On Fri, Sep 30, 2011 at 09:50:09AM +0200, Richard Guenther wrote:
> Hmm, in fwprop can you limit your change to non-invariant addresses? 
> That is, we do want to propagate invariant addresses over
> restrict casts, because that will give us _more_ precise alias info
> than restrict.

Will it?

I'd think we instead want add the non-restrict -> restrict check
in another spot (ssa_forward_propagate_and_combine) below.
Without that I'm afraid it is harder to disambiguate the accesses
(though, it still fails).  Or should PTA be able to disambiguate
it even without the ssa_forward_propagate_and_combine hunk?
One store will be through p1 + variableoffset with PT { a, <restrict decl for 
p1> } (restr)
and the other either with the hunk to p2 + constoffset with PT { a, <restrict 
decl for p2> } (restr)
or without the hunk a + constoffset.

2011-09-30  Jakub Jelinek  <ja...@redhat.com>

        * fold-const.c (fold_unary_loc): Don't optimize
        POINTER_PLUS_EXPR casted to TYPE_RESTRICT pointer by
        casting the inner pointer if it isn't TYPE_RESTRICT.
        * tree-ssa-forwprop.c (forward_propagate_addr_expr_1): Don't through
        casts from non-TYPE_RESTRICT pointer to TYPE_RESTRICT pointer.

        * gcc.dg/tree-ssa/restrict-4.c: New test.
        * gcc.dg/tree-ssa/restrict-5.c: New test.

--- gcc/fold-const.c.jj 2011-09-29 14:25:46.000000000 +0200
+++ gcc/fold-const.c    2011-09-29 18:20:04.000000000 +0200
@@ -7929,6 +7929,7 @@ fold_unary_loc (location_t loc, enum tre
         that this happens when X or Y is NOP_EXPR or Y is INTEGER_CST. */
       if (POINTER_TYPE_P (type)
          && TREE_CODE (arg0) == POINTER_PLUS_EXPR
+         && (!TYPE_RESTRICT (type) || TYPE_RESTRICT (TREE_TYPE (arg0)))
          && (TREE_CODE (TREE_OPERAND (arg0, 1)) == INTEGER_CST
              || TREE_CODE (TREE_OPERAND (arg0, 0)) == NOP_EXPR
              || TREE_CODE (TREE_OPERAND (arg0, 1)) == NOP_EXPR))
--- gcc/tree-ssa-forwprop.c.jj  2011-09-15 12:18:54.000000000 +0200
+++ gcc/tree-ssa-forwprop.c     2011-09-30 10:02:46.000000000 +0200
@@ -804,6 +804,10 @@ forward_propagate_addr_expr_1 (tree name
       && ((rhs_code == SSA_NAME && rhs == name)
          || CONVERT_EXPR_CODE_P (rhs_code)))
     {
+      /* Don't propagate restrict pointer's RHS.  */
+      if (TYPE_RESTRICT (TREE_TYPE (lhs))
+         && !TYPE_RESTRICT (TREE_TYPE (name)))
+       return false;
       /* Only recurse if we don't deal with a single use or we cannot
         do the propagation to the current statement.  In particular
         we can end up with a conversion needed for a non-invariant
@@ -2392,7 +2396,9 @@ ssa_forward_propagate_and_combine (void)
                 as well, as this is valid gimple.  */
              || (CONVERT_EXPR_CODE_P (code)
                  && TREE_CODE (rhs) == ADDR_EXPR
-                 && POINTER_TYPE_P (TREE_TYPE (lhs))))
+                 && POINTER_TYPE_P (TREE_TYPE (lhs))
+                 && (!TYPE_RESTRICT (TREE_TYPE (lhs))
+                     || TYPE_RESTRICT (TREE_TYPE (rhs)))))
            {
              tree base = get_base_address (TREE_OPERAND (rhs, 0));
              if ((!base
--- gcc/testsuite/gcc.dg/tree-ssa/restrict-4.c.jj       2011-09-29 
20:21:00.000000000 +0200
+++ gcc/testsuite/gcc.dg/tree-ssa/restrict-4.c  2011-09-29 20:21:57.000000000 
+0200
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+int
+foo (int *x, int y)
+{
+  int *__restrict p1 = x;
+  int *__restrict p2 = x + 32;
+  p1[y] = 1;
+  p2[4] = 2;
+  return p1[y];
+}
+
+int
+bar (int *x, int y)
+{
+  int *__restrict p1 = x;
+  int *p3 = x + 32;
+  int *__restrict p2 = p3;
+  p1[y] = 1;
+  p2[4] = 2;
+  return p1[y];
+}
+
+/* { dg-final { scan-tree-dump-times "return 1;" 2 "optimized" } } */
+/* { dg-final { cleanup-tree-dump "optimized" } } */
--- gcc/testsuite/gcc.dg/tree-ssa/restrict-5.c.jj       2011-09-30 
10:04:45.000000000 +0200
+++ gcc/testsuite/gcc.dg/tree-ssa/restrict-5.c  2011-09-30 10:05:11.000000000 
+0200
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+int a[64];
+
+int
+foo (int x)
+{
+  int *__restrict p1 = a + 4;
+  int *__restrict p2 = a + 16;
+  p1[x] = 1;
+  p2[2] = 2;
+  return p1[x];
+}
+
+/* { dg-final { scan-tree-dump-times "return 1;" 1 "optimized" } } */
+/* { dg-final { cleanup-tree-dump "optimized" } } */


        Jakub

Reply via email to