re PR tree-optimization/37027 (SLP loop vectorization missing support for reductions)

	PR tree-optimization/37027
	* tree-vectorizer.h (struct _loop_vec_info): Add new field reductions 
	and macro to access it.
	(vectorizable_reduction): Add argument.
	(vect_get_slp_defs): Likewise.
	* tree-vect-loop.c (vect_analyze_scalar_cycles_1): Collect reduction
	statements for possible use in SLP.
	(new_loop_vec_info): Initialize LOOP_VINFO_REDUCTIONS.
	(destroy_loop_vec_info): Free LOOP_VINFO_REDUCTIONS.
	(vect_create_epilog_for_reduction): Handle SLP. Modify documentation,
	add new argument.
	(vectorizable_reduction): Likewise.
	* tree-vect-stmts.c (vect_get_vec_defs): Update call to 
	vect_get_slp_defs.
	(vectorizable_type_demotion, vectorizable_type_promotion,
	vectorizable_store): Likewise.
	(vect_analyze_stmt): Update call to vectorizable_reduction.
	(vect_transform_stmt): Likewise.
	* tree-vect-slp.c (vect_get_and_check_slp_defs): Handle reduction.
	(vect_build_slp_tree): Fix indentation. Check that there are no loads
	from different interleaving chains in same node.
	(vect_slp_rearrange_stmts): New function.
	(vect_supported_load_permutation_p): Allow load permutations for 
	reductions. Call vect_slp_rearrange_stmts() to rearrange statements
	inside SLP nodes if necessary.
	(vect_analyze_slp_instance): Handle reductions.
	(vect_analyze_slp): Try to build SLP instances originating from groups
	of reductions.
	(vect_detect_hybrid_slp_stmts): Skip reduction statements.
	(vect_get_constant_vectors): Create initial vectors for reductions
	according to reduction code. Add new argument.
	(vect_get_slp_defs): Add new argument, pass it to 
	vect_get_constant_vectors.
	(vect_schedule_slp_instance): Remove SLP tree root statements.

From-SVN: r158506

1 files changed, 6 insertions, 7 deletions

diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 4868f73..988749b 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -1134,7 +1134,7 @@ vect_get_vec_defs (tree op0, tree op1, gimple stmt,
 		   slp_tree slp_node)
 {
   if (slp_node)
-    vect_get_slp_defs (slp_node, vec_oprnds0, vec_oprnds1);
+    vect_get_slp_defs (slp_node, vec_oprnds0, vec_oprnds1, -1);
   else
     {
       tree vec_oprnd;
@@ -2519,7 +2519,7 @@ vectorizable_type_demotion (gimple stmt, gimple_stmt_iterator *gsi,
     {
       /* Handle uses.  */
       if (slp_node)
-        vect_get_slp_defs (slp_node, &vec_oprnds0, NULL);
+        vect_get_slp_defs (slp_node, &vec_oprnds0, NULL, -1);
       else
         {
           VEC_free (tree, heap, vec_oprnds0);
@@ -2819,7 +2819,7 @@ vectorizable_type_promotion (gimple stmt, gimple_stmt_iterator *gsi,
       if (j == 0)
         {
           if (slp_node)
-              vect_get_slp_defs (slp_node, &vec_oprnds0, &vec_oprnds1);
+              vect_get_slp_defs (slp_node, &vec_oprnds0, &vec_oprnds1, -1);
           else
             {
               vec_oprnd0 = vect_get_vec_def_for_operand (op0, stmt, NULL);
@@ -3105,7 +3105,7 @@ vectorizable_store (gimple stmt, gimple_stmt_iterator *gsi, gimple *vec_stmt,
           if (slp)
             {
 	      /* Get vectorized arguments for SLP_NODE.  */
-              vect_get_slp_defs (slp_node, &vec_oprnds, NULL);
+              vect_get_slp_defs (slp_node, &vec_oprnds, NULL, -1);
 
               vec_oprnd = VEC_index (tree, vec_oprnds, 0);
             }
@@ -4049,7 +4049,7 @@ vect_analyze_stmt (gimple stmt, bool *need_to_vectorize, slp_tree node)
             || vectorizable_load (stmt, NULL, NULL, NULL, NULL)
             || vectorizable_call (stmt, NULL, NULL)
             || vectorizable_store (stmt, NULL, NULL, NULL)
-            || vectorizable_reduction (stmt, NULL, NULL)
+            || vectorizable_reduction (stmt, NULL, NULL, NULL)
             || vectorizable_condition (stmt, NULL, NULL, NULL, 0));
     else
       {
@@ -4201,8 +4201,7 @@ vect_transform_stmt (gimple stmt, gimple_stmt_iterator *gsi,
       break;
 
     case reduc_vec_info_type:
-      gcc_assert (!slp_node);
-      done = vectorizable_reduction (stmt, gsi, &vec_stmt);
+      done = vectorizable_reduction (stmt, gsi, &vec_stmt, slp_node);
       gcc_assert (done);
       break;