (NULL);
+         SLP_TREE_DEF_TYPE (child) = vect_external_def;
+         SLP_TREE_CHILDREN (*node).quick_push (child);
          continue;
        }
 
@@ -1066,7 +1064,7 @@ vect_build_slp_tree (vec_info *vinfo,
                  slp_tree grandchild;
 
                  FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (child), j, grandchild)
-                   if (grandchild != NULL)
+                   if (SLP_TREE_DEF_TYPE (grandchild) == vect_internal_def)
                      break;
                  if (!grandchild)
                    {
@@ -1081,8 +1079,8 @@ vect_build_slp_tree (vec_info *vinfo,
                                       "Building parent vector operands from "
                                       "scalars instead\n");
                      oprnd_info->def_stmts = vNULL;
-                     vect_free_slp_tree (child);
-                     SLP_TREE_CHILDREN (*node).quick_push (NULL);
+                     SLP_TREE_DEF_TYPE (child) = vect_external_def;
+                     SLP_TREE_CHILDREN (*node).quick_push (child);
                      continue;
                    }
                }
@@ -1117,10 +1115,9 @@ vect_print_slp_tree (int dump_kind, location_t loc, slp_tree node)
   gimple *stmt;
   slp_tree child;
 
-  if (!node)
-    return;
-
-  dump_printf_loc (dump_kind, loc, "node\n");
+  dump_printf_loc (dump_kind, loc, "node%s\n",
+                  SLP_TREE_DEF_TYPE (node) != vect_internal_def
+                  ? " (external)" : "");
   FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), i, stmt)
     {
       dump_printf_loc (dump_kind, loc, "\tstmt %d ", i);
@@ -1143,7 +1140,7 @@ vect_mark_slp_stmts (slp_tree node, enum slp_vect_type mark, int j)
   gimple *stmt;
   slp_tree child;
 
-  if (!node)
+  if (SLP_TREE_DEF_TYPE (node) != vect_internal_def)
     return;
 
   FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), i, stmt)
@@ -1165,7 +1162,7 @@ vect_mark_slp_stmts_relevant (slp_tree node)
   stmt_vec_info stmt_info;
   slp_tree child;
 
-  if (!node)
+  if (SLP_TREE_DEF_TYPE (node) != vect_internal_def)
     return;
 
   FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), i, stmt)
@@ -1403,7 +1400,7 @@ vect_analyze_slp_cost_1 (slp_instance instance, slp_tree node,
                         stmt_vector_for_cost *body_cost_vec,
                         unsigned ncopies_for_cost)
 {
-  unsigned i;
+  unsigned i, j;
   slp_tree child;
   gimple *stmt, *s;
   stmt_vec_info stmt_info;
@@ -1412,7 +1409,7 @@ vect_analyze_slp_cost_1 (slp_instance instance, slp_tree node,
 
   /* Recurse down the SLP tree.  */
   FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
-    if (child)
+    if (SLP_TREE_DEF_TYPE (child) == vect_internal_def)
       vect_analyze_slp_cost_1 (instance, child, prologue_cost_vec,
                               body_cost_vec, ncopies_for_cost);
 
@@ -1467,9 +1464,16 @@ vect_analyze_slp_cost_1 (slp_instance instance, slp_tree node,
        }
     }
 
+  /* Push SLP node def-type to stmts.  */
+  FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
+    if (SLP_TREE_DEF_TYPE (child) != vect_internal_def)
+      FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (child), j, stmt)
+       STMT_VINFO_DEF_TYPE (vinfo_for_stmt (stmt)) = SLP_TREE_DEF_TYPE (child);
+
   /* Scan operands and account for prologue cost of constants/externals.
      ???  This over-estimates cost for multiple uses and should be
      re-engineered.  */
+  stmt = SLP_TREE_SCALAR_STMTS (node)[0];
   lhs = gimple_get_lhs (stmt);
   for (i = 0; i < gimple_num_ops (stmt); ++i)
     {
@@ -1492,6 +1496,12 @@ vect_analyze_slp_cost_1 (slp_instance instance, slp_tree node,
                              stmt_info, 0, vect_prologue);
        }
     }
+
+  /* Restore stmt def-types.  */
+  FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
+    if (SLP_TREE_DEF_TYPE (child) != vect_internal_def)
+      FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (child), j, stmt)
+       STMT_VINFO_DEF_TYPE (vinfo_for_stmt (stmt)) = vect_internal_def;
 }
 
