Re: [vec-cmp, patch 3/6] Vectorize comparison

[Ilya Enkovich <enkovich dot gnu at gmail dot com>]

On 14 Oct 15:06, Ilya Enkovich wrote:
> 
> Will send an updated version after testing.
> 
> Thanks,
> Ilya
> 

Here is an updated patch version.

Thanks,
Ilya
--
gcc/

2015-10-14  Ilya Enkovich  <enkovich.gnu@gmail.com>

	* tree-vect-data-refs.c (vect_get_new_vect_var): Support vect_mask_var.
	(vect_create_destination_var): Likewise.
	* tree-vect-stmts.c (vectorizable_comparison): New.
	(vect_analyze_stmt): Add vectorizable_comparison.
	(vect_transform_stmt): Likewise.
	* tree-vectorizer.h (enum vect_var_kind): Add vect_mask_var.
	(enum stmt_vec_info_type): Add comparison_vec_info_type.
	(vectorizable_comparison): New.


diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
index 8a4d489..0be0523 100644
--- a/gcc/tree-vect-data-refs.c
+++ b/gcc/tree-vect-data-refs.c
@@ -3870,6 +3870,9 @@ vect_get_new_vect_var (tree type, enum vect_var_kind var_kind, const char *name)
   case vect_scalar_var:
     prefix = "stmp";
     break;
+  case vect_mask_var:
+    prefix = "mask";
+    break;
   case vect_pointer_var:
     prefix = "vectp";
     break;
@@ -4424,7 +4427,11 @@ vect_create_destination_var (tree scalar_dest, tree vectype)
   tree type;
   enum vect_var_kind kind;
 
-  kind = vectype ? vect_simple_var : vect_scalar_var;
+  kind = vectype
+    ? VECTOR_BOOLEAN_TYPE_P (vectype)
+    ? vect_mask_var
+    : vect_simple_var
+    : vect_scalar_var;
   type = vectype ? vectype : TREE_TYPE (scalar_dest);
 
   gcc_assert (TREE_CODE (scalar_dest) == SSA_NAME);
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 23cec8a..6a52895 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -7516,6 +7516,192 @@ vectorizable_condition (gimple *stmt, gimple_stmt_iterator *gsi,
   return true;
 }
 
