Patchwork [tree-optimization] : Improve handling of conditional-branches on targets with high branch costs

login
register
mail settings
Submitter Kai Tietz
Date Oct. 10, 2011, 11:56 a.m.
Message ID <CAEwic4Y9eaa+EUtuMwCmXg7m0fA9=2kAZx7dkK0rKN93Y-UGQg@mail.gmail.com>
Download mbox | patch
Permalink /patch/118722/
State New
Headers show

Comments

Kai Tietz - Oct. 10, 2011, 11:56 a.m.
2011/10/10 Richard Guenther <richard.guenther@gmail.com>:
> On Fri, Oct 7, 2011 at 11:36 PM, Kai Tietz <ktietz70@googlemail.com> wrote:
>> Hello,
>>
>> this is the updated version with the suggestion
>>
>> 2011/10/7 Richard Guenther <richard.guenther@gmail.com>:
>>> On Thu, Oct 6, 2011 at 4:25 PM, Kai Tietz <ktietz@redhat.com> wrote:
>>>> +      && ((TREE_CODE_CLASS (TREE_CODE (arg1)) != tcc_comparison
>>>> +           && TREE_CODE (arg1) != TRUTH_NOT_EXPR
>>>> +           && simple_operand_p (arg1))
>>>
>>> As I said previously simple_operand_p already rejects covers
>>> comparisons and TRUTH_NOT_EXPR.  Also arg1 had better
>>> TREE_SIDE_EFFECTS set if the comparison might trap, as
>>> it might just be hidden in something more complicated - so
>>> the simple check isn't enough anyway (and if simple_operand_p
>>> would cover it, the check would be better placed there).
>>
>> I reworked simple_operand_p so that it does this special-casing and additionally
>> also checks for trapping.
>>
>>>> +      if (TREE_CODE (arg0) == code
>>>> +          && !TREE_SIDE_EFFECTS (TREE_OPERAND (arg0, 1))
>>>> +          && simple_operand_p (TREE_OPERAND (arg0, 1)))
>>>> +       {
>>>> +         tem = build2_loc (loc,
>>>> +                           (code == TRUTH_ANDIF_EXPR ? TRUTH_AND_EXPR
>>>> +                                                     : TRUTH_OR_EXPR),
>>>> +                           type, TREE_OPERAND (arg0, 1), arg1);
>>>> +         return build2_loc (loc, code, type, TREE_OPERAND (arg0, 0),
>>>> +                            tem);
>>>
>>> All trees should be folded, don't use plain build without a good reason.
>>
>> Ok, done
>>
>>>> +       }
>>>> +      /* Convert X TRUTH-ANDORIF Y to X TRUTH-ANDOR Y, if X and Y
>>>> +        are simple operands and have no side-effects.  */
>>>> +      if (simple_operand_p (arg0)
>>>> +          && !TREE_SIDE_EFFECTS (arg0))
>>>
>>> Again, the checks you do for arg0 do not match those for arg1.  OTOH
>>> it doesn't matter whether arg0 is simple or not or has side-effects or
>>> not for this transformation, so why check it at all?
>>
>> It is required.  For left-hand operand, if it isn't a logical
>> and/or/xor, we need to check for side-effects (and for trapping).  I
>> see that calling of simple_operand_p is wrong here, as it rejects too
>> much.  Nevertheless the check for side-effects is necessary for having
>> valid sequence-points.  Without that checking a simple test
>>
>> int getter (void);
>>
>> int foo (void)
>> {
>>  int c, r = 0;
>>  while ((c = getter ()) != '"' && c >= 0)
>>    r +=c;
>>  return r;
>> }
>>
>> would give a warning about sequence-points.  As left-hand operand has
>> side-effects, but right-hand not.  If we would combine it as AND, the
>> operands are exchange-able.  So right-hand operand needs to be another
>> ANDIF expression instead.
>> Same apply on trapping.
>>
>>> In fold_truthop we still have the same (albeit more restricted transform),
>>> but guarded with
>>>
>>>  if (BRANCH_COST (optimize_function_for_speed_p (cfun),
>>>                   false) >= 2
