[RFC, PR66873] Use graphite for parloops

[Tom de Vries <Tom_deVries@mentor.com>]

[-- Attachment #1: Type: text/plain, Size: 2258 bytes --]

Hi,

I tried to parallelize this fortran test-case (based on 
autopar/outer-1.c), specifically the outer loop of the first loop nest 
using -ftree-parallelize-loops=2:
...
program main
   implicit none
   integer, parameter         :: n = 500
   integer, dimension (0:n-1, 0:n-1) :: x
   integer                    :: i, j, ii, jj


   do ii = 0, n - 1
      do jj = 0, n - 1
         x(jj, ii) = ii + jj + 3
      end do
   end do

   do i = 0, n - 1
      do j = 0, n - 1
         if (x(j, i) .ne. i + j + 3) call abort
      end do
   end do

end program main
...

But autopar fails to parallelize due to failing dependency analysis.

I then tried to add -floop-parallelize-all, and found that the graphite 
dependency analysis did manage to decide that the iterations are 
independent.

At https://gcc.gnu.org/wiki/Graphite/Parallelization I read:
...
In GCC there already exists an auto-parallelization pass 
(tree-parloops.c), which is base on the lambda framework originally 
developed by Sebastian. Since Lambda framework is limited to some cases 
(e.g. triangle loops, loops with 'if' conditions), Graphite was 
developed to handle the loops that lambda was not able to handle .
...

So I wondered, why not always use the graphite dependency analysis in 
parloops. (Of course you could use -floop-parallelize-all, but that also 
changes the heuristic). So I wrote a patch for parloops to use graphite 
dependency analysis by default (so without -floop-parallelize-all), but 
while testing found out that all the reduction test-cases started 
failing because the modifications graphite makes to the code messes up 
the parloops reduction analysis.

Then I came up with this patch, which:
- first runs a parloops pass, restricted to reduction loops only,
- then runs graphite dependency analysis
- followed by a normal parloops pass run.

This way, we get to both:
- compile the reduction testcases as before, and
- profit from the better graphite dependency analysis otherwise.

A point worth noting is that I stopped running pass_iv_canon before 
parloops (only in case of -ftree-parallelize-loops > 1) because running 
it before graphite makes the graphite scop detection fail.

Bootstrapped and reg-tested on x86_64.

Any comments?

Thanks,
- Tom

[-- Attachment #2: 0001-Use-graphite-for-parloops.patch --]
[-- Type: text/x-patch, Size: 39954 bytes --]

Use graphite for parloops

2015-07-15  Tom de Vries  <tom@codesourcery.com>

	PR tree-optimization/66873
	* graphite-isl-ast-to-gimple.c (translate_isl_ast_for_loop):
	(scop_to_isl_ast): Handle flag_tree_parallelize_loops.
	* graphite-poly.c (apply_poly_transforms): Same.
	* graphite.c (gate_graphite_transforms): Remove static.
	(pass_graphite_parloops): New pass.
	(make_pass_graphite_parloops): New function.
	(pass_graphite_transforms2): New pass.
	(make_pass_graphite_transforms2): New function.
	* omp-low.c (pass_expand_omp_ssa::clone): Same.
	* passes.def: Add pass groups pass_parallelize_reductions and
	pass_graphite_parloops.
	* tree-parloops.c (gen_parallel_loop): Add debug print for alternative
	exit-first loop transform.
	(parallelize_loops): Add reductions_only parameter.
	(pass_parallelize_loops::execute): Call parallelize_loops with extra
	argument.
	(pass_parallelize_reductions): New pass.
	(pass_parallelize_reductions::execute)
	(make_pass_parallelize_reductions): New function.
	* tree-pass.h (make_pass_graphite_parloops)
	(make_pass_parallelize_reductions, make_pass_graphite_transforms2)
	(gate_graphite_transforms): Declare.
	tree-ssa-loop-ivcanon.c (pass_iv_canon::gate): Return false if
	flag_tree_parallelize_loops > 1.

