2015-06-18 Richard Biener <rguenther@suse.de>

	PR tree-optimization/66510
	* tree-vect-stmts.c (vectorizable_load): Properly compute the
	number of vector loads for SLP permuted loads.
	* tree-vect-data-refs.c (vect_compute_data_ref_alignment): Also
	check the stride for loop vectorization.
	(vect_enhance_data_refs_alignment): Deal with SLP adjusted
	vectorization factor.
	(vect_analyze_group_access): If the group size is not a power
	of two require a epilogue loop.
	* tree-vect-loop.c (vect_analyze_loop_2): Move alignment
	compute and optimizing and alias test pruning after final
	vectorization factor computation.
	* tree-vect-slp.c (vect_build_slp_tree_1): Remove check on
	vector alignment.
	(vect_transform_slp_perm_load): Properly compute the original
	number of vector load stmts.

	* gcc.dg/vect/slp-perm-12.c: New testcase.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@224598 138bc75d-0d04-0410-961f-82ee72b054a4

1 files changed, 10 insertions, 34 deletions

diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index e44396af629..47d8a42474e 100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -485,9 +485,8 @@ vect_build_slp_tree_1 (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
   int icode;
   machine_mode optab_op2_mode;
   machine_mode vec_mode;
-  struct data_reference *first_dr;
   HOST_WIDE_INT dummy;
-  gimple first_load = NULL, prev_first_load = NULL, old_first_load = NULL;
+  gimple first_load = NULL, prev_first_load = NULL;
   tree cond;
 
   /* For every stmt in NODE find its def stmt/s.  */
@@ -785,7 +784,6 @@ vect_build_slp_tree_1 (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
                   return false;
                 }
 
-	      old_first_load = first_load;
               first_load = GROUP_FIRST_ELEMENT (vinfo_for_stmt (stmt));
               if (prev_first_load)
                 {
@@ -809,30 +807,6 @@ vect_build_slp_tree_1 (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo,
                 }
               else
                 prev_first_load = first_load;
-
-	      /* In some cases a group of loads is just the same load
-		 repeated N times.  Only analyze its cost once.  */
-              if (first_load == stmt && old_first_load != first_load)
-                {
-                  first_dr = STMT_VINFO_DATA_REF (vinfo_for_stmt (stmt));
-                  if (vect_supportable_dr_alignment (first_dr, false)
-                      == dr_unaligned_unsupported)
-                    {
-                      if (dump_enabled_p ())
-                        {
-                          dump_printf_loc (MSG_MISSED_OPTIMIZATION,
-					   vect_location, 
-					   "Build SLP failed: unsupported "
-					   "unaligned load ");
-                          dump_gimple_stmt (MSG_MISSED_OPTIMIZATION, TDF_SLIM,
-					    stmt, 0);
-                          dump_printf (MSG_MISSED_OPTIMIZATION, "\n");
-                        }
-		      /* Fatal mismatch.  */
-		      matches[0] = false;
-                      return false;
-                    }
-                }
            }
         } /* Grouped access.  */
       else
@@ -3201,6 +3175,11 @@ vect_transform_slp_perm_load (slp_tree node, vec<tree> dr_chain,
   bool needs_first_vector = false;
   machine_mode mode;
 
+  if (!STMT_VINFO_GROUPED_ACCESS (stmt_info))
+    return false;
+
+  stmt_info = vinfo_for_stmt (GROUP_FIRST_ELEMENT (stmt_info));
+
   mode = TYPE_MODE (vectype);
 
   if (!can_vec_perm_p (mode, false, NULL))
@@ -3226,8 +3205,10 @@ vect_transform_slp_perm_load (slp_tree node, vec<tree> dr_chain,
 
   /* The number of vector stmts to generate based only on SLP_NODE_INSTANCE
      unrolling factor.  */
-  orig_vec_stmts_num = group_size *
-                SLP_INSTANCE_UNROLLING_FACTOR (slp_node_instance) / nunits;
+  orig_vec_stmts_num
+    = (STMT_VINFO_GROUP_SIZE (stmt_info)
+       * SLP_INSTANCE_UNROLLING_FACTOR (slp_node_instance)
+       + nunits - 1) / nunits;
   if (orig_vec_stmts_num == 1)
     only_one_vec = true;
 
@@ -3235,11 +3216,6 @@ vect_transform_slp_perm_load (slp_tree node, vec<tree> dr_chain,
      relatively to SLP_NODE_INSTANCE unrolling factor.  */
   ncopies = vf / SLP_INSTANCE_UNROLLING_FACTOR (slp_node_instance);
 
-  if (!STMT_VINFO_GROUPED_ACCESS (stmt_info))
-    return false;
-
-  stmt_info = vinfo_for_stmt (GROUP_FIRST_ELEMENT (stmt_info));
-
   /* Generate permutation masks for every NODE. Number of masks for each NODE
      is equal to GROUP_SIZE.
      E.g., we have a group of three nodes with three loads from the same