 /* Compute the cost for the SLP instance INSTANCE.  */
@@ -1798,6 +1808,33 @@ vect_analyze_slp_instance (vec_info *vinfo,
             }
         }
 
+      /* If the loads and stores can be handled with load/store-lane
+         instructions do not generate this SLP instance.  */
+      if (is_a <loop_vec_info> (vinfo)
+         && loads_permuted
+         && dr && vect_store_lanes_supported (vectype, group_size))
+       {
+         slp_tree load_node;
+         FOR_EACH_VEC_ELT (loads, i, load_node)
+           {
+             gimple *first_stmt = GROUP_FIRST_ELEMENT
+                 (vinfo_for_stmt (SLP_TREE_SCALAR_STMTS (load_node)[0]));
+             stmt_vec_info stmt_vinfo = vinfo_for_stmt (first_stmt);
+             if (! vect_load_lanes_supported (STMT_VINFO_VECTYPE (stmt_vinfo),
+                                              GROUP_SIZE (stmt_vinfo)))
+               break;
+           }
+         if (i == loads.length ())
+           {
+             if (dump_enabled_p ())
+               dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
+                                "Built SLP cancelled: can use "
+                                "load/store-lanes\n");
+              vect_free_slp_instance (new_instance);
+              return false;
+           }
+       }
+
       vinfo->slp_instances.safe_push (new_instance);
 
       if (dump_enabled_p ())
@@ -2007,7 +2044,7 @@ vect_detect_hybrid_slp_stmts (slp_tree node, unsigned i, slp_vect_type stype)
     }
 
   FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), j, child)
-    if (child)
+    if (SLP_TREE_DEF_TYPE (child) != vect_external_def)
       vect_detect_hybrid_slp_stmts (child, i, stype);
 }
 
@@ -2188,17 +2225,24 @@ static bool
 vect_slp_analyze_node_operations (slp_tree node)
 {
   bool dummy;
-  int i;
+  int i, j;
   gimple *stmt;
   slp_tree child;
 
-  if (!node)
+  if (SLP_TREE_DEF_TYPE (node) != vect_internal_def)
     return true;
 
   FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
     if (!vect_slp_analyze_node_operations (child))
       return false;
 
+  /* Push SLP node def-type to stmts.  */
+  FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
+    if (SLP_TREE_DEF_TYPE (child) != vect_internal_def)
+      FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (child), j, stmt)
+       STMT_VINFO_DEF_TYPE (vinfo_for_stmt (stmt)) = SLP_TREE_DEF_TYPE (child);
+
+  bool res = true;
   FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), i, stmt)
     {
       stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
@@ -2206,10 +2250,19 @@ vect_slp_analyze_node_operations (slp_tree node)
       gcc_assert (STMT_SLP_TYPE (stmt_info) != loop_vect);
 
       if (!vect_analyze_stmt (stmt, &dummy, node))
-       return false;
+       {
+         res = false;
+         break;
+       }
     }
 
-  return true;
+  /* Restore stmt def-types.  */
+  FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
+    if (SLP_TREE_DEF_TYPE (child) != vect_internal_def)
+      FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (child), j, stmt)
+       STMT_VINFO_DEF_TYPE (vinfo_for_stmt (stmt)) = vect_internal_def;
+
+  return res;
 }
 
 
@@ -2289,7 +2342,7 @@ vect_bb_slp_scalar_cost (basic_block bb,
            if (!is_gimple_debug (use_stmt)
                && (! vect_stmt_in_region_p (vinfo_for_stmt (stmt)->vinfo,
                                             use_stmt)
-                   || !STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (use_stmt))))
+                   || ! PURE_SLP_STMT (vinfo_for_stmt (use_stmt))))
              {
                (*life)[i] = true;
                BREAK_FROM_IMM_USE_STMT (use_iter);
@@ -2313,7 +2366,7 @@ vect_bb_slp_scalar_cost (basic_block bb,
     }
 
   FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
-    if (child)
+    if (SLP_TREE_DEF_TYPE (child) == vect_internal_def)
       scalar_cost += vect_bb_slp_scalar_cost (bb, child, life);
 
   return scalar_cost;
@@ -2502,15 +2555,6 @@ vect_slp_analyze_bb_1 (gimple_stmt_iterator region_begin,
       return NULL;
     }
 
