diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 93022ad89cb..ff4534683c3 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,8 @@
+2016-07-05  Richard Biener  <rguenther@suse.de>
+
+	* tree-loop-distribution.c (distribute_loop): Fix issue with
+	the cost model loop.
+
 2016-07-05  Christophe Lyon  <christophe.lyon@linaro.org>
 
 	* config/arm/neon-testgen.ml: Delete.
diff --git a/gcc/tree-loop-distribution.c b/gcc/tree-loop-distribution.c
index e4163b274ff..9bca56a9b6f 100644
--- a/gcc/tree-loop-distribution.c
+++ b/gcc/tree-loop-distribution.c
@@ -1504,6 +1504,7 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
      memory accesses.  */
   for (i = 0; partitions.iterate (i, &into); ++i)
     {
+      bool changed = false;
       if (partition_builtin_p (into))
 	continue;
       for (int j = i + 1;
@@ -1524,8 +1525,15 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
 	      partitions.unordered_remove (j);
 	      partition_free (partition);
 	      j--;
+	      changed = true;
 	    }
 	}
+      /* If we fused 0 1 2 in step 1 to 0,2 1 as 0 and 2 have similar
+         accesses when 1 and 2 have similar accesses but not 0 and 1
+	 then in the next iteration we will fail to consider merging
+	 1 into 0,2.  So try again if we did any merging into 0.  */
+      if (changed)
+	i--;
     }
 
   /* Build the partition dependency graph.  */