>>>
>>> too.  Why not here?  Please delete redundant code in fold_truthop.
>> Well, in general this is the default definition of
>> LOGICAL_OP_NON_SHORT_CIRCUIT, so I missed that.  As for some targets
>> the macro LOGICAL_OP_NON_SHORT_CIRCUIT might be defined differently,
>> it might make sense to check for BRANCH_COST again.
>>
>>> It's also odd that this is only called from fold_truth_andor but has
>>> a more generic name, so maybe rename it to fold_truth_andor_1 on the way.
>>
>> I renamed it.
>>
>>> Richard.
>>
>> ChangeLog
>>
>> 2011-10-07  Kai Tietz  <ktietz@redhat.com>
>>
>>        * fold-const.c (simple_operand_p): Make argument non-const
>>        and add floating-point trapping check, and special cases for
>>        comparisons, and logical-not's.
>>        (fold_truthop): Rename to
>>        (fold_truth_andor_1): function name.
>>        Additionally remove here TRUTH-AND|OR_EXPR generation.
>>        (fold_truth_andor): Handle branching at one place.
>>
>> Bootstrapped and regression-tested for all languages plus Ada and
>> Obj-C++ on x86_64-pc-linux-gnu.
>> Ok for apply?
>>
>> Regards,
>> Kai
>>
>> Index: gcc/gcc/fold-const.c
>> ===================================================================
>> --- gcc.orig/gcc/fold-const.c
>> +++ gcc/gcc/fold-const.c
>> @@ -111,14 +111,13 @@ static tree decode_field_reference (loca
>>                                    tree *, tree *);
>>  static int all_ones_mask_p (const_tree, int);
>>  static tree sign_bit_p (tree, const_tree);
>> -static int simple_operand_p (const_tree);
>> +static int simple_operand_p (tree);
>>  static tree range_binop (enum tree_code, tree, tree, int, tree, int);
>>  static tree range_predecessor (tree);
>>  static tree range_successor (tree);
>>  static tree fold_range_test (location_t, enum tree_code, tree, tree, tree);
>>  static tree fold_cond_expr_with_comparison (location_t, tree, tree,
>> tree, tree);
>>  static tree unextend (tree, int, int, tree);
>> -static tree fold_truthop (location_t, enum tree_code, tree, tree, tree);
>>  static tree optimize_minmax_comparison (location_t, enum tree_code,
>>                                        tree, tree, tree);
>>  static tree extract_muldiv (tree, tree, enum tree_code, tree, bool *);
>> @@ -3500,7 +3499,7 @@ optimize_bit_field_compare (location_t l
>>   return lhs;
>>  }
>>
>> -/* Subroutine for fold_truthop: decode a field reference.
>> +/* Subroutine for fold_truth_andor_1: decode a field reference.
>>
>>    If EXP is a comparison reference, we return the innermost reference.
>>
>> @@ -3668,17 +3667,43 @@ sign_bit_p (tree exp, const_tree val)
>>   return NULL_TREE;
>>  }
>>
>> -/* Subroutine for fold_truthop: determine if an operand is simple enough
>> +/* Subroutine for fold_truth_andor_1: determine if an operand is simple enough
>>    to be evaluated unconditionally.  */
>>
>>  static int
>> -simple_operand_p (const_tree exp)
>> +simple_operand_p (tree exp)
>>  {
>> +  enum tree_code code;
>>   /* Strip any conversions that don't change the machine mode.  */
>>   STRIP_NOPS (exp);
>>
>> +  code = TREE_CODE (exp);
>> +
>> +  /* Handle some trivials  $$$$ */
>> +  if (TREE_CODE_CLASS (code) == tcc_comparison)
>> +    return (tree_could_trap_p (exp)
>> +           && simple_operand_p (TREE_OPERAND (exp, 0))
>> +           && simple_operand_p (TREE_OPERAND (exp, 1)));
>
> Clearly wrong.  And what's $$$$ supposed to be?
The $$$$ was a marker.  Will remove here from patch

