peel-1.c: New testcase.

	* gcc.dg/tree-prof/peel-1.c: New testcase.
	* loop-unroll.c (decide_peel_simple): Simple peeling makes sense even
	with simple loops; bound number of branches only when FDO is not
	available.
	(decide_unroll_stupid): Mention that num_loop_branches heuristics
	is off.

From-SVN: r192718

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index bbe8f8417b752d801c4252d2b3524400f023461c..41e004b44cb8db2009a136e531f4032b1a184e57 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2012-10-23  Jan Hubicka  <jh@suse.cz>
+
+       * loop-unroll.c (decide_peel_simple): Simple peeling makes sense even
+       with simple loops; bound number of branches only when FDO is not
+       available.
+       (decide_unroll_stupid): Mention that num_loop_branches heuristics
+       is off.
+
 2012-10-23  Nick Clifton  <nickc@redhat.com>
 
        PR target/54660

diff --git a/gcc/loop-unroll.c b/gcc/loop-unroll.c
index 2398e6d6b1145af2dc51b9dd4f214be6f2732488..92e3c1a127cd522f987ea47c4c48123639105478 100644 (file)
--- a/gcc/loop-unroll.c
+++ b/gcc/loop-unroll.c
@@ -1228,7 +1228,6 @@ static void
 decide_peel_simple (struct loop *loop, int flags)
 {
   unsigned npeel;
-  struct niter_desc *desc;
   double_int iterations;
 
   if (!(flags & UAP_PEEL))
@@ -1253,20 +1252,17 @@ decide_peel_simple (struct loop *loop, int flags)
       return;
     }
 
-  /* Check for simple loops.  */
-  desc = get_simple_loop_desc (loop);
-
-  /* Check number of iterations.  */
-  if (desc->simple_p && !desc->assumptions && desc->const_iter)
-    {
-      if (dump_file)
-       fprintf (dump_file, ";; Loop iterates constant times\n");
-      return;
-    }
-
   /* Do not simply peel loops with branches inside -- it increases number
-     of mispredicts.  */
-  if (num_loop_branches (loop) > 1)
+     of mispredicts.  
+     Exception is when we do have profile and we however have good chance
+     to peel proper number of iterations loop will iterate in practice.
+     TODO: this heuristic needs tunning; while for complette unrolling
+     the branch inside loop mostly eliminates any improvements, for
+     peeling it is not the case.  Also a function call inside loop is
+     also branch from branch prediction POV (and probably better reason
+     to not unroll/peel).  */
+  if (num_loop_branches (loop) > 1
+      && profile_status != PROFILE_READ)
     {
       if (dump_file)
        fprintf (dump_file, ";; Not peeling, contains branches\n");
@@ -1435,7 +1431,9 @@ decide_unroll_stupid (struct loop *loop, int flags)
     }
 
   /* Do not unroll loops with branches inside -- it increases number
-     of mispredicts.  */
+     of mispredicts. 
+     TODO: this heuristic needs tunning; call inside the loop body
+     is also relatively good reason to not unroll.  */
   if (num_loop_branches (loop) > 1)
     {
       if (dump_file)

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 89a45791f1fcd2387cffd2209a8afae0e47d14ac..ddfef9753f192412eea9f19560a57b7e7ee61391 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,7 +1,11 @@
+2012-10-23  Jan Hubicka  <jh@suse.cz>
+
+       * gcc.dg/tree-prof/peel-1.c: New testcase.
+
 2012-10-23  Dominique d'Humieres  <dominiq@lps.ens.fr>
 
        PR gcc/52945
-       * testsuite/gcc.dg/lto/pr52634_0.c: skip the test on Darwin.
+       * gcc.dg/lto/pr52634_0.c: skip the test on Darwin.
 
 2012-10-23  Joseph Myers  <joseph@codesourcery.com>
 

diff --git a/gcc/testsuite/gcc.dg/tree-prof/peel-1.c b/gcc/testsuite/gcc.dg/tree-prof/peel-1.c
new file mode 100644 (file)
index 0000000..baa601d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-prof/peel-1.c
@@ -0,0 +1,25 @@
+/* { dg-options "-O3 -fdump-rtl-loop2_unroll -fno-unroll-loops -fpeel-loops" } */
+void abort();
+
+int a[1000];
+int
+__attribute__ ((noinline))
+t()
+{
+  int i;
+  for (i=0;i<1000;i++)
+    if (!a[i])
+      return 1;
+  abort ();
+}
+main()
+{
+  int i;
+  for (i=0;i<1000;i++)
+    t();
+  return 0;
+}
+/* { dg-final-use { scan-rtl-dump "Considering simply peeling loop" "loop2_unroll" } } */
+/* In fact one peeling is enough; we however mispredict number of iterations of the loop
+   at least until loop_ch is schedule ahead of profiling pass.  */
+/* { dg-final-use { cleanup-rtl-dump "Decided to simply peel the loop 2 times" } } */