target.h (struct vectorize): Add new target builtin.

	* target.h (struct vectorize): Add new target builtin.
	* tree-vectorizer.c (destroy_loop_vec_info): Call
	vect_free_slp_instance instead of vect_free_slp_node.
	* tree-vectorizer.h (enum slp_load_perm_type): New.
	(struct _slp_instance): Add new fields.
	(SLP_INSTANCE_LOAD_PERMUTATION): New.
	(SLP_INSTANCE_LOADS): New.
	(vect_free_slp_tree): Remove.
	(vect_free_slp_instance): Declare.
	(SLP_TREE_LOADS_PERM_TYPE, TARG_VEC_PERMUTE_COST): New.
	(vectorizable_load): Add argument.
	(vect_transform_slp_perm_load): New.
	* tree-vect-analyze.c (vect_analyze_operations): Add an argument to
	vectorizable_load.
	(vect_get_place_in_interleaving_chain): New function.
	(vect_free_slp_tree): Make static.
	(vect_free_slp_instance): New function.
	(vect_build_slp_tree): Add new arguments. Allow load permutations and
	collect the load location in the interleaving chain.
	(vect_supported_slp_permutation_p): New function.
	(vect_supported_load_permutation_p): Likewise.
	(vect_analyze_slp_instance): In case of loads permutation, call
	vect_supported_load_permutation_p to check that the permutation is
	supported.
	* target-def.h (TARGET_VECTORIZE_BUILTIN_VEC_PERM): New.
	* tree-vect-transform.c (vect_transform_stmt): Add new argument.
	(vect_create_mask_and_perm): New function.
	(vect_get_mask_element, vect_transform_slp_perm_load): Likewise.
	(vectorizable_load): Add an argument. Don't keep the created vectors
	statements in the node if permutation is required. Call
	vect_transform_slp_perm_load to generate the permutation.
	(vect_transform_stmt): Add new argument. Call vectorizable_load with
	additional argument.
	(vect_schedule_slp_instance): In case of loads permutation, allocate
	vectorized statements structure for all the related SLP nodes. Call
	vect_transform_stmt with addditional argument.
	(vect_transform_loop): Call vect_transform_stmt with correct arguments.
	* config/spu/spu.c (spu_builtin_vec_perm): New.
	(TARGET_VECTORIZE_BUILTIN_VEC_PERM): Redefine.
	* config/spu/spu.h (TARG_VEC_PERMUTE_COS): Define.
	* config/rs6000/rs6000.c (rs6000_builtin_vec_perm): New.
	(TARGET_VECTORIZE_BUILTIN_VEC_PERM): Redefine.

From-SVN: r139706

1 files changed, 21 insertions, 2 deletions

diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 10e7aa3..678dc59 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -105,6 +105,8 @@ typedef struct _slp_tree {
   } cost;
 } *slp_tree;
 
+DEF_VEC_P(slp_tree);
+DEF_VEC_ALLOC_P(slp_tree, heap);
 
 /* SLP instance is a sequence of stmts in a loop that can be packed into
    SIMD stmts.  */
@@ -124,6 +126,13 @@ typedef struct _slp_instance {
     int outside_of_loop;     /* Statements generated outside loop.  */
     int inside_of_loop;      /* Statements generated inside loop.  */
   } cost;
+
+  /* Loads permutation relatively to the stores, NULL if there is no 
+     permutation.  */
+  VEC (int, heap) *load_permutation;
+
+  /* The group of nodes that contain loads of this SLP instance.  */
+  VEC (slp_tree, heap) *loads;
 } *slp_instance;
 
 DEF_VEC_P(slp_instance);
@@ -135,6 +144,8 @@ DEF_VEC_ALLOC_P(slp_instance, heap);
 #define SLP_INSTANCE_UNROLLING_FACTOR(S)         (S)->unrolling_factor
 #define SLP_INSTANCE_OUTSIDE_OF_LOOP_COST(S)     (S)->cost.outside_of_loop
 #define SLP_INSTANCE_INSIDE_OF_LOOP_COST(S)      (S)->cost.inside_of_loop
+#define SLP_INSTANCE_LOAD_PERMUTATION(S)         (S)->load_permutation
+#define SLP_INSTANCE_LOADS(S)                    (S)->loads
 
 #define SLP_TREE_LEFT(S)                         (S)->left
 #define SLP_TREE_RIGHT(S)                        (S)->right
@@ -522,6 +533,11 @@ typedef struct _stmt_vec_info {
 #define TARG_VEC_STORE_COST          1
 #endif
 
+/* Cost of vector permutation.  */
+#ifndef TARG_VEC_PERMUTE_COST
+#define TARG_VEC_PERMUTE_COST          1
+#endif
+
 /* The maximum number of intermediate steps required in multi-step type
    conversion.  */
 #define MAX_INTERM_CVT_STEPS         3
@@ -700,7 +716,7 @@ extern void free_stmt_vec_info (gimple stmt);
 /** In tree-vect-analyze.c  **/
 /* Driver for analysis stage.  */
 extern loop_vec_info vect_analyze_loop (struct loop *);
-extern void vect_free_slp_tree (slp_tree);
+extern void vect_free_slp_instance (slp_instance);
 extern loop_vec_info vect_analyze_loop_form (struct loop *);
 extern tree vect_get_smallest_scalar_type (gimple, HOST_WIDE_INT *, 
                                            HOST_WIDE_INT *);
@@ -716,7 +732,7 @@ void vect_pattern_recog (loop_vec_info);
 
 /** In tree-vect-transform.c  **/
 extern bool vectorizable_load (gimple, gimple_stmt_iterator *, gimple *,
-			       slp_tree);
+			       slp_tree, slp_instance);
 extern bool vectorizable_store (gimple, gimple_stmt_iterator *, gimple *,
 				slp_tree);
 extern bool vectorizable_operation (gimple, gimple_stmt_iterator *, gimple *,
@@ -742,6 +758,9 @@ extern void vect_model_simple_cost (stmt_vec_info, int, enum vect_def_type *,
 extern void vect_model_store_cost (stmt_vec_info, int, enum vect_def_type, 
 				   slp_tree);
 extern void vect_model_load_cost (stmt_vec_info, int, slp_tree);
+extern bool vect_transform_slp_perm_load (gimple, VEC (tree, heap) *, 
+                             gimple_stmt_iterator *, int, slp_instance, bool);
+
 /* Driver for transformation stage.  */
 extern void vect_transform_loop (loop_vec_info);