re PR tree-optimization/64365 (Predictive commoning after loop vectorization…

re PR tree-optimization/64365 (Predictive commoning after loop vectorization produces incorrect code.)

2015-01-15  Richard Biener  <rguenther@suse.de>

	PR middle-end/64365
	* tree-data-ref.c (dr_analyze_indices): Make sure that accesses
	for MEM_REF access functions with the same base can never partially
	overlap.

	* gcc.dg/torture/pr64365.c: New testcase.

From-SVN: r219634

gcc/ChangeLog

+2015-01-15  Richard Biener  <rguenther@suse.de>
+
+	PR middle-end/64365
+	* tree-data-ref.c (dr_analyze_indices): Make sure that accesses
+	for MEM_REF access functions with the same base can never partially
+	overlap.
+
 2015-01-14  Marcos Diaz <marcos.diaz@tallertechnologies.com>
 
 	* common.opt: New option -fstack-protector-explicit.

gcc/testsuite/ChangeLog

+2015-01-15  Richard Biener  <rguenther@suse.de>
+
+	PR middle-end/64365
+	* gcc.dg/torture/pr64365.c: New testcase.
+
 2015-01-14  Marcos Diaz <marcos.diaz@tallertechnologies.com>
 
 	* gcc.dg/stackprotectexplicit1.c: New test.

gcc/testsuite/gcc.dg/torture/pr64365.c

+/* { dg-do run } */
+/* { dg-require-effective-target int32plus } */
+
+extern void abort (void);
+extern int memcmp (const void * , const void *, __SIZE_TYPE__);
+
+void __attribute__((noinline,noclone))
+foo(int *in)
+{
+  int i;
+  for (i = 62; i >= 10; i--)
+    {
+      in[i - 8] -= in[i];
+      in[i - 5] += in[i] * 2;
+      in[i - 4] += in[i];
+    }
+}
+
+int main()
+{
+  int x[64];
+  int y[64] = { 0, 1, -2380134, -1065336, -1026376, 3264240, 3113534, 2328130, 3632054, 3839634, 2380136, 1065339, 1026380, 1496037, 1397286, 789976, 386408, 450984, 597112, 497464, 262008, 149184, 194768, 231519, 173984, 87753, 60712, 82042, 87502, 60014, 30050, 25550, 33570, 32386, 20464, 10675, 10868, 13329, 11794, 6892, 3988, 4564, 5148, 4228, 2284, 1568, 1848, 1943, 1472, 741, 628, 702, 714, 474, 230, 234, 238, 242, 120, 59, 60, 61, 62, 63 };
+  int i;
+
+  for (i = 0; i < 64; ++i)
+    {
+      x[i] = i;
+      __asm__ volatile ("");
+    }
+
+  foo (x);
+
+  if (memcmp (x, y, sizeof (x)) != 0)
+    abort ();
+
+  return 0;
+}

gcc/tree-data-ref.c

@@ -992,6 +992,22 @@ dr_analyze_indices (struct data_reference *dr, loop_p nest, loop_p loop)
 				fold_convert (ssizetype, memoff));
 	      memoff = build_int_cst (TREE_TYPE (memoff), 0);
 	    }
+	  /* Adjust the offset so it is a multiple of the access type
+	     size and thus we separate bases that can possibly be used
+	     to produce partial overlaps (which the access_fn machinery
+	     cannot handle).  */
+	  wide_int rem;
+	  if (TYPE_SIZE_UNIT (TREE_TYPE (ref))
+	      && TREE_CODE (TYPE_SIZE_UNIT (TREE_TYPE (ref))) == INTEGER_CST
+	      && !integer_zerop (TYPE_SIZE_UNIT (TREE_TYPE (ref))))
+	    rem = wi::mod_trunc (off, TYPE_SIZE_UNIT (TREE_TYPE (ref)), SIGNED);
+	  else
+	    /* If we can't compute the remainder simply force the initial
+	       condition to zero.  */
+	    rem = off;
+	  off = wide_int_to_tree (ssizetype, wi::sub (off, rem));
+	  memoff = wide_int_to_tree (TREE_TYPE (memoff), rem);
+	  /* And finally replace the initial condition.  */
 	  access_fn = chrec_replace_initial_condition
 	      (access_fn, fold_convert (orig_type, off));
 	  /* ???  This is still not a suitable base object for