[Vectorizer] Make REDUC_xxx_EXPR tree codes produce a scalar result

PR tree-optimization/61114
	* expr.c (expand_expr_real_2): For REDUC_{MIN,MAX,PLUS}_EXPR, add
	extract_bit_field around optab result.

	* fold-const.c (fold_unary_loc): For REDUC_{MIN,MAX,PLUS}_EXPR, produce
	scalar not vector.

	* tree-cfg.c (verify_gimple_assign_unary): Check result vs operand type
	for REDUC_{MIN,MAX,PLUS}_EXPR.

	* tree-vect-loop.c (vect_analyze_loop): Update comment.
	(vect_create_epilog_for_reduction): For direct vector reduction, use
	result of tree code directly without extract_bit_field.

	* tree.def (REDUC_MAX_EXPR, REDUC_MIN_EXPR, REDUC_PLUS_EXPR): Update
	comment.

From-SVN: r216736

gcc/ChangeLog

@@ -1,3 +1,22 @@
+2014-10-27  Alan Lawrence  <alan.lawrence@arm.com>
+
+	PR tree-optimization/61114
+	* expr.c (expand_expr_real_2): For REDUC_{MIN,MAX,PLUS}_EXPR, add
+	extract_bit_field around optab result.
+
+	* fold-const.c (fold_unary_loc): For REDUC_{MIN,MAX,PLUS}_EXPR, produce
+	scalar not vector.
+
+	* tree-cfg.c (verify_gimple_assign_unary): Check result vs operand type
+	for REDUC_{MIN,MAX,PLUS}_EXPR.
+
+	* tree-vect-loop.c (vect_analyze_loop): Update comment.
+	(vect_create_epilog_for_reduction): For direct vector reduction, use
+	result of tree code directly without extract_bit_field.
+
+	* tree.def (REDUC_MAX_EXPR, REDUC_MIN_EXPR, REDUC_PLUS_EXPR): Update
+	comment.
+
 2014-10-27  Andrew MacLeod  <amacleod@redhat.com>
 
 	* basic-block.h: Remove all includes.

gcc/expr.c

@@ -9051,7 +9051,17 @@ expand_expr_real_2 (sepops ops, rtx target, enum machine_mode tmode,
       {
         op0 = expand_normal (treeop0);
         this_optab = optab_for_tree_code (code, type, optab_default);
-        temp = expand_unop (mode, this_optab, op0, target, unsignedp);
+        enum machine_mode vec_mode = TYPE_MODE (TREE_TYPE (treeop0));
+        temp = expand_unop (vec_mode, this_optab, op0, NULL_RTX, unsignedp);
+        gcc_assert (temp);
+        /* The tree code produces a scalar result, but (somewhat by convention)
+           the optab produces a vector with the result in element 0 if
+           little-endian, or element N-1 if big-endian.  So pull the scalar
+           result out of that element.  */
+        int index = BYTES_BIG_ENDIAN ? GET_MODE_NUNITS (vec_mode) - 1 : 0;
+        int bitsize = GET_MODE_BITSIZE (GET_MODE_INNER (vec_mode));
+        temp = extract_bit_field (temp, bitsize, bitsize * index, unsignedp,
+				  target, mode, mode);
         gcc_assert (temp);
         return temp;
       }

gcc/fold-const.c

@@ -8259,12 +8259,13 @@ fold_unary_loc (location_t loc, enum tree_code code, tree type, tree op0)
     case REDUC_MAX_EXPR:
     case REDUC_PLUS_EXPR:
       {
-	unsigned int nelts = TYPE_VECTOR_SUBPARTS (type), i;
+	unsigned int nelts, i;
 	tree *elts;
 	enum tree_code subcode;
 
 	if (TREE_CODE (op0) != VECTOR_CST)
 	  return NULL_TREE;
+        nelts = TYPE_VECTOR_SUBPARTS (TREE_TYPE (op0));
 
 	elts = XALLOCAVEC (tree, nelts);
 	if (!vec_cst_ctor_to_array (op0, elts))
@@ -8283,10 +8284,9 @@ fold_unary_loc (location_t loc, enum tree_code code, tree type, tree op0)
 	    elts[0] = const_binop (subcode, elts[0], elts[i]);
 	    if (elts[0] == NULL_TREE || !CONSTANT_CLASS_P (elts[0]))
 	      return NULL_TREE;
-	    elts[i] = build_zero_cst (TREE_TYPE (type));
 	  }
 