>> +
>> +  if (FLOAT_TYPE_P (TREE_TYPE (exp))
>> +      && tree_could_trap_p (exp))
>> +    return false;
>> +
>> +  switch (code)
>> +    {
>> +    case SSA_NAME:
>> +      return true;
>> +    case TRUTH_NOT_EXPR:
>> +      return simple_operand_p (TREE_OPERAND (exp, 0));
>> +    case BIT_NOT_EXPR:
>> +      if (TREE_CODE (TREE_TYPE (exp)) != BOOLEAN_TYPE)
>> +        return false;
>> +      return simple_operand_p (TREE_OPERAND (exp, 0));
>> +    default:
>> +      break;
>> +    }
>> +
>
> You add a lot of cases here without a good reason.  Why in this patch?
> Simply removing the tcc_comparison checks would have been enough ...

We should treat comparisons and truth-not expressions as simple to
allow folding on them.   But the more important point for this here
is, that we need to see if we might have floating-point trapping in
such comparisons.  Also for high branching costs we want to evaluate
two expressions together.  If we don't allow comparisons and truth-not
here, we would always end-up for such with a sequences of (AND|OR)IF
expressions for no good reason.

>>   return (CONSTANT_CLASS_P (exp)
>> -         || TREE_CODE (exp) == SSA_NAME
>>          || (DECL_P (exp)
>>              && ! TREE_ADDRESSABLE (exp)
>>              && ! TREE_THIS_VOLATILE (exp)
>> @@ -4888,7 +4913,7 @@ fold_range_test (location_t loc, enum tr
>>   return 0;
>>  }
>>
>> -/* Subroutine for fold_truthop: C is an INTEGER_CST interpreted as a P
>> +/* Subroutine for fold_truth_andor_1: C is an INTEGER_CST interpreted as a P
>
> fold_truth_andor
>
>>    bit value.  Arrange things so the extra bits will be set to zero if and
>>    only if C is signed-extended to its full width.  If MASK is nonzero,
>>    it is an INTEGER_CST that should be AND'ed with the extra bits.  */
>> @@ -5025,8 +5050,8 @@ merge_truthop_with_opposite_arm (locatio
>>    We return the simplified tree or 0 if no optimization is possible.  */
>>
>>  static tree
>> -fold_truthop (location_t loc, enum tree_code code, tree truth_type,
>> -             tree lhs, tree rhs)
>> +fold_truth_andor_1 (location_t loc, enum tree_code code, tree truth_type,
>> +                   tree lhs, tree rhs)
>>  {
>>   /* If this is the "or" of two comparisons, we can do something if
>>      the comparisons are NE_EXPR.  If this is the "and", we can do something
>> @@ -5054,8 +5079,6 @@ fold_truthop (location_t loc, enum tree_
>>   tree lntype, rntype, result;
>>   HOST_WIDE_INT first_bit, end_bit;
>>   int volatilep;
>> -  tree orig_lhs = lhs, orig_rhs = rhs;
>> -  enum tree_code orig_code = code;
>>
>>   /* Start by getting the comparison codes.  Fail if anything is volatile.
>>      If one operand is a BIT_AND_EXPR with the constant one, treat it as if
>> @@ -5119,8 +5142,7 @@ fold_truthop (location_t loc, enum tree_
>>   /* If the RHS can be evaluated unconditionally and its operands are
>>      simple, it wins to evaluate the RHS unconditionally on machines
>>      with expensive branches.  In this case, this isn't a comparison
>> -     that can be merged.  Avoid doing this if the RHS is a floating-point
>> -     comparison since those can trap.  */
>> +     that can be merged.  */
>>
>>   if (BRANCH_COST (optimize_function_for_speed_p (cfun),