	* gcc.dg/autopar/outer-6.c: Update for new pass parloopsred.
	* gcc.dg/autopar/reduc-1.c: Same.
	* gcc.dg/autopar/reduc-1char.c: Same.
	* gcc.dg/autopar/reduc-1short.c: Same.
	* gcc.dg/autopar/reduc-2.c: Same.
	* gcc.dg/autopar/reduc-2char.c: Same.
	* gcc.dg/autopar/reduc-2short.c: Same.
	* gcc.dg/autopar/reduc-3.c: Same.
	* gcc.dg/autopar/reduc-6.c: Same.
	* gcc.dg/autopar/reduc-7.c: Same.
	* gcc.dg/autopar/reduc-8.c: Same.
	* gcc.dg/autopar/reduc-9.c: Same.
	* gcc.dg/parloops-exit-first-loop-alt-2.c: Same.
	* gcc.dg/parloops-exit-first-loop-alt-3.c: Same.
	* gcc.dg/parloops-exit-first-loop-alt-4.c: Same.
	* gcc.dg/parloops-exit-first-loop-alt-5.c: Same.
	* gcc.dg/parloops-exit-first-loop-alt-6.c: Same.
	* gcc.dg/parloops-exit-first-loop-alt-7.c: Same.
	* gcc.dg/parloops-exit-first-loop-alt-pr66652.c: Same.
	* gcc.dg/parloops-exit-first-loop-alt.c: Same.
	* gfortran.dg/parloops-exit-first-loop-alt-2.f95: Same.
	* gfortran.dg/parloops-exit-first-loop-alt.f95: Same.
	* gfortran.dg/parloops-outer-1.f95: New test.
---
 gcc/graphite-isl-ast-to-gimple.c                   |  6 +-
 gcc/graphite-poly.c                                |  3 +-
 gcc/graphite.c                                     | 83 ++++++++++++++++++-
 gcc/omp-low.c                                      |  1 +
 gcc/passes.def                                     | 11 +++
 gcc/testsuite/gcc.dg/autopar/outer-6.c             |  6 +-
 gcc/testsuite/gcc.dg/autopar/reduc-1.c             |  7 +-
 gcc/testsuite/gcc.dg/autopar/reduc-1char.c         |  7 +-
 gcc/testsuite/gcc.dg/autopar/reduc-1short.c        |  7 +-
 gcc/testsuite/gcc.dg/autopar/reduc-2.c             |  7 +-
 gcc/testsuite/gcc.dg/autopar/reduc-2char.c         |  7 +-
 gcc/testsuite/gcc.dg/autopar/reduc-2short.c        |  7 +-
 gcc/testsuite/gcc.dg/autopar/reduc-3.c             |  5 +-
 gcc/testsuite/gcc.dg/autopar/reduc-6.c             |  6 +-
 gcc/testsuite/gcc.dg/autopar/reduc-7.c             |  7 +-
 gcc/testsuite/gcc.dg/autopar/reduc-8.c             |  7 +-
 gcc/testsuite/gcc.dg/autopar/reduc-9.c             |  7 +-
 .../gcc.dg/parloops-exit-first-loop-alt-2.c        |  9 +--
 .../gcc.dg/parloops-exit-first-loop-alt-3.c        |  9 +--
 .../gcc.dg/parloops-exit-first-loop-alt-4.c        |  9 +--
 .../gcc.dg/parloops-exit-first-loop-alt-5.c        |  9 +--
 .../gcc.dg/parloops-exit-first-loop-alt-6.c        |  9 +--
 .../gcc.dg/parloops-exit-first-loop-alt-7.c        |  9 +--
 .../gcc.dg/parloops-exit-first-loop-alt-pr66652.c  | 11 +--
 .../gcc.dg/parloops-exit-first-loop-alt.c          | 10 +--
 .../gfortran.dg/parloops-exit-first-loop-alt-2.f95 |  9 +--
 .../gfortran.dg/parloops-exit-first-loop-alt.f95   | 10 +--
 gcc/testsuite/gfortran.dg/parloops-outer-1.f95     | 37 +++++++++
 gcc/tree-parloops.c                                | 93 ++++++++++++++++++++--
 gcc/tree-pass.h                                    |  5 ++
 gcc/tree-ssa-loop-ivcanon.c                        |  6 +-
 31 files changed, 303 insertions(+), 116 deletions(-)
 create mode 100644 gcc/testsuite/gfortran.dg/parloops-outer-1.f95

diff --git a/gcc/graphite-isl-ast-to-gimple.c b/gcc/graphite-isl-ast-to-gimple.c
index b32781a5..bdafd40 100644
--- a/gcc/graphite-isl-ast-to-gimple.c
+++ b/gcc/graphite-isl-ast-to-gimple.c
@@ -442,7 +442,8 @@ translate_isl_ast_for_loop (loop_p context_loop,
   redirect_edge_succ_nodup (next_e, after);
   set_immediate_dominator (CDI_DOMINATORS, next_e->dest, next_e->src);
 
