Handle 2 preds for fin_bb in expand_omp_for_static_chunk

2015-08-31  Tom de Vries  <tom@codesourcery.com>

	PR tree-optimization/65637
	* omp-low.c (expand_omp_for_static_chunk): Handle case that fin_bb has 2
	predecessors.

	* gcc.dg/autopar/reduc-3-chunk-size.c: New test.
---
 gcc/ChangeLog                                     |  6 +++
 gcc/omp-low.c                                     | 26 +++++++----
 gcc/testsuite/gcc.dg/autopar/reduc-3-chunk-size.c | 56 +++++++++++++++++++++++
 3 files changed, 79 insertions(+), 9 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/autopar/reduc-3-chunk-size.c

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index a14564c..c9e426f 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,6 +1,12 @@
 2015-05-18  Tom de Vries  <tom@codesourcery.com>
 
 	PR tree-optimization/65637
+	* omp-low.c (expand_omp_for_static_chunk): Handle case that fin_bb has 2
+	predecessors.
+
+2015-05-18  Tom de Vries  <tom@codesourcery.com>
+
+	PR tree-optimization/65637
 	* omp-low.c (find_phi_with_arg_on_edge): New function.
 	(expand_omp_for_static_chunk): Fix inner loop phi.
 
diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index e2be7c7..f3257ac 100644
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -7033,7 +7033,7 @@ expand_omp_for_static_chunk (struct omp_region *region,
       se->probability = REG_BR_PROB_BASE / 2000 - 1;
       if (gimple_in_ssa_p (cfun))
 	{
-	  int dest_idx = find_edge (entry_bb, fin_bb)->dest_idx;
+	  int dest_idx = find_edge (iter_part_bb, fin_bb)->dest_idx;
 	  for (gphi_iterator gpi = gsi_start_phis (fin_bb);
 	       !gsi_end_p (gpi); gsi_next (&gpi))
 	    {
@@ -7314,7 +7314,7 @@ expand_omp_for_static_chunk (struct omp_region *region,
       /* When we redirect the edge from trip_update_bb to iter_part_bb, we
 	 remove arguments of the phi nodes in fin_bb.  We need to create
 	 appropriate phi nodes in iter_part_bb instead.  */
-      se = single_pred_edge (fin_bb);
+      se = find_edge (iter_part_bb, fin_bb);
       re = single_succ_edge (trip_update_bb);
       vec<edge_var_map> *head = redirect_edge_var_map_vector (re);
       ene = single_succ_edge (entry_bb);
@@ -7329,6 +7329,10 @@ expand_omp_for_static_chunk (struct omp_region *region,
 	  phi = psi.phi ();
 	  t = gimple_phi_result (phi);
 	  gcc_assert (t == redirect_edge_var_map_result (vm));
+
+	  if (!single_pred_p (fin_bb))
+	    t = copy_ssa_name (t, phi);
+
 	  nphi = create_phi_node (t, iter_part_bb);
 
 	  t = PHI_ARG_DEF_FROM_EDGE (phi, se);
@@ -7353,16 +7357,20 @@ expand_omp_for_static_chunk (struct omp_region *region,
 	  gcc_assert (inner_loop_phi != NULL);
 	  add_phi_arg (inner_loop_phi, gimple_phi_result (nphi),
 		       find_edge (seq_start_bb, body_bb), locus);
+
+	  if (!single_pred_p (fin_bb))
+	    add_phi_arg (phi, gimple_phi_result (nphi), se, locus);
 	}
       gcc_assert (gsi_end_p (psi) && (head == NULL || i == head->length ()));
       redirect_edge_var_map_clear (re);
-      while (1)
-	{
-	  psi = gsi_start_phis (fin_bb);
-	  if (gsi_end_p (psi))
-	    break;
-	  remove_phi_node (&psi, false);
-	}
+      if (single_pred_p (fin_bb))
+	while (1)
+	  {
+	    psi = gsi_start_phis (fin_bb);
+	    if (gsi_end_p (psi))
+	      break;
+	    remove_phi_node (&psi, false);
+	  }
 
       /* Make phi node for trip.  */
       phi = create_phi_node (trip_main, iter_part_bb);
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-3-chunk-size.c b/gcc/testsuite/gcc.dg/autopar/reduc-3-chunk-size.c
new file mode 100644
index 0000000..ca4ab2f
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-3-chunk-size.c
@@ -0,0 +1,56 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops-details -fdump-tree-optimized --param parloops-chunk-size=100" } */
+
+#include <stdarg.h>
+#include <stdlib.h>
+
+#define N 1600
+
+unsigned int ub[N];
+unsigned int uc[N];
+
+/* Reduction of unsigned-int.  */
+
+int __attribute__ ((noinline))
+main1 (int n, int res)
+{
+  int i;
+  unsigned int udiff;
+
+  udiff = 0;
+  for (i = 0; i < n; i++) {
+    udiff += (ub[i] - uc[i]);
+  }
+
+  /* check results:  */
+  if (udiff != res)
+    abort ();
+
+  return 0;
+}
+
+void __attribute__((noinline))
+init_arrays ()
+{
+  int i;
+
+  for (i = 0; i < N; i++)
+    {
+      ub[i] = i * 3;
+      uc[i] = i;
+    }
+}
+
+int
+main (void)
+{
+  init_arrays ();
+  main1 (N, 2558400);
+  main1 (N-1, 2555202);
+  return 0;
+}
+
+
+/* { dg-final { scan-tree-dump-times "Detected reduction" 1 "parloops" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloops" } } */
+
-- 
1.9.1