+/* vectorizable_comparison.
+
+   Check if STMT is comparison expression that can be vectorized.
+   If VEC_STMT is also passed, vectorize the STMT: create a vectorized
+   comparison, put it in VEC_STMT, and insert it at GSI.
+
+   Return FALSE if not a vectorizable STMT, TRUE otherwise.  */
+
+bool
+vectorizable_comparison (gimple *stmt, gimple_stmt_iterator *gsi,
+			 gimple **vec_stmt, tree reduc_def,
+			 slp_tree slp_node)
+{
+  tree lhs, rhs1, rhs2;
+  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
+  tree vectype1 = NULL_TREE, vectype2 = NULL_TREE;
+  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
+  tree vec_rhs1 = NULL_TREE, vec_rhs2 = NULL_TREE;
+  tree vec_compare;
+  tree new_temp;
+  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
+  tree def;
+  enum vect_def_type dts[2] = {vect_unknown_def_type, vect_unknown_def_type};
+  unsigned nunits;
+  int ncopies;
+  enum tree_code code;
+  stmt_vec_info prev_stmt_info = NULL;
+  int i, j;
+  bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (stmt_info);
+  vec<tree> vec_oprnds0 = vNULL;
+  vec<tree> vec_oprnds1 = vNULL;
+  gimple *def_stmt;
+  tree mask_type;
+  tree mask;
+
+  if (!VECTOR_BOOLEAN_TYPE_P (vectype))
+    return false;
+
+  mask_type = vectype;
+  nunits = TYPE_VECTOR_SUBPARTS (vectype);
+
+  if (slp_node || PURE_SLP_STMT (stmt_info))
+    ncopies = 1;
+  else
+    ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
+
+  gcc_assert (ncopies >= 1);
+  if (!STMT_VINFO_RELEVANT_P (stmt_info) && !bb_vinfo)
+    return false;
+
+  if (STMT_VINFO_DEF_TYPE (stmt_info) != vect_internal_def
+      && !(STMT_VINFO_DEF_TYPE (stmt_info) == vect_nested_cycle
+	   && reduc_def))
+    return false;
+
+  if (STMT_VINFO_LIVE_P (stmt_info))
+    {
+      if (dump_enabled_p ())
+	dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
+			 "value used after loop.\n");
+      return false;
+    }
+
+  if (!is_gimple_assign (stmt))
+    return false;
+
+  code = gimple_assign_rhs_code (stmt);
+
+  if (TREE_CODE_CLASS (code) != tcc_comparison)
+    return false;
+
+  rhs1 = gimple_assign_rhs1 (stmt);
+  rhs2 = gimple_assign_rhs2 (stmt);
+
+  if (!vect_is_simple_use_1 (rhs1, stmt, stmt_info->vinfo,
+			     &def_stmt, &def, &dts[0], &vectype1))
+    return false;
+
+  if (!vect_is_simple_use_1 (rhs2, stmt, stmt_info->vinfo,
+			     &def_stmt, &def, &dts[1], &vectype2))
+	return false;
+
+  if (vectype1 && vectype2
+      && TYPE_VECTOR_SUBPARTS (vectype1) != TYPE_VECTOR_SUBPARTS (vectype2))
+    return false;
+
+  vectype = vectype1 ? vectype1 : vectype2;
+
+  /* Invariant comparison.  */
+  if (!vectype)
+    {
+      vectype = build_vector_type (TREE_TYPE (rhs1), nunits);
+      if (tree_to_shwi (TYPE_SIZE_UNIT (vectype)) != current_vector_size)
+	return false;
+    }
+  else if (nunits != TYPE_VECTOR_SUBPARTS (vectype))
+    return false;
+
+  if (!vec_stmt)
+    {
+      STMT_VINFO_TYPE (stmt_info) = comparison_vec_info_type;
+      vect_model_simple_cost (stmt_info, ncopies, dts, NULL, NULL);
+      return expand_vec_cmp_expr_p (vectype, mask_type);
+    }
+
+  /* Transform.  */
+  if (!slp_node)
+    {
+      vec_oprnds0.create (1);
+      vec_oprnds1.create (1);
+    }
+
+  /* Handle def.  */
+  lhs = gimple_assign_lhs (stmt);
+  mask = vect_create_destination_var (lhs, mask_type);
+
+  /* Handle cmp expr.  */
+  for (j = 0; j < ncopies; j++)
+    {
+      gassign *new_stmt = NULL;
+      if (j == 0)
+	{
+	  if (slp_node)
+	    {
+	      auto_vec<tree, 2> ops;
+	      auto_vec<vec<tree>, 2> vec_defs;
+
+	      ops.safe_push (rhs1);
+	      ops.safe_push (rhs2);
+	      vect_get_slp_defs (ops, slp_node, &vec_defs, -1);
+	      vec_oprnds1 = vec_defs.pop ();
+	      vec_oprnds0 = vec_defs.pop ();
+
+	      ops.release ();
+	      vec_defs.release ();
+	    }
+	  else
+	    {
+	      vec_rhs1 = vect_get_vec_def_for_operand (rhs1, stmt, NULL);
+	      vec_rhs2 = vect_get_vec_def_for_operand (rhs2, stmt, NULL);
+	    }
+	}
+      else
+	{
+	  vec_rhs1 = vect_get_vec_def_for_stmt_copy (dts[0],
+						     vec_oprnds0.pop ());
+	  vec_rhs2 = vect_get_vec_def_for_stmt_copy (dts[1],
+						     vec_oprnds1.pop ());
+	}
+
+      if (!slp_node)
+	{
+	  vec_oprnds0.quick_push (vec_rhs1);
+	  vec_oprnds1.quick_push (vec_rhs2);
+	}
+
+      /* Arguments are ready.  Create the new vector stmt.  */
+      FOR_EACH_VEC_ELT (vec_oprnds0, i, vec_rhs1)
+	{
+	  vec_rhs2 = vec_oprnds1[i];
+
+	  vec_compare = build2 (code, mask_type, vec_rhs1, vec_rhs2);
+	  new_stmt = gimple_build_assign (mask, vec_compare);
+	  new_temp = make_ssa_name (mask, new_stmt);
+	  gimple_assign_set_lhs (new_stmt, new_temp);
+	  vect_finish_stmt_generation (stmt, new_stmt, gsi);
+	  if (slp_node)
+	    SLP_TREE_VEC_STMTS (slp_node).quick_push (new_stmt);
+	}
+
+      if (slp_node)
+	continue;
+
+      if (j == 0)
+	STMT_VINFO_VEC_STMT (stmt_info) = *vec_stmt = new_stmt;
+      else
+	STMT_VINFO_RELATED_STMT (prev_stmt_info) = new_stmt;
+
+      prev_stmt_info = vinfo_for_stmt (new_stmt);
+    }
+
+  vec_oprnds0.release ();
+  vec_oprnds1.release ();
+
+  return true;
+}
 