-  if (flag_loop_parallelize_all)
+  if (flag_loop_parallelize_all
+      || flag_tree_parallelize_loops > 1)
   {
     isl_id *id = isl_ast_node_get_annotation (node_for);
     gcc_assert (id);
@@ -995,7 +996,8 @@ scop_to_isl_ast (scop_p scop, ivs_params &ip)
   context_isl = set_options (context_isl, schedule_isl, options_luj);
 
   isl_union_map *dependences = NULL;
-  if (flag_loop_parallelize_all)
+  if (flag_loop_parallelize_all
+      || flag_tree_parallelize_loops > 1)
   {
     dependences = scop_get_dependences (scop);
     context_isl =
diff --git a/gcc/graphite-poly.c b/gcc/graphite-poly.c
index bcd08d8..e32325e 100644
--- a/gcc/graphite-poly.c
+++ b/gcc/graphite-poly.c
@@ -241,7 +241,8 @@ apply_poly_transforms (scop_p scop)
   if (flag_graphite_identity)
     transform_done = true;
 
-  if (flag_loop_parallelize_all)
+  if (flag_loop_parallelize_all
+      || flag_tree_parallelize_loops > 1)
     transform_done = true;
 
   if (flag_loop_block)
diff --git a/gcc/graphite.c b/gcc/graphite.c
index a81ef6a..6ba58c0 100644
--- a/gcc/graphite.c
+++ b/gcc/graphite.c
@@ -319,7 +319,7 @@ graphite_transforms (struct function *fun)
   return 0;
 }
 
-static bool
+bool
 gate_graphite_transforms (void)
 {
   /* Enable -fgraphite pass if any one of the graphite optimization flags
@@ -373,6 +373,45 @@ make_pass_graphite (gcc::context *ctxt)
 
 namespace {
 
+const pass_data pass_data_graphite_parloops =
+{
+  GIMPLE_PASS, /* type */
+  "graphite_parloops", /* name */
+  OPTGROUP_LOOP, /* optinfo_flags */
+  TV_GRAPHITE, /* tv_id */
+  ( PROP_cfg | PROP_ssa ), /* properties_required */
+  0, /* properties_provided */
+  0, /* properties_destroyed */
+  0, /* todo_flags_start */
+  0, /* todo_flags_finish */
+};
+
+class pass_graphite_parloops : public gimple_opt_pass
+{
+public:
+  pass_graphite_parloops (gcc::context *ctxt)
+    : gimple_opt_pass (pass_data_graphite_parloops, ctxt)
+  {}
+
+  /* opt_pass methods: */
+  virtual bool gate (function *)
+  {
+    return (flag_tree_parallelize_loops > 1
+	    && !gate_graphite_transforms ());
+  }
+
+}; // class pass_graphite_parloops
+
+} // anon namespace
+
+gimple_opt_pass *
+make_pass_graphite_parloops (gcc::context *ctxt)
+{
+  return new pass_graphite_parloops (ctxt);
+}
+
+namespace {
+
 const pass_data pass_data_graphite_transforms =
 {
   GIMPLE_PASS, /* type */
@@ -407,4 +446,46 @@ make_pass_graphite_transforms (gcc::context *ctxt)
   return new pass_graphite_transforms (ctxt);
 }
 
+/* It would be preferable to use a clone of pass_data_graphite_transforms rather
+   than declare a new pass.  But when using a clone of
+   pass_data_graphite_transforms (and changing the gate to trigger for
+   flag_tree_parallelize_loops > 1 as well) in pass group
+   pass_graphite_parloops, the pass is not executed.  */
+
+namespace {
+
+const pass_data pass_data_graphite_transforms2 =
+{
+  GIMPLE_PASS, /* type */
+  "graphite2", /* name */
+  OPTGROUP_LOOP, /* optinfo_flags */
+  TV_GRAPHITE_TRANSFORMS, /* tv_id */
+  ( PROP_cfg | PROP_ssa ), /* properties_required */
+  0, /* properties_provided */
+  0, /* properties_destroyed */
+  0, /* todo_flags_start */
+  0, /* todo_flags_finish */
+};
+
+class pass_graphite_transforms2 : public gimple_opt_pass
+{
+public:
+  pass_graphite_transforms2 (gcc::context *ctxt)
+    : gimple_opt_pass (pass_data_graphite_transforms2, ctxt)
+  {}
 
