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.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@158506 138bc75d-0d04-0410-961f-82ee72b054a4

1 files changed, 7 insertions, 2 deletions

diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 52b2a7ec59f..bd43a4bc173 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -242,6 +242,9 @@ typedef struct _loop_vec_info {
   /* The unrolling factor needed to SLP the loop. In case of that pure SLP is
      applied to the loop, i.e., no unrolling is needed, this is 1.  */
   unsigned slp_unrolling_factor;
+
+  /* Reduction cycles detected in the loop. Used in loop-aware SLP.  */
+  VEC (gimple, heap) *reductions;
 } *loop_vec_info;
 
 /* Access Functions.  */
@@ -266,6 +269,7 @@ typedef struct _loop_vec_info {
 #define LOOP_VINFO_STRIDED_STORES(L)       (L)->strided_stores
 #define LOOP_VINFO_SLP_INSTANCES(L)        (L)->slp_instances
 #define LOOP_VINFO_SLP_UNROLLING_FACTOR(L) (L)->slp_unrolling_factor
+#define LOOP_VINFO_REDUCTIONS(L)           (L)->reductions
 
 #define LOOP_REQUIRES_VERSIONING_FOR_ALIGNMENT(L) \
 VEC_length (gimple, (L)->may_misalign_stmts) > 0
@@ -844,7 +848,8 @@ extern void vect_transform_loop (loop_vec_info);
 extern loop_vec_info vect_analyze_loop_form (struct loop *);
 extern bool vectorizable_live_operation (gimple, gimple_stmt_iterator *,
                                          gimple *);
-extern bool vectorizable_reduction (gimple, gimple_stmt_iterator *, gimple *);
+extern bool vectorizable_reduction (gimple, gimple_stmt_iterator *, gimple *,
+                                    slp_tree);
 extern bool vectorizable_induction (gimple, gimple_stmt_iterator *, gimple *);
 extern int vect_estimate_min_profitable_iters (loop_vec_info);
 extern tree get_initial_def_for_reduction (gimple, tree, tree *);
@@ -862,7 +867,7 @@ extern bool vect_analyze_slp (loop_vec_info, bb_vec_info);
 extern void vect_make_slp_decision (loop_vec_info);
 extern void vect_detect_hybrid_slp (loop_vec_info);
 extern void vect_get_slp_defs (slp_tree, VEC (tree,heap) **,
-                               VEC (tree,heap) **);
+                               VEC (tree,heap) **, int);
 extern LOC find_bb_location (basic_block);
 extern bb_vec_info vect_slp_analyze_bb (basic_block);
 extern void vect_slp_transform_bb (basic_block);