 /* Make sure the statement is vectorizable.  */
 
@@ -7719,7 +7905,8 @@ vect_analyze_stmt (gimple *stmt, bool *need_to_vectorize, slp_tree node)
 	  || vectorizable_call (stmt, NULL, NULL, node)
 	  || vectorizable_store (stmt, NULL, NULL, node)
 	  || vectorizable_reduction (stmt, NULL, NULL, node)
-	  || vectorizable_condition (stmt, NULL, NULL, NULL, 0, node));
+	  || vectorizable_condition (stmt, NULL, NULL, NULL, 0, node)
+	  || vectorizable_comparison (stmt, NULL, NULL, NULL, node));
   else
     {
       if (bb_vinfo)
@@ -7731,7 +7918,8 @@ vect_analyze_stmt (gimple *stmt, bool *need_to_vectorize, slp_tree node)
 	      || vectorizable_load (stmt, NULL, NULL, node, NULL)
 	      || vectorizable_call (stmt, NULL, NULL, node)
 	      || vectorizable_store (stmt, NULL, NULL, node)
-	      || vectorizable_condition (stmt, NULL, NULL, NULL, 0, node));
+	      || vectorizable_condition (stmt, NULL, NULL, NULL, 0, node)
+	      || vectorizable_comparison (stmt, NULL, NULL, NULL, node));
     }
 
   if (!ok)
@@ -7847,6 +8035,11 @@ vect_transform_stmt (gimple *stmt, gimple_stmt_iterator *gsi,
       gcc_assert (done);
       break;
 
+    case comparison_vec_info_type:
+      done = vectorizable_comparison (stmt, gsi, &vec_stmt, NULL, slp_node);
+      gcc_assert (done);
+      break;
+
     case call_vec_info_type:
       done = vectorizable_call (stmt, gsi, &vec_stmt, slp_node);
       stmt = gsi_stmt (*gsi);
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 5b766cf..f8d1e97 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -28,7 +28,8 @@ along with GCC; see the file COPYING3.  If not see
 enum vect_var_kind {
   vect_simple_var,
   vect_pointer_var,
-  vect_scalar_var
+  vect_scalar_var,
+  vect_mask_var
 };
 
 /* Defines type of operation.  */
@@ -441,6 +442,7 @@ enum stmt_vec_info_type {
   call_simd_clone_vec_info_type,
   assignment_vec_info_type,
   condition_vec_info_type,
+  comparison_vec_info_type,
   reduc_vec_info_type,
   induc_vec_info_type,
   type_promotion_vec_info_type,
@@ -1002,6 +1004,8 @@ extern void vect_remove_stores (gimple *);
 extern bool vect_analyze_stmt (gimple *, bool *, slp_tree);
 extern bool vectorizable_condition (gimple *, gimple_stmt_iterator *,
 				    gimple **, tree, int, slp_tree);
+extern bool vectorizable_comparison (gimple *, gimple_stmt_iterator *,
+				     gimple **, tree, int, slp_tree);
 extern void vect_get_load_cost (struct data_reference *, int, bool,
 				unsigned int *, unsigned int *,
 				stmt_vector_for_cost *,