+  /* opt_pass methods: */
+  virtual bool gate (function *)
+  {
+    return (flag_tree_parallelize_loops > 1);
+  }
+  virtual unsigned int execute (function *fun) { return graphite_transforms (fun); }
+}; // class pass_graphite_transforms2
+
+} // anon namespace
+
+gimple_opt_pass *
+make_pass_graphite_transforms2 (gcc::context *ctxt)
+{
+  return new pass_graphite_transforms2 (ctxt);
+}
diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index 3135606..8cbee3a 100644
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -9576,6 +9576,7 @@ public:
       return !(fun->curr_properties & PROP_gimple_eomp);
     }
   virtual unsigned int execute (function *) { return execute_expand_omp (); }
+  opt_pass *clone () { return new pass_expand_omp_ssa (m_ctxt); }
 
 }; // class pass_expand_omp_ssa
 
diff --git a/gcc/passes.def b/gcc/passes.def
index 5cd07ae..aa1d1a1 100644
--- a/gcc/passes.def
+++ b/gcc/passes.def
@@ -244,6 +244,17 @@ along with GCC; see the file COPYING3.  If not see
 	      NEXT_PASS (pass_dce);
 	  POP_INSERT_PASSES ()
 	  NEXT_PASS (pass_iv_canon);
+	  NEXT_PASS (pass_parallelize_reductions);
+	  PUSH_INSERT_PASSES_WITHIN (pass_parallelize_reductions)
+	      NEXT_PASS (pass_expand_omp_ssa);
+	  POP_INSERT_PASSES ()
+	  NEXT_PASS (pass_graphite_parloops);
+	  PUSH_INSERT_PASSES_WITHIN (pass_graphite_parloops)
+	      NEXT_PASS (pass_graphite_transforms2);
+	      NEXT_PASS (pass_lim);
+	      NEXT_PASS (pass_copy_prop);
+	      NEXT_PASS (pass_dce);
+	  POP_INSERT_PASSES ()
 	  NEXT_PASS (pass_parallelize_loops);
 	  PUSH_INSERT_PASSES_WITHIN (pass_parallelize_loops)
 	      NEXT_PASS (pass_expand_omp_ssa);
diff --git a/gcc/testsuite/gcc.dg/autopar/outer-6.c b/gcc/testsuite/gcc.dg/autopar/outer-6.c
index 6bef7cc..0f01bd5 100644
--- a/gcc/testsuite/gcc.dg/autopar/outer-6.c
+++ b/gcc/testsuite/gcc.dg/autopar/outer-6.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-optimized" } */
 
 void abort (void);
 
@@ -44,6 +44,6 @@ int main(void)
 
 
 /* Check that outer loop is parallelized.  */
-/* { dg-final { scan-tree-dump-times "parallelizing outer loop" 1 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "parallelizing inner loop" 0 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "parallelizing outer loop" 1 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "parallelizing inner loop" 0 "parloopsred" } } */
 /* { dg-final { scan-tree-dump-times "loopfn" 4 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-1.c b/gcc/testsuite/gcc.dg/autopar/reduc-1.c
index 6e9a280..4fc9b31 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-1.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-1.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdarg.h>
 #include <stdlib.h>
@@ -66,6 +66,7 @@ int main (void)
 }
 
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 4 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
 
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-1char.c b/gcc/testsuite/gcc.dg/autopar/reduc-1char.c
index 48ead88..497b7e0 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-1char.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-1char.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdarg.h>
 #include <stdlib.h>
@@ -60,6 +60,7 @@ int main (void)
 }
 
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 4 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
 
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-1short.c b/gcc/testsuite/gcc.dg/autopar/reduc-1short.c
index f3f547c..6af8e4b 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-1short.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-1short.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdarg.h>
 #include <stdlib.h>
@@ -59,6 +59,7 @@ int main (void)
   return 0;
 }
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 4 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
 
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-2.c b/gcc/testsuite/gcc.dg/autopar/reduc-2.c
index 3ad16e4..2d0b2a1 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-2.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-2.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdarg.h>
 #include <stdlib.h>
@@ -63,6 +63,7 @@ int main (void)
   return 0;
 }
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 4 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
 
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-2char.c b/gcc/testsuite/gcc.dg/autopar/reduc-2char.c
index 072489f..49ef16d 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-2char.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-2char.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdarg.h>
 #include <stdlib.h>
@@ -60,7 +60,8 @@ int main (void)
 }
 
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
 
 
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-2short.c b/gcc/testsuite/gcc.dg/autopar/reduc-2short.c
index 4dbbc8a..3ec1c2a 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-2short.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-2short.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdarg.h>
 #include <stdlib.h>
@@ -59,6 +59,7 @@ int main (void)
 }
 
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
 
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-3.c b/gcc/testsuite/gcc.dg/autopar/reduc-3.c
index 0d4baef..e7ca82b 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-3.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-3.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdarg.h>
 #include <stdlib.h>
@@ -50,6 +50,7 @@ int main (void)
 }
 