-	return build_vector (type, elts);
+	return elts[0];
       }
 
     default:

gcc/tree-cfg.c

@@ -3553,12 +3553,21 @@ verify_gimple_assign_unary (gimple stmt)
 
         return false;
       }
-
-    case VEC_UNPACK_HI_EXPR:
-    case VEC_UNPACK_LO_EXPR:
     case REDUC_MAX_EXPR:
     case REDUC_MIN_EXPR:
     case REDUC_PLUS_EXPR:
+      if (!VECTOR_TYPE_P (rhs1_type)
+	  || !useless_type_conversion_p (lhs_type, TREE_TYPE (rhs1_type)))
+        {
+	  error ("reduction should convert from vector to element type");
+	  debug_generic_expr (lhs_type);
+	  debug_generic_expr (rhs1_type);
+	  return true;
+	}
+      return false;
+
+    case VEC_UNPACK_HI_EXPR:
+    case VEC_UNPACK_LO_EXPR:
     case VEC_UNPACK_FLOAT_HI_EXPR:
     case VEC_UNPACK_FLOAT_LO_EXPR:
       /* FIXME.  */

gcc/tree-vect-loop.c

@@ -1903,9 +1903,9 @@ vect_analyze_loop (struct loop *loop)
 
    Output:
    REDUC_CODE - the corresponding tree-code to be used to reduce the
-      vector of partial results into a single scalar result (which
-      will also reside in a vector) or ERROR_MARK if the operation is
-      a supported reduction operation, but does not have such tree-code.
+      vector of partial results into a single scalar result, or ERROR_MARK
+      if the operation is a supported reduction operation, but does not have
+      such a tree-code.
 
    Return FALSE if CODE currently cannot be vectorized as reduction.  */
 
@@ -4179,6 +4179,7 @@ vect_create_epilog_for_reduction (vec<tree> vect_defs, gimple stmt,
   if (reduc_code != ERROR_MARK && !slp_reduc)
     {
       tree tmp;
+      tree vec_elem_type;
 
       /*** Case 1:  Create:
            v_out2 = reduc_expr <v_out1>  */
@@ -4187,14 +4188,26 @@ vect_create_epilog_for_reduction (vec<tree> vect_defs, gimple stmt,
         dump_printf_loc (MSG_NOTE, vect_location,
 			 "Reduce using direct vector reduction.\n");
 
-      vec_dest = vect_create_destination_var (scalar_dest, vectype);
-      tmp = build1 (reduc_code, vectype, new_phi_result);
-      epilog_stmt = gimple_build_assign (vec_dest, tmp);
-      new_temp = make_ssa_name (vec_dest, epilog_stmt);
+      vec_elem_type = TREE_TYPE (TREE_TYPE (new_phi_result));
+      if (!useless_type_conversion_p (scalar_type, vec_elem_type))
+	{
+          tree tmp_dest =
+	      vect_create_destination_var (scalar_dest, vec_elem_type);
+	  tmp = build1 (reduc_code, vec_elem_type, new_phi_result);
+	  epilog_stmt = gimple_build_assign (tmp_dest, tmp);
+	  new_temp = make_ssa_name (tmp_dest, epilog_stmt);
+	  gimple_assign_set_lhs (epilog_stmt, new_temp);
+	  gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
+
+	  tmp = build1 (NOP_EXPR, scalar_type, new_temp);
+	}
+      else
+	tmp = build1 (reduc_code, scalar_type, new_phi_result);
+      epilog_stmt = gimple_build_assign (new_scalar_dest, tmp);
+      new_temp = make_ssa_name (new_scalar_dest, epilog_stmt);
       gimple_assign_set_lhs (epilog_stmt, new_temp);
       gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
-
-      extract_scalar_result = true;
+      scalar_results.safe_push (new_temp);
     }
   else
     {

gcc/tree.def

@@ -1161,10 +1161,9 @@ DEFTREECODE (TRANSACTION_EXPR, "transaction_expr", tcc_expression, 1)
    result (e.g. summing the elements of the vector, finding the minimum over
    the vector elements, etc).
    Operand 0 is a vector.
-   The expression returns a vector of the same type, with the first
-   element in the vector holding the result of the reduction of all elements
-   of the operand.  The content of the other elements in the returned vector
-   is undefined.  */
+   The expression returns a scalar, with type the same as the elements of the
+   vector, holding the result of the reduction of all elements of the operand.
+   */
 DEFTREECODE (REDUC_MAX_EXPR, "reduc_max_expr", tcc_unary, 1)
 DEFTREECODE (REDUC_MIN_EXPR, "reduc_min_expr", tcc_unary, 1)
 DEFTREECODE (REDUC_PLUS_EXPR, "reduc_plus_expr", tcc_unary, 1)