>>                   false) >= 2
>> @@ -5149,13 +5171,6 @@ fold_truthop (location_t loc, enum tree_
>>                           build2 (BIT_IOR_EXPR, TREE_TYPE (ll_arg),
>>                                   ll_arg, rl_arg),
>>                           build_int_cst (TREE_TYPE (ll_arg), 0));
>> -
>> -      if (LOGICAL_OP_NON_SHORT_CIRCUIT)
>> -       {
>> -         if (code != orig_code || lhs != orig_lhs || rhs != orig_rhs)
>> -           return build2_loc (loc, code, truth_type, lhs, rhs);
>> -         return NULL_TREE;
>> -       }
>>     }
>>
>>   /* See if the comparisons can be merged.  Then get all the parameters for
>> @@ -8380,13 +8395,52 @@ fold_truth_andor (location_t loc, enum t
>>      lhs is another similar operation, try to merge its rhs with our
>>      rhs.  Then try to merge our lhs and rhs.  */
>>   if (TREE_CODE (arg0) == code
>> -      && 0 != (tem = fold_truthop (loc, code, type,
>> -                                  TREE_OPERAND (arg0, 1), arg1)))
>> +      && 0 != (tem = fold_truth_andor_1 (loc, code, type,
>> +                                        TREE_OPERAND (arg0, 1), arg1)))
>>     return fold_build2_loc (loc, code, type, TREE_OPERAND (arg0, 0), tem);
>>
>> -  if ((tem = fold_truthop (loc, code, type, arg0, arg1)) != 0)
>> +  if ((tem = fold_truth_andor_1 (loc, code, type, arg0, arg1)) != 0)
>>     return tem;
>>
>> +  if ((code == TRUTH_ANDIF_EXPR || code == TRUTH_ORIF_EXPR)
>> +      && (BRANCH_COST (optimize_function_for_speed_p (cfun),
>> +                      false) >= 2)
>> +      && !TREE_SIDE_EFFECTS (arg1)
>> +      && LOGICAL_OP_NON_SHORT_CIRCUIT
>> +      && simple_operand_p (arg1))
>> +    {
>> +      enum tree_code ncode = (code == TRUTH_ANDIF_EXPR ? TRUTH_AND_EXPR
>> +                                                      : TRUTH_OR_EXPR);
>> +
>> +      /* We don't want to pack more then two non-IF branches
>> +         together.  Therefore we need to check, if rhs isn't
>> +         already an TRUTH_(XOR|OR|AND)[IF]_EXPR.  */
>
> which means, just check if (simple_operand_p (arg0)) ...
>
>> +      if (TREE_CODE (arg0) == code
>> +         && TREE_CODE (TREE_OPERAND (arg0, 1)) != TRUTH_AND_EXPR
>> +         && TREE_CODE (TREE_OPERAND (arg0, 1)) != TRUTH_OR_EXPR
>> +         && TREE_CODE (TREE_OPERAND (arg0, 1)) != TRUTH_XOR_EXPR
>> +         && TREE_CODE (TREE_OPERAND (arg0, 1)) != TRUTH_ANDIF_EXPR
>> +         && TREE_CODE (TREE_OPERAND (arg0, 1)) != TRUTH_ORIF_EXPR
>> +         /* Needed for sequence points and trappings, or side-effects.  */
>> +         && !TREE_SIDE_EFFECTS (TREE_OPERAND (arg0, 1))
>> +         && !tree_could_trap_p (TREE_OPERAND (arg0, 1)))
>> +       {
>> +         tem = fold_build2_loc (loc, ncode, type, TREE_OPERAND (arg0, 1),
>> +                               arg1);
>> +         return fold_build2_loc (loc, code, type, TREE_OPERAND (arg0, 0),
>> +                                tem);
>
> Don't do this association here.  Why should it not be applied to
> (a TRUTH_ANDIF_EXPR b) TRUTH_AND_EXPR c?
Again, this would destroy sequence.  As associative law might be used.
 It might be that a, or b have side-effects and changing value of c.
So we have here the same reason.