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 1 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 1 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloopsred" } } */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloops" } } */
 
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-6.c b/gcc/testsuite/gcc.dg/autopar/reduc-6.c
index 91f679e..6c5ec7b 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-6.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-6.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdarg.h>
 #include <stdlib.h>
@@ -56,6 +56,6 @@ int main (void)
 
 
 /* need -ffast-math to  parallelize these loops.  */
-/* { dg-final { scan-tree-dump-times "Detected reduction" 0 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 0 "parloopsred" } } */
 /* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "FAILED: it is not a part of reduction" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "FAILED: it is not a part of reduction" 3 "parloopsred" } } */
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-7.c b/gcc/testsuite/gcc.dg/autopar/reduc-7.c
index 77b99e1..dccf2a5 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-7.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-7.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdlib.h>
 
@@ -84,6 +84,7 @@ int main (void)
 }
 
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
 
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-8.c b/gcc/testsuite/gcc.dg/autopar/reduc-8.c
index 16fb954..466bcc5 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-8.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-8.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdlib.h>
 
@@ -84,5 +84,6 @@ int main (void)
 }
 
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-9.c b/gcc/testsuite/gcc.dg/autopar/reduc-9.c
index 90f4db2..11556d7 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-9.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-9.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloopsred-details -fdump-tree-parloops-details -fdump-tree-optimized" } */
 
 #include <stdlib.h>
 
@@ -84,5 +84,6 @@ int main (void)
 }
 
 
-/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloops" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } } */
diff --git a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-2.c b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-2.c
index 24e605a..f1cf75f 100644
--- a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-2.c
+++ b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-2.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target pthread } */
-/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops-details" } */
 
 /* Constant bound, vector addition.  */
 
@@ -19,9 +19,4 @@ f (void)
       c[i] = a[i] + b[i];
 }
 
-/* Three times three array accesses:
-   - three in f._loopfn.0
-   - three in the parallel
-   - three in the low iteration count loop
-   Crucially, none for a peeled off last iteration following the parallel.  */
-/* { dg-final { scan-tree-dump-times "(?n)\\\[i" 9 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloops" } } */
diff --git a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-3.c b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-3.c
index fec53a1..6c34084 100644
--- a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-3.c
+++ b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-3.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target pthread } */
-/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloopsred-details" } */
 
 /* Variable bound, reduction.  */
 
@@ -18,9 +18,4 @@ f (unsigned int n, unsigned int *__restrict__ a)
   return sum;
 }
 
-/* Three array accesses:
-   - one in f._loopfn.0
-   - one in the parallel
-   - one in the low iteration count loop
-   Crucially, none for a peeled off last iteration following the parallel.  */
-/* { dg-final { scan-tree-dump-times "(?n)\\\* 4" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloopsred" } } */
diff --git a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-4.c b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-4.c
index 2b8d289..f051ed4 100644
--- a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-4.c
+++ b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-4.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target pthread } */
-/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloopsred-details" } */
 
 /* Constant bound, reduction.  */
 
@@ -20,9 +20,4 @@ f (void)
   return sum;
 }
 
-/* Three array accesses:
-   - one in f._loopfn.0
-   - one in the parallel
-   - one in the low iteration count loop
-   Crucially, none for a peeled off last iteration following the parallel.  */
-/* { dg-final { scan-tree-dump-times "(?n)\\\* 4" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloopsred" } } */
diff --git a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-5.c b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-5.c
index 3f799cf..3c1e99b 100644
--- a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-5.c
+++ b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-5.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target pthread } */
-/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops-details" } */
 
 /* Variable bound, vector addition, unsigned loop counter, unsigned bound.  */
 
@@ -14,9 +14,4 @@ f (unsigned int n, unsigned int *__restrict__ a, unsigned int *__restrict__ b,
     c[i] = a[i] + b[i];
 }
 
-/* Three times a store:
-   - one in f._loopfn.0
-   - one in the parallel
-   - one in the low iteration count loop
-   Crucially, none for a peeled off last iteration following the parallel.  */
-/* { dg-final { scan-tree-dump-times "(?n)^  \\*_\[0-9\]*" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloops" } } */
diff --git a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-6.c b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-6.c
index ee19a55..edc60ba 100644
--- a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-6.c
+++ b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-6.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target pthread } */
-/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops-details" } */
 
