diff mbox

Fix estimated number of iterations for loops with multiple exits

Message ID 20121014162215.GB14032@kam.mff.cuni.cz
State New
Headers show

Commit Message

Jan Hubicka Oct. 14, 2012, 4:22 p.m. UTC
Hi,
the update of RTL optimizers to use SCEV's loop bounds make them to be inexpectedly active.
One of reasons is invalid.  For loop

int *a;
int t()
{
   int i;
  for (i=0;i<1000000;i++)
    if (a[i])
      return 1;
  return 0;
}

We get realistic number of iteration estimate to be 9999999. This is quite
wrong.  We could however still predict loop:

int t2()
{
   int i;
  for (i=0;i<3000000;i++)
    if (a[i])
        abort ();
  return 0;
}

This patch implements that by making estimate_numbers_of_iterations_loop to 
save the realistic estimate only when all other exits out of the loop are unlikely
(i.e. EH or predicted by NORETURN or similarly strong heuristic).

Bootstrapped/regtested x86_64-linux, comitted.

Honza

	* tree-ssa-loop-niter.c (estimate_numbers_of_iterations_loop): Do not
	predict loops with multiple exits realistically.
	* cfgloopanal.c (single_likely_exit): New function.

	* gcc.dg/unroll_5.c: New testcase.
diff mbox

Patch

Index: tree-ssa-loop-niter.c
===================================================================
--- tree-ssa-loop-niter.c	(revision 192432)
+++ tree-ssa-loop-niter.c	(working copy)
@@ -2965,6 +2965,7 @@  estimate_numbers_of_iterations_loop (str
   struct tree_niter_desc niter_desc;
   edge ex;
   double_int bound;
+  edge likely_exit;
 
   /* Give up if we already have tried to compute an estimation.  */
   if (loop->estimate_state != EST_NOT_COMPUTED)
@@ -2975,6 +2976,7 @@  estimate_numbers_of_iterations_loop (str
   loop->any_estimate = false;
 
   exits = get_loop_exit_edges (loop);
+  likely_exit = single_likely_exit (loop);
   FOR_EACH_VEC_ELT (edge, exits, i, ex)
     {
       if (!number_of_iterations_exit (loop, ex, &niter_desc, false))
@@ -2988,7 +2990,7 @@  estimate_numbers_of_iterations_loop (str
 			niter);
       record_estimate (loop, niter, niter_desc.max,
 		       last_stmt (ex->src),
-		       true, true, true);
+		       true, ex == likely_exit, true);
     }
   VEC_free (edge, heap, exits);
 
Index: cfgloopanal.c
===================================================================
--- cfgloopanal.c	(revision 192432)
+++ cfgloopanal.c	(working copy)
@@ -446,3 +446,40 @@  mark_loop_exit_edges (void)
     }
 }
 
+/* Return exit edge if loop has only one exit that is likely
+   to be executed on runtime (i.e. it is not EH or leading
+   to noreturn call.  */
+
+edge
+single_likely_exit (struct loop *loop)
+{
+  edge found = single_exit (loop);
+  VEC (edge, heap) *exits;
+  unsigned i;
+  edge ex;
+
+  if (found)
+    return found;
+  exits = get_loop_exit_edges (loop);
+  FOR_EACH_VEC_ELT (edge, exits, i, ex)
+    {
+      if (ex->flags & (EDGE_EH | EDGE_ABNORMAL_CALL))
+	continue;
+      /* The constant of 5 is set in a way so noreturn calls are
+	 ruled out by this test.  The static branch prediction algorithm
+         will not assign such a low probability to conditionals for usual
+         reasons.  */
+      if (profile_status != PROFILE_ABSENT
+	  && ex->probability < 5 && !ex->count)
+	continue;
+      if (!found)
+	found = ex;
+      else
+	{
+	  VEC_free (edge, heap, exits);
+	  return NULL;
+	}
+    }
+  VEC_free (edge, heap, exits);
+  return found;
+}
Index: testsuite/gcc.dg/unroll_5.c
===================================================================
--- testsuite/gcc.dg/unroll_5.c	(revision 0)
+++ testsuite/gcc.dg/unroll_5.c	(revision 0)
@@ -0,0 +1,25 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-rtl-loop2_unroll -funroll-loops" } */
+void abort (void);
+int *a;
+int t()
+{
+   int i;
+  for (i=0;i<1000000;i++)
+    if (a[i])
+      return 1;
+  return 0;
+}
+int t2()
+{
+   int i;
+  for (i=0;i<3000000;i++)
+    if (a[i])
+        abort ();
+  return 0;
+}
+/* { dg-final { scan-rtl-dump-times "upper bound: 999999" 1 "loop2_unroll" } } */
+/* { dg-final { scan-rtl-dump-not "realistic bound: 999999" "loop2_unroll" } } */
+/* { dg-final { scan-rtl-dump-times "upper bound: 2999999" 1 "loop2_unroll" } } */
+/* { dg-final { scan-rtl-dump-times "realistic bound: 2999999" 1 "loop2_unroll" } } */
+/* { dg-final { cleanup-rtl-dump "loop2_unroll" } } */