> Thus, if you
> want to associate the above if b and c do not have side-effects then
> do so generally, not only when you are converting a TRUTH_ANDIF_EXPR
> to TRUTH_AND_EXPR.
There is no need to change an TRUTH_AND_EXPR to an TRUTH_AND_EXPR
here. So this case is not of much interest and would just be costy.

> Thus, please remove this association code.
>
>> +       }
>> +     else if (TREE_CODE (arg0) != TRUTH_AND_EXPR
>> +             && TREE_CODE (arg0) != TRUTH_OR_EXPR
>> +             && TREE_CODE (arg0) != TRUTH_ANDIF_EXPR
>> +             && TREE_CODE (arg0) != TRUTH_ORIF_EXPR
>> +             && TREE_CODE (arg0) != TRUTH_XOR_EXPR
>> +             /* Needed for sequence points and trappings, or side-effects.  */
>> +             && !TREE_SIDE_EFFECTS (arg0)
>> +             && !tree_could_trap_p (arg0))
>
> See above.

Yes. see above.

> You made the patch more complex when I asked for a simpler one.

Updated patch attached with checking for right-hand operand with same
properties as for left-hand operand .

Regards,
Kai

 static tree extract_muldiv (tree, tree, enum tree_code, tree, bool *);
@@ -3500,7 +3499,7 @@ optimize_bit_field_compare (location_t l
   return lhs;
 }
 
-/* Subroutine for fold_truthop: decode a field reference.
+/* Subroutine for fold_truth_andor_1: decode a field reference.

    If EXP is a comparison reference, we return the innermost reference.

@@ -3668,17 +3667,43 @@ sign_bit_p (tree exp, const_tree val)
   return NULL_TREE;
 }

-/* Subroutine for fold_truthop: determine if an operand is simple enough
+/* Subroutine for fold_truth_andor_1: determine if an operand is simple enough
    to be evaluated unconditionally.  */

 static int
-simple_operand_p (const_tree exp)
+simple_operand_p (tree exp)
 {
+  enum tree_code code;
   /* Strip any conversions that don't change the machine mode.  */
   STRIP_NOPS (exp);

+  code = TREE_CODE (exp);
+
+  /* Handle some trivials   */
+  if (TREE_CODE_CLASS (code) == tcc_comparison)
+    return (tree_could_trap_p (exp)
+    	    && simple_operand_p (TREE_OPERAND (exp, 0))
+	    && simple_operand_p (TREE_OPERAND (exp, 1)));
+
+  if (FLOAT_TYPE_P (TREE_TYPE (exp))
+      && tree_could_trap_p (exp))
+    return false;
+
+  switch (code)
+    {
+    case SSA_NAME:
+      return true;
+    case TRUTH_NOT_EXPR:
+      return simple_operand_p (TREE_OPERAND (exp, 0));
+    case BIT_NOT_EXPR:
+      if (TREE_CODE (TREE_TYPE (exp)) != BOOLEAN_TYPE)
+        return false;
+      return simple_operand_p (TREE_OPERAND (exp, 0));
+    default:
+      break;
+    }
+
   return (CONSTANT_CLASS_P (exp)
-	  || TREE_CODE (exp) == SSA_NAME
 	  || (DECL_P (exp)
 	      && ! TREE_ADDRESSABLE (exp)
 	      && ! TREE_THIS_VOLATILE (exp)
@@ -4888,7 +4913,7 @@ fold_range_test (location_t loc, enum tr
   return 0;
 }
 
-/* Subroutine for fold_truthop: C is an INTEGER_CST interpreted as a P
+/* Subroutine for fold_truth_andor_1: C is an INTEGER_CST interpreted as a P
    bit value.  Arrange things so the extra bits will be set to zero if and
    only if C is signed-extended to its full width.  If MASK is nonzero,
    it is an INTEGER_CST that should be AND'ed with the extra bits.  */
@@ -5025,8 +5050,8 @@ merge_truthop_with_opposite_arm (locatio
    We return the simplified tree or 0 if no optimization is possible.  */

 static tree
-fold_truthop (location_t loc, enum tree_code code, tree truth_type,
-	      tree lhs, tree rhs)
+fold_truth_andor_1 (location_t loc, enum tree_code code, tree truth_type,
+		    tree lhs, tree rhs)
 {
   /* If this is the "or" of two comparisons, we can do something if
      the comparisons are NE_EXPR.  If this is the "and", we can do something
@@ -5054,8 +5079,6 @@ fold_truthop (location_t loc, enum tree_
   tree lntype, rntype, result;
   HOST_WIDE_INT first_bit, end_bit;
   int volatilep;
-  tree orig_lhs = lhs, orig_rhs = rhs;
-  enum tree_code orig_code = code;

   /* Start by getting the comparison codes.  Fail if anything is volatile.
      If one operand is a BIT_AND_EXPR with the constant one, treat it as if
@@ -5119,8 +5142,7 @@ fold_truthop (location_t loc, enum tree_
   /* If the RHS can be evaluated unconditionally and its operands are
      simple, it wins to evaluate the RHS unconditionally on machines
      with expensive branches.  In this case, this isn't a comparison
-     that can be merged.  Avoid doing this if the RHS is a floating-point
-     comparison since those can trap.  */
+     that can be merged.  */

   if (BRANCH_COST (optimize_function_for_speed_p (cfun),
 		   false) >= 2
@@ -5149,13 +5171,6 @@ fold_truthop (location_t loc, enum tree_
 			   build2 (BIT_IOR_EXPR, TREE_TYPE (ll_arg),
 				   ll_arg, rl_arg),
 			   build_int_cst (TREE_TYPE (ll_arg), 0));
-
-      if (LOGICAL_OP_NON_SHORT_CIRCUIT)
-	{
-	  if (code != orig_code || lhs != orig_lhs || rhs != orig_rhs)
-	    return build2_loc (loc, code, truth_type, lhs, rhs);
-	  return NULL_TREE;
-	}
     }