 /* Variable bound, vector addition, unsigned loop counter, signed bound.  */
 
@@ -14,9 +14,4 @@ f (int n, unsigned int *__restrict__ a, unsigned int *__restrict__ b,
     c[i] = a[i] + b[i];
 }
 
-/* Three times a store:
-   - one in f._loopfn.0
-   - one in the parallel
-   - one in the low iteration count loop
-   Crucially, none for a peeled off last iteration following the parallel.  */
-/* { dg-final { scan-tree-dump-times "(?n)^  \\*_\[0-9\]*" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloops" } } */
diff --git a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-7.c b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-7.c
index c337342..38be2e8 100644
--- a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-7.c
+++ b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-7.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target pthread } */
-/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops-details" } */
 
 /* Variable bound, vector addition, signed loop counter, signed bound.  */
 
@@ -14,9 +14,4 @@ f (int n, unsigned int *__restrict__ a, unsigned int *__restrict__ b,
     c[i] = a[i] + b[i];
 }
 
-/* Three times a store:
-   - one in f._loopfn.0
-   - one in the parallel
-   - one in the low iteration count loop
-   Crucially, none for a peeled off last iteration following the parallel.  */
-/* { dg-final { scan-tree-dump-times "(?n)^  \\*_\[0-9\]*" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloops" } } */
diff --git a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-pr66652.c b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-pr66652.c
index 2ea097d..7b64368 100644
--- a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-pr66652.c
+++ b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt-pr66652.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target pthread } */
-/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloopsred-details" } */
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -22,10 +22,5 @@ f (unsigned int n, unsigned int sum)
   return sum;
 }
 
-/* Four times % 13:
-   - once in f._loopfn.0
-   - once in the parallel
-   - once in the low iteration count loop
-   - once for a peeled off last iteration following the parallel.
-   In other words, we want try_transform_to_exit_first_loop_alt to fail.  */
-/* { dg-final { scan-tree-dump-times "(?n)% 13" 4 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "parallelizing inner loop" 1 "parloopsred" } } */
+/* { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 0 "parloopsred" } } */
diff --git a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt.c b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt.c
index 0b69165..44596e3 100644
--- a/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt.c
+++ b/gcc/testsuite/gcc.dg/parloops-exit-first-loop-alt.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
 /* { dg-require-effective-target pthread } */
-/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops" } */
+/* { dg-options "-O2 -ftree-parallelize-loops=2 -fdump-tree-parloops-details" } */
 
 /* Variable bound, vector addition, signed loop counter, unsigned bound.  */
 
@@ -14,9 +14,5 @@ f (unsigned int n, unsigned int *__restrict__ a, unsigned int *__restrict__ b,
     c[i] = a[i] + b[i];
 }
 
-/* Three times a store:
-   - one in f._loopfn.0
-   - one in the parallel
-   - one in the low iteration count loop
-   Crucially, none for a peeled off last iteration following the parallel.  */
-/* { dg-final { scan-tree-dump-times "(?n)^  \\*_\[0-9\]*" 3 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloops" } } */
+
diff --git a/gcc/testsuite/gfortran.dg/parloops-exit-first-loop-alt-2.f95 b/gcc/testsuite/gfortran.dg/parloops-exit-first-loop-alt-2.f95
index f26a6e3..52434f2 100644
--- a/gcc/testsuite/gfortran.dg/parloops-exit-first-loop-alt-2.f95
+++ b/gcc/testsuite/gfortran.dg/parloops-exit-first-loop-alt-2.f95
@@ -1,7 +1,7 @@
 ! { dg-additional-options "-O2" }
 ! { dg-require-effective-target pthread }
 ! { dg-additional-options "-ftree-parallelize-loops=2" }
-! { dg-additional-options "-fdump-tree-parloops" }
+! { dg-additional-options "-fdump-tree-parloops-details" }
 
 ! Constant bound, vector addition.
 
@@ -16,9 +16,4 @@ subroutine foo ()
   end do
 end subroutine foo
 
-! Three times plus 25:
-! - once in f._loopfn.0
-! - once in the parallel
-! - once in the low iteration count loop
-! Crucially, none for a peeled off last iteration following the parallel.
-! { dg-final { scan-tree-dump-times "(?n) \\+ 25;" 3 "parloops" } }
+! { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloops" } }
diff --git a/gcc/testsuite/gfortran.dg/parloops-exit-first-loop-alt.f95 b/gcc/testsuite/gfortran.dg/parloops-exit-first-loop-alt.f95
index 6dc8a38..1eb9dfd 100644
--- a/gcc/testsuite/gfortran.dg/parloops-exit-first-loop-alt.f95
+++ b/gcc/testsuite/gfortran.dg/parloops-exit-first-loop-alt.f95
@@ -1,7 +1,7 @@
 ! { dg-additional-options "-O2" }
 ! { dg-require-effective-target pthread }
 ! { dg-additional-options "-ftree-parallelize-loops=2" }
-! { dg-additional-options "-fdump-tree-parloops" }
+! { dg-additional-options "-fdump-tree-parloops-details" }
 
 ! Variable bound, vector addition.
 
