PR c++/54652

[pf3gnuchains/gcc-fork.git] / gcc / tree-vect-slp.c

diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index f21abb3..b74f5eb 100644 (file)
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -95,6 +95,7 @@ vect_free_slp_instance (slp_instance instance)
   vect_free_slp_tree (SLP_INSTANCE_TREE (instance));
   VEC_free (int, heap, SLP_INSTANCE_LOAD_PERMUTATION (instance));
   VEC_free (slp_tree, heap, SLP_INSTANCE_LOADS (instance));
+  free (instance);
 }
 
 
@@ -1197,7 +1198,8 @@ vect_supported_load_permutation_p (slp_instance slp_instn, int group_size,
 
   /* We checked that this case ok, so there is no need to proceed with 
      permutation tests.  */
-  if (complex_numbers == 2)
+  if (complex_numbers == 2
+      && VEC_length (slp_tree, SLP_INSTANCE_LOADS (slp_instn)) == 2)
     {
       VEC_free (slp_tree, heap, SLP_INSTANCE_LOADS (slp_instn));
       VEC_free (int, heap, SLP_INSTANCE_LOAD_PERMUTATION (slp_instn));
@@ -1566,6 +1568,9 @@ vect_analyze_slp_instance (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
           if (vect_print_dump_info (REPORT_SLP))
             fprintf (vect_dump, "Build SLP failed: unrolling required in basic"
                                " block SLP");
+         vect_free_slp_tree (node);
+         VEC_free (int, heap, load_permutation);
+         VEC_free (slp_tree, heap, loads);
           return false;
         }
 
@@ -1822,8 +1827,11 @@ new_bb_vec_info (basic_block bb)
 static void
 destroy_bb_vec_info (bb_vec_info bb_vinfo)
 {
+  VEC (slp_instance, heap) *slp_instances;
+  slp_instance instance;
   basic_block bb;
   gimple_stmt_iterator si;
+  unsigned i;
 
   if (!bb_vinfo)
     return;
@@ -1843,6 +1851,9 @@ destroy_bb_vec_info (bb_vec_info bb_vinfo)
   free_data_refs (BB_VINFO_DATAREFS (bb_vinfo));
   free_dependence_relations (BB_VINFO_DDRS (bb_vinfo));
   VEC_free (gimple, heap, BB_VINFO_STRIDED_STORES (bb_vinfo));
+  slp_instances = BB_VINFO_SLP_INSTANCES (bb_vinfo);
+  FOR_EACH_VEC_ELT (slp_instance, slp_instances, i, instance)
+    vect_free_slp_instance (instance);
   VEC_free (slp_instance, heap, BB_VINFO_SLP_INSTANCES (bb_vinfo));
   free (bb_vinfo);
   bb->aux = NULL;
@@ -2970,7 +2981,8 @@ vect_schedule_slp (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo)
 {
   VEC (slp_instance, heap) *slp_instances;
   slp_instance instance;
-  unsigned int i, vf;
+  slp_tree loads_node;
+  unsigned int i, j, vf;
   bool is_store = false;
 
   if (loop_vinfo)
@@ -2989,6 +3001,15 @@ vect_schedule_slp (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo)
       /* Schedule the tree of INSTANCE.  */
       is_store = vect_schedule_slp_instance (SLP_INSTANCE_TREE (instance),
                                              instance, vf);
+
+      /* Clear STMT_VINFO_VEC_STMT of all loads.  With shared loads
+        between SLP instances we fail to properly initialize the
+        vectorized SLP stmts and confuse different load permutations.  */
+      FOR_EACH_VEC_ELT (slp_tree, SLP_INSTANCE_LOADS (instance), j, loads_node)
+       STMT_VINFO_VEC_STMT
+         (vinfo_for_stmt
+           (VEC_index (gimple, SLP_TREE_SCALAR_STMTS (loads_node), 0))) = NULL;
+
       if (vect_print_dump_info (REPORT_VECTORIZED_LOCATIONS)
          || vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
        fprintf (vect_dump, "vectorizing stmts using SLP.");
@@ -3001,7 +3022,15 @@ vect_schedule_slp (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo)
       unsigned int j;
       gimple_stmt_iterator gsi;
 
-      vect_remove_slp_scalar_calls (root);
+      /* Remove scalar call stmts.  Do not do this for basic-block
+        vectorization as not all uses may be vectorized.
+        ???  Why should this be necessary?  DCE should be able to
+        remove the stmts itself.
+        ???  For BB vectorization we can as well remove scalar
+        stmts starting from the SLP tree root if they have no
+        uses.  */
+      if (loop_vinfo)
+       vect_remove_slp_scalar_calls (root);
 
       for (j = 0; VEC_iterate (gimple, SLP_TREE_SCALAR_STMTS (root), j, store)
                   && j < SLP_INSTANCE_GROUP_SIZE (instance); j++)