re PR tree-optimization/58246 (wrong code at -O1 and above)

2013-08-29  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/58246
	* tree-ssa-dce.c (mark_aliased_reaching_defs_necessary_1): Properly
	handle the dominance check inside a basic-block.

	* gcc.dg/torture/pr58246.c: New testcase.

From-SVN: r202071

gcc/ChangeLog

 2013-08-29  Richard Biener  <rguenther@suse.de>
 
+	PR tree-optimization/58246
+	* tree-ssa-dce.c (mark_aliased_reaching_defs_necessary_1): Properly
+	handle the dominance check inside a basic-block.
+
+2013-08-29  Richard Biener  <rguenther@suse.de>
+
 	PR middle-end/57287
 	* tree-ssa-copy.c (may_propagate_copy): Allow propagating
 	of default defs that appear in abnormal PHI nodes.

gcc/testsuite/ChangeLog

+2013-08-29  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/58246
+	* gcc.dg/torture/pr58246.c: New testcase.
+
 2013-08-29  Thomas Koenig  <tkoenig@gcc.gnu.org>
 
 	PR fortran/52243

gcc/testsuite/gcc.dg/torture/pr58246.c

+/* { dg-do run } */
+
+extern void abort (void);
+
+int a, b; 
+
+int main ()
+{
+  int t[2] = {1,1};
+
+  for (a = 0; a < 2; a++)
+    {
+      b ^= t[a];
+      t[a] = t[1] = 0;
+    }
+
+  if (b != 1)
+    abort ();
+
+  return 0;
+}

gcc/tree-ssa-dce.c

@@ -574,6 +574,11 @@ mark_aliased_reaching_defs_necessary_1 (ao_ref *ref, tree vdef, void *data)
 		      in the references (gcc.c-torture/execute/pr42142.c).
 		      The simplest way is to check if the kill dominates
 		      the use.  */
+		   /* But when both are in the same block we cannot
+		      easily tell whether we came from a backedge
+		      unless we decide to compute stmt UIDs
+		      (see PR58246).  */
+		   && (basic_block) data != gimple_bb (def_stmt)
 		   && dominated_by_p (CDI_DOMINATORS, (basic_block) data,
 				      gimple_bb (def_stmt))
 		   && operand_equal_p (ref->ref, lhs, 0))