@@ -17,9 +17,5 @@ subroutine foo (nr)
   end do
 end subroutine foo
 
-! Three times plus 25:
-! - once in f._loopfn.0
-! - once in the parallel
-! - once in the low iteration count loop
-! Crucially, none for a peeled off last iteration following the parallel.
-! { dg-final { scan-tree-dump-times "(?n) \\+ 25;" 3 "parloops" } }
+! { dg-final { scan-tree-dump-times "alternative exit-first loop transform succeeded" 1 "parloops" } }
+
diff --git a/gcc/testsuite/gfortran.dg/parloops-outer-1.f95 b/gcc/testsuite/gfortran.dg/parloops-outer-1.f95
new file mode 100644
index 0000000..144e4e8
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/parloops-outer-1.f95
@@ -0,0 +1,37 @@
+! { dg-do compile }
+! { dg-additional-options "-O2" }
+! { dg-additional-options "-ftree-parallelize-loops=2" }
+! { dg-additional-options "-fdump-tree-parloops-all" }
+! { dg-additional-options "-fdump-tree-optimized" }
+
+! Based on autopar/outer-1.c.
+
+program main
+  implicit none
+  integer, parameter         :: n = 500
+  integer, dimension (0:n-1, 0:n-1) :: x
+  integer                    :: i, j, ii, jj
+
+
+  do ii = 0, n - 1
+     do jj = 0, n - 1
+        x(jj, ii) = ii + jj + 3
+     end do
+  end do
+
+  do i = 0, n - 1
+     do j = 0, n - 1
+        if (x(j, i) .ne. i + j + 3) call abort
+     end do
+  end do
+
+end program main
+
+! Check that only one loop is analyzed, and that it can be parallelized.
+! { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops" } }
+! { dg-final { scan-tree-dump-not "FAILED:" "parloops" } }
+! { dg-final { scan-tree-dump-times "parallelizing outer loop" 1 "parloops" } }
+
+! Check that the loop has been split off into a function.
+! { dg-final { scan-tree-dump-times "(?n);; Function main._loopfn.0 " 1 "optimized" } }
+
diff --git a/gcc/tree-parloops.c b/gcc/tree-parloops.c
index 036677b..4bfe588 100644
--- a/gcc/tree-parloops.c
+++ b/gcc/tree-parloops.c
@@ -2238,7 +2238,15 @@ gen_parallel_loop (struct loop *loop,
      increment) and immediately follows the loop exit test.  Attempt to move the
      entry of the loop directly before the exit check and increase the number of
      iterations of the loop by one.  */
-  if (!try_transform_to_exit_first_loop_alt (loop, reduction_list, nit))
+  if (try_transform_to_exit_first_loop_alt (loop, reduction_list, nit))
+    {
+      if (dump_file
+	  && (dump_flags & TDF_DETAILS))
+	fprintf (dump_file,
+		 "alternative exit-first loop transform succeeded"
+		 " for loop %d\n", loop->num);
+    }
+  else
     {
       /* Fall back on the method that handles more cases, but duplicates the
 	 loop body: move the exit condition of LOOP to the beginning of its
@@ -2508,7 +2516,7 @@ try_create_reduction_list (loop_p loop,
    otherwise.  */
 
 static bool
-parallelize_loops (void)
+parallelize_loops (bool reductions_only)
 {
   unsigned n_threads = flag_tree_parallelize_loops;
   bool changed = false;
@@ -2584,10 +2592,31 @@ parallelize_loops (void)
       if (!try_create_reduction_list (loop, &reduction_list))
 	continue;
 
-      if (!flag_loop_parallelize_all
-	  && !loop_parallel_p (loop, &parloop_obstack))
+      if (reductions_only
+	  && reduction_list.elements () == 0)
 	continue;
 
