2012-03-27 Richard Guenther <rguenther@suse.de>

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

diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index e854da5..edfe98d 100644 (file)
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -811,6 +811,46 @@ vect_model_simple_cost (stmt_vec_info stmt_info, int ncopies,
 }
 
 
+/* Model cost for type demotion and promotion operations.  PWR is normally
+   zero for single-step promotions and demotions.  It will be one if 
+   two-step promotion/demotion is required, and so on.  Each additional
+   step doubles the number of instructions required.  */
+
+static void
+vect_model_promotion_demotion_cost (stmt_vec_info stmt_info,
+                                   enum vect_def_type *dt, int pwr)
+{
+  int i, tmp;
+  int inside_cost = 0, outside_cost = 0, single_stmt_cost;
+
+  /* The SLP costs were already calculated during SLP tree build.  */
+  if (PURE_SLP_STMT (stmt_info))
+    return;
+
+  single_stmt_cost = vect_get_stmt_cost (vec_promote_demote);
+  for (i = 0; i < pwr + 1; i++)
+    {
+      tmp = (STMT_VINFO_TYPE (stmt_info) == type_promotion_vec_info_type) ?
+       (i + 1) : i;
+      inside_cost += vect_pow2 (tmp) * single_stmt_cost;
+    }
+
+  /* FORNOW: Assuming maximum 2 args per stmts.  */
+  for (i = 0; i < 2; i++)
+    {
+      if (dt[i] == vect_constant_def || dt[i] == vect_external_def)
+        outside_cost += vect_get_stmt_cost (vector_stmt);
+    }
+
+  if (vect_print_dump_info (REPORT_COST))
+    fprintf (vect_dump, "vect_model_promotion_demotion_cost: inside_cost = %d, "
+             "outside_cost = %d .", inside_cost, outside_cost);
+
+  /* Set the costs in STMT_INFO.  */
+  stmt_vinfo_set_inside_of_loop_cost (stmt_info, NULL, inside_cost);
+  stmt_vinfo_set_outside_of_loop_cost (stmt_info, NULL, outside_cost);
+}
+
 /* Function vect_cost_strided_group_size
 
    For strided load or store, return the group_size only if it is the first
@@ -887,7 +927,6 @@ vect_model_store_cost (stmt_vec_info stmt_info, int ncopies,
       if (vect_print_dump_info (REPORT_COST))
         fprintf (vect_dump, "vect_model_store_cost: strided group_size = %d .",
                  group_size);
-
     }
 
   /* Costs of the stores.  */
@@ -1049,7 +1088,7 @@ vect_get_load_cost (struct data_reference *dr, int ncopies,
     case dr_explicit_realign:
       {
         *inside_cost += ncopies * (2 * vect_get_stmt_cost (vector_load)
-           + vect_get_stmt_cost (vector_stmt));
+                                  + vect_get_stmt_cost (vec_perm));
 
         /* FIXME: If the misalignment remains fixed across the iterations of
            the containing loop, the following cost should be added to the
@@ -1057,6 +1096,9 @@ vect_get_load_cost (struct data_reference *dr, int ncopies,
         if (targetm.vectorize.builtin_mask_for_load)
           *inside_cost += vect_get_stmt_cost (vector_stmt);
 
+        if (vect_print_dump_info (REPORT_COST))
+          fprintf (vect_dump, "vect_model_load_cost: explicit realign");
+
         break;
       }
     case dr_explicit_realign_optimized:
@@ -1080,7 +1122,12 @@ vect_get_load_cost (struct data_reference *dr, int ncopies,
           }
 
         *inside_cost += ncopies * (vect_get_stmt_cost (vector_load)
-          + vect_get_stmt_cost (vector_stmt));
+                                  + vect_get_stmt_cost (vec_perm));
+
+        if (vect_print_dump_info (REPORT_COST))
+          fprintf (vect_dump,
+                  "vect_model_load_cost: explicit realign optimized");
+
         break;
       }
 
@@ -2392,16 +2439,19 @@ vectorizable_conversion (gimple stmt, gimple_stmt_iterator *gsi,
       if (vect_print_dump_info (REPORT_DETAILS))
        fprintf (vect_dump, "=== vectorizable_conversion ===");
       if (code == FIX_TRUNC_EXPR || code == FLOAT_EXPR)
-       STMT_VINFO_TYPE (stmt_info) = type_conversion_vec_info_type;
+        {
+         STMT_VINFO_TYPE (stmt_info) = type_conversion_vec_info_type;
+         vect_model_simple_cost (stmt_info, ncopies, dt, NULL);
+       }
       else if (modifier == NARROW)
        {
          STMT_VINFO_TYPE (stmt_info) = type_demotion_vec_info_type;
-         vect_model_simple_cost (stmt_info, ncopies, dt, NULL);
+         vect_model_promotion_demotion_cost (stmt_info, dt, multi_step_cvt);
        }
       else
        {
          STMT_VINFO_TYPE (stmt_info) = type_promotion_vec_info_type;
-         vect_model_simple_cost (stmt_info, 2 * ncopies, dt, NULL);
+         vect_model_promotion_demotion_cost (stmt_info, dt, multi_step_cvt);
        }
       VEC_free (tree, heap, interm_types);
       return true;
@@ -3703,7 +3753,9 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
   if (!STMT_VINFO_DATA_REF (stmt_info))
     return false;
 
-  if (tree_int_cst_compare (DR_STEP (dr), size_zero_node) < 0)
+  if (tree_int_cst_compare (loop && nested_in_vect_loop_p (loop, stmt)
+                           ? STMT_VINFO_DR_STEP (stmt_info) : DR_STEP (dr),
+                           size_zero_node) < 0)
     {
       if (vect_print_dump_info (REPORT_DETAILS))
         fprintf (vect_dump, "negative step for store.");
@@ -4216,7 +4268,10 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
   if (!STMT_VINFO_DATA_REF (stmt_info))
     return false;
 
-  negative = tree_int_cst_compare (DR_STEP (dr), size_zero_node) < 0;
+  negative = tree_int_cst_compare (nested_in_vect_loop
+                                  ? STMT_VINFO_DR_STEP (stmt_info)
+                                  : DR_STEP (dr),
+                                  size_zero_node) < 0;
   if (negative && ncopies > 1)
     {
       if (vect_print_dump_info (REPORT_DETAILS))
@@ -4603,7 +4658,7 @@ vectorizable_load (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
      This can only occur when vectorizing memory accesses in the inner-loop
      nested within an outer-loop that is being vectorized.  */
 
-  if (loop && nested_in_vect_loop_p (loop, stmt)
+  if (nested_in_vect_loop
       && (TREE_INT_CST_LOW (DR_STEP (dr))
          % GET_MODE_SIZE (TYPE_MODE (vectype)) != 0))
     {