   /* See if the comparisons can be merged.  Then get all the parameters for
@@ -8380,13 +8395,47 @@ fold_truth_andor (location_t loc, enum t
      lhs is another similar operation, try to merge its rhs with our
      rhs.  Then try to merge our lhs and rhs.  */
   if (TREE_CODE (arg0) == code
-      && 0 != (tem = fold_truthop (loc, code, type,
-				   TREE_OPERAND (arg0, 1), arg1)))
+      && 0 != (tem = fold_truth_andor_1 (loc, code, type,
+					 TREE_OPERAND (arg0, 1), arg1)))
     return fold_build2_loc (loc, code, type, TREE_OPERAND (arg0, 0), tem);

-  if ((tem = fold_truthop (loc, code, type, arg0, arg1)) != 0)
+  if ((tem = fold_truth_andor_1 (loc, code, type, arg0, arg1)) != 0)
     return tem;

+  if ((code == TRUTH_ANDIF_EXPR || code == TRUTH_ORIF_EXPR)
+      && (BRANCH_COST (optimize_function_for_speed_p (cfun),
+		       false) >= 2)
+      && !TREE_SIDE_EFFECTS (arg1)
+      && LOGICAL_OP_NON_SHORT_CIRCUIT
+      && simple_operand_p (arg1))
+    {
+      enum tree_code ncode = (code == TRUTH_ANDIF_EXPR ? TRUTH_AND_EXPR
+						       : TRUTH_OR_EXPR);
+
+      /* We don't want to pack more then two leafs to an non-IF
+         If tree-code of left-hand operand isn't an AND/OR-IF code,
+         then we don't want to add right-hand operand.
+         If the inner right-hand side of left-hand operand has side-effects,
+         or isn't simple, then we can't add to it, as otherwise we might
+         destroy if-sequence.  */
+      if ((TREE_CODE (arg0) == TRUTH_ANDIF_EXPR
+           || TREE_CODE (arg0) == TRUTH_ORIF_EXPR)
+      	  /* Needed for sequence points to handle trappings, and
+      	     side-effects.  */
+      	  && !TREE_SIDE_EFFECTS (TREE_OPERAND (arg0, 1))
+      	  && simple_operand_p (TREE_OPERAND (arg0, 1)))
+       {
+         tem = fold_build2_loc (loc, ncode, type, TREE_OPERAND (arg0, 1),
+				arg1);
+         return fold_build2_loc (loc, code, type, TREE_OPERAND (arg0, 0),
+				 tem);
+       }
+     /* Needed for sequence points to handle trappings, and side-effects.  */
+     else if (!TREE_SIDE_EFFECTS (arg0)
+	      && simple_operand_p (arg0))
+       return fold_build2_loc (loc, ncode, type, arg0, arg1);
+    }
+
   return NULL_TREE;
 }

Patch

Index: gcc/gcc/fold-const.c
===================================================================
--- gcc.orig/gcc/fold-const.c
+++ gcc/gcc/fold-const.c
@@ -111,14 +111,13 @@  static tree decode_field_reference (loca
 				    tree *, tree *);
 static int all_ones_mask_p (const_tree, int);
 static tree sign_bit_p (tree, const_tree);
-static int simple_operand_p (const_tree);
+static int simple_operand_p (tree);
 static tree range_binop (enum tree_code, tree, tree, int, tree, int);
 static tree range_predecessor (tree);
 static tree range_successor (tree);
 static tree fold_range_test (location_t, enum tree_code, tree, tree, tree);
 static tree fold_cond_expr_with_comparison (location_t, tree, tree,
tree, tree);
 static tree unextend (tree, int, int, tree);
-static tree fold_truthop (location_t, enum tree_code, tree, tree, tree);
 static tree optimize_minmax_comparison (location_t, enum tree_code,
 					tree, tree, tree);