+      if (!flag_loop_parallelize_all)
+	{
+	  bool independent = false;
+
+	  if (!independent
+	      && loop->can_be_parallel)
+	    {
+	      if (dump_file
+		  && (dump_flags & TDF_DETAILS))
+		fprintf (dump_file,
+			 "  SUCCESS: may be parallelized, graphite analysis\n");
+	      independent = true;
+	    }
+
+	  if (!independent)
+	    independent = loop_parallel_p (loop, &parloop_obstack);
+
+	  if (!independent)
+	    continue;
+	}
+
       changed = true;
       if (dump_file && (dump_flags & TDF_DETAILS))
       {
@@ -2652,7 +2681,7 @@ pass_parallelize_loops::execute (function *fun)
   if (number_of_loops (fun) <= 1)
     return 0;
 
-  if (parallelize_loops ())
+  if (parallelize_loops (false))
     {
       fun->curr_properties &= ~(PROP_gimple_eomp);
       return TODO_update_ssa;
@@ -2668,3 +2697,57 @@ make_pass_parallelize_loops (gcc::context *ctxt)
 {
   return new pass_parallelize_loops (ctxt);
 }
+
+namespace {
+
+const pass_data pass_data_parallelize_reductions =
+{
+  GIMPLE_PASS, /* type */
+  "parloopsred", /* name */
+  OPTGROUP_LOOP, /* optinfo_flags */
+  TV_TREE_PARALLELIZE_LOOPS, /* tv_id */
+  ( PROP_cfg | PROP_ssa ), /* properties_required */
+  0, /* properties_provided */
+  0, /* properties_destroyed */
+  0, /* todo_flags_start */
+  0, /* todo_flags_finish */
+};
+
+class pass_parallelize_reductions : public gimple_opt_pass
+{
+public:
+  pass_parallelize_reductions (gcc::context *ctxt)
+    : gimple_opt_pass (pass_data_parallelize_reductions, ctxt)
+  {}
+
+  /* opt_pass methods: */
+  virtual bool gate (function *)
+  {
+    return (flag_tree_parallelize_loops > 1
+	    && !gate_graphite_transforms ());
+  }
+  virtual unsigned int execute (function *);
+}; // class pass_parallelize_reductions
+
+unsigned
+pass_parallelize_reductions::execute (function *fun)
+{
+  if (number_of_loops (fun) <= 1)
+    return 0;
+
+  if (parallelize_loops (true))
+    {
+      fun->curr_properties &= ~(PROP_gimple_eomp);
+      return TODO_update_ssa;
+    }
+
+  return 0;
+}
+
+} // anon namespace
+
+gimple_opt_pass *
+make_pass_parallelize_reductions (gcc::context *ctxt)
+{
+  return new pass_parallelize_reductions (ctxt);
+}
diff --git a/gcc/tree-pass.h b/gcc/tree-pass.h
index c47b22e..f0a7017 100644
--- a/gcc/tree-pass.h
+++ b/gcc/tree-pass.h
@@ -368,7 +368,9 @@ extern gimple_opt_pass *make_pass_scev_cprop (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_empty_loop (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_record_bounds (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_graphite (gcc::context *ctxt);
+extern gimple_opt_pass *make_pass_graphite_parloops (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_graphite_transforms (gcc::context *ctxt);
+extern gimple_opt_pass *make_pass_graphite_transforms2 (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_if_conversion (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_loop_distribution (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_vectorize (gcc::context *ctxt);
@@ -377,6 +379,7 @@ extern gimple_opt_pass *make_pass_slp_vectorize (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_complete_unroll (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_complete_unrolli (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_parallelize_loops (gcc::context *ctxt);
+extern gimple_opt_pass *make_pass_parallelize_reductions (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_loop_prefetch (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_iv_optimize (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_tree_loop_done (gcc::context *ctxt);
@@ -595,6 +598,8 @@ extern gimple_opt_pass *make_pass_update_address_taken (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_convert_switch (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_lower_vaarg (gcc::context *ctxt);
 
+extern bool gate_graphite_transforms (void);
+
 /* Current optimization pass.  */
 extern opt_pass *current_pass;
 
diff --git a/gcc/tree-ssa-loop-ivcanon.c b/gcc/tree-ssa-loop-ivcanon.c
index eca70a9..43724ed 100644
--- a/gcc/tree-ssa-loop-ivcanon.c
+++ b/gcc/tree-ssa-loop-ivcanon.c
@@ -1421,7 +1421,11 @@ public:
   {}
 
   /* opt_pass methods: */
-  virtual bool gate (function *) { return flag_tree_loop_ivcanon != 0; }
+  virtual bool gate (function *)
+  {
+    return (flag_tree_loop_ivcanon != 0
+	    && flag_tree_parallelize_loops <= 1);
+  }
   virtual unsigned int execute (function *fun);
 
 }; // class pass_iv_canon
-- 
1.9.1