-  /* Mark all the statements that we do not want to vectorize.  */
-  for (gimple_stmt_iterator gsi = bb_vinfo->region_begin;
-       gsi_stmt (gsi) != gsi_stmt (bb_vinfo->region_end); gsi_next (&gsi))
-    {
-      stmt_vec_info vinfo = vinfo_for_stmt (gsi_stmt (gsi));
-      if (STMT_SLP_TYPE (vinfo) != pure_slp)
-       STMT_VINFO_VECTORIZABLE (vinfo) = false;
-    }
-
   if (!vect_slp_analyze_operations (BB_VINFO_SLP_INSTANCES (bb_vinfo),
                                    BB_VINFO_TARGET_COST_DATA (bb_vinfo)))
     {
@@ -3088,7 +3132,7 @@ vect_get_slp_defs (vec<tree> ops, slp_tree slp_node,
           child = SLP_TREE_CHILDREN (slp_node)[child_index];
 
          /* We have to check both pattern and original def, if available.  */
-         if (child)
+         if (SLP_TREE_DEF_TYPE (child) == vect_internal_def)
            {
              gimple *first_def = SLP_TREE_SCALAR_STMTS (child)[0];
              gimple *related
@@ -3377,15 +3421,21 @@ vect_schedule_slp_instance (slp_tree node, slp_instance instance,
   stmt_vec_info stmt_info;
   unsigned int vec_stmts_size, nunits, group_size;
   tree vectype;
-  int i;
+  int i, j;
   slp_tree child;
 
-  if (!node)
+  if (SLP_TREE_DEF_TYPE (node) != vect_internal_def)
     return false;
 
   FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
     vect_schedule_slp_instance (child, instance, vectorization_factor);
 
+  /* Push SLP node def-type to stmts.  */
+  FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
+    if (SLP_TREE_DEF_TYPE (child) != vect_internal_def)
+      FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (child), j, stmt)
+       STMT_VINFO_DEF_TYPE (vinfo_for_stmt (stmt)) = SLP_TREE_DEF_TYPE (child);
+
   stmt = SLP_TREE_SCALAR_STMTS (node)[0];
   stmt_info = vinfo_for_stmt (stmt);
 
@@ -3504,6 +3554,13 @@ vect_schedule_slp_instance (slp_tree node, slp_instance instance,
        }
     }
   is_store = vect_transform_stmt (stmt, &si, &grouped_store, node, instance);
+
+  /* Restore stmt def-types.  */
+  FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)
+    if (SLP_TREE_DEF_TYPE (child) != vect_internal_def)
+      FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (child), j, stmt)
+       STMT_VINFO_DEF_TYPE (vinfo_for_stmt (stmt)) = vect_internal_def;
+
   return is_store;
 }
 
@@ -3522,7 +3579,7 @@ vect_remove_slp_scalar_calls (slp_tree node)
   tree lhs;
   stmt_vec_info stmt_info;
 
-  if (!node)
+  if (SLP_TREE_DEF_TYPE (node) != vect_internal_def)
     return;
 
   FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child)

diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index abcd9a4..b1342fb 100644 (file)
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -8649,10 +8649,7 @@ vect_is_simple_use (tree operand, vec_info *vinfo,
   else
     {
       stmt_vec_info stmt_vinfo = vinfo_for_stmt (*def_stmt);
-      if (is_a <bb_vec_info> (vinfo) && !STMT_VINFO_VECTORIZABLE (stmt_vinfo))
-       *dt = vect_external_def;
-      else
-       *dt = STMT_VINFO_DEF_TYPE (stmt_vinfo);
+      *dt = STMT_VINFO_DEF_TYPE (stmt_vinfo);
     }
 
   if (dump_enabled_p ())

diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index b07f270..ac68750 100644 (file)
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -107,6 +107,8 @@ struct _slp_tree {
   unsigned int vec_stmts_size;
   /* Whether the scalar computations use two different operators.  */
   bool two_operators;
+  /* The DEF type of this node.  */
+  enum vect_def_type def_type;
 };
 
 
@@ -139,6 +141,7 @@ typedef struct _slp_instance {
 #define SLP_TREE_NUMBER_OF_VEC_STMTS(S)          (S)->vec_stmts_size
 #define SLP_TREE_LOAD_PERMUTATION(S)             (S)->load_permutation
 #define SLP_TREE_TWO_OPERATORS(S)               (S)->two_operators
+#define SLP_TREE_DEF_TYPE(S)                    (S)->def_type