re PR tree-optimization/42108 (50% performance regression)

2014-12-11  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/42108
	* trans-stmt.c (gfc_trans_do): Execute the division computing
	countm1 before the loop entry check.

	* gfortran.dg/pr42108.f90: Amend.

From-SVN: r218630

gcc/fortran/ChangeLog

+2014-12-11  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/42108
+	* trans-stmt.c (gfc_trans_do): Execute the division computing
+	countm1 before the loop entry check.
+
 2014-12-11  Manuel López-Ibáñez  <manu@gcc.gnu.org>
 
 	PR fortran/44054

gcc/fortran/trans-stmt.c

@@ -1645,15 +1645,15 @@ gfc_trans_do (gfc_code * code, tree exit_cond)
      This code is executed before we enter the loop body. We generate:
      if (step > 0)
        {
+	 countm1 = (to - from) / step;
 	 if (to < from)
 	   goto exit_label;
-	 countm1 = (to - from) / step;
        }
      else
        {
+	 countm1 = (from - to) / -step;
 	 if (to > from)
 	   goto exit_label;
-	 countm1 = (from - to) / -step;
        }
    */
 
@@ -1675,11 +1675,12 @@ gfc_trans_do (gfc_code * code, tree exit_cond)
 			      fold_build2_loc (loc, MINUS_EXPR, utype,
 					       tou, fromu),
 			      stepu);
-      pos = fold_build3_loc (loc, COND_EXPR, void_type_node, tmp,
-			     fold_build1_loc (loc, GOTO_EXPR, void_type_node,
-					      exit_label),
+      pos = build2 (COMPOUND_EXPR, void_type_node,
 		    fold_build2 (MODIFY_EXPR, void_type_node,
-					  countm1, tmp2));
+				 countm1, tmp2),
+		    build3_loc (loc, COND_EXPR, void_type_node, tmp,
+				build1_loc (loc, GOTO_EXPR, void_type_node,
+					    exit_label), NULL_TREE));
 
       /* For a negative step, when to > from, exit, otherwise compute
          countm1 = ((unsigned)from - (unsigned)to) / -(unsigned)step  */
@@ -1688,11 +1689,12 @@ gfc_trans_do (gfc_code * code, tree exit_cond)
 			      fold_build2_loc (loc, MINUS_EXPR, utype,
 					       fromu, tou),
 			      fold_build1_loc (loc, NEGATE_EXPR, utype, stepu));
-      neg = fold_build3_loc (loc, COND_EXPR, void_type_node, tmp,
-			     fold_build1_loc (loc, GOTO_EXPR, void_type_node,
-					      exit_label),
+      neg = build2 (COMPOUND_EXPR, void_type_node,
 		    fold_build2 (MODIFY_EXPR, void_type_node,
-					  countm1, tmp2));
+				 countm1, tmp2),
+		    build3_loc (loc, COND_EXPR, void_type_node, tmp,
+				build1_loc (loc, GOTO_EXPR, void_type_node,
+					    exit_label), NULL_TREE));
 
       tmp = fold_build2_loc (loc, LT_EXPR, boolean_type_node, step,
 			     build_int_cst (TREE_TYPE (step), 0));

gcc/testsuite/ChangeLog

+2014-12-11  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/42108
+	* gfortran.dg/pr42108.f90: Amend.
+
 2014-12-11  Manuel López-Ibáñez  <manu@gcc.gnu.org>
 
         * gfortran.dg/do_iterator.f90: Remove bogus dg-warning.

gcc/testsuite/gfortran.dg/pr42108.f90

 ! { dg-do compile }
-! { dg-options "-O2 -fdump-tree-fre1" }
+! { dg-options "-O2 -fdump-tree-fre1 -fdump-tree-pre-details" }
 
 subroutine  eval(foo1,foo2,foo3,foo4,x,n,nnd)
   implicit real*8 (a-h,o-z)
@@ -21,7 +21,9 @@ subroutine  eval(foo1,foo2,foo3,foo4,x,n,nnd)
   end do
 end subroutine eval
 
+! We should have hoisted the division
+! { dg-final { scan-tree-dump "in all uses of countm1\[^\n\]* / " "pre" } }
 ! There should be only one load from n left
-
 ! { dg-final { scan-tree-dump-times "\\*n_" 1 "fre1" } }
 ! { dg-final { cleanup-tree-dump "fre1" } }
+! { dg-final { cleanup-tree-dump "pre" } }