tm.texi.in (TARGET_VECTORIZE_BUILTIN_VECTORIZATION_COST): Document new arguments.

	* doc/tm.texi.in (TARGET_VECTORIZE_BUILTIN_VECTORIZATION_COST):
	Document new arguments.
	* doc/tm.texi: Regenerate.
	* targhooks.c (default_builtin_vectorization_cost): Add new arguments.
	Handle unaligned store.
	* targhooks.h (default_builtin_vectorization_cost): Add new arguments.
	* target.def (builtin_vectorization_cost): Add new arguments.
	* target.h (enum vect_cost_for_stmt): Add unaligned_store.
	* tree-vect-loop-manip.c (vect_gen_niters_for_prolog_loop): Take number
	of iterations of prolog loop directly from LOOP_PEELING_FOR_ALIGNMENT.
	(vect_vfa_segment_size): Fix indentation.
	* tree-vectorizer.h (struct _vect_peel_info): New.
	(struct _vect_peel_extended_info): New.
	(struct _loop_vec_info): Add new field for peeling hash table and a
	macro for its access.
	(VECT_MAX_COST): Define.
	(vect_get_load_cost): Declare.
	(vect_get_store_cost, vect_get_known_peeling_cost, 
	vect_get_single_scalar_iteraion_cost): Likewise.
	(vect_supportable_dr_alignment): Add new argument.
	* tree-vect-loop.c (new_loop_vec_info): Initialize peeling hash table
	field.
	(destroy_loop_vec_info): Free peeling hash table.
	(vect_analyze_loop_form): Update call to builtin_vectorization_cost.
	(vect_analyze_loop): Move vect_enhance_data_refs_alignment before
	vect_analyze_slp. Fix indentation.
	(vect_get_single_scalar_iteraion_cost): New function.
	(vect_get_known_peeling_cost): Likewise.
	(vect_estimate_min_profitable_iters): Rename byte_misalign to npeel. 
	Call vect_get_single_scalar_iteraion_cost instead of cost_for_stmt per 
	statement. Move outside cost calculation inside unknown peeling case.
	Call vect_get_known_peeling_cost for known amount of peeling.
	* tree-vect-data-refs.c (vect_compute_data_ref_alignment): Add data
	reference to the print message of forced alignment.
	(vect_verify_datarefs_alignment): Update call to 
	vect_supportable_dr_alignment.
	(vect_get_data_access_cost): New function.
	(vect_peeling_hash, vect_peeling_hash_eq, vect_peeling_hash_insert,
	vect_peeling_hash_get_most_frequent, vect_peeling_hash_get_lowest_cost,
	vect_peeling_hash_choose_best_peeling): Likewise.
	(vect_enhance_data_refs_alignment): Fix documentation. Use hash table
	to store all the accesses in the loop and find best possible access to
	align using peeling for known alignment case. For unknown alignment
	check if stores are preferred or if peeling is worthy.
	(vect_find_same_alignment_drs): Analyze pairs of loads too.
	(vect_supportable_dr_alignment): Add new argument and check aligned
	accesses according to it. 
	* tree-vect-stmts.c (vect_get_stmt_cost): New function.
	(cost_for_stmt): Call vect_get_stmt_cost. 
	(vect_model_simple_cost): Likewise.
	(vect_model_store_cost): Call vect_get_stmt_cost. Call 
	vect_get_store_cost to calculate the cost of the statement.
	(vect_get_store_cost): New function.
	(vect_model_load_cost): Call vect_get_stmt_cost. Call 
	vect_get_load_cost to calculate the cost of the statement.
	(vect_get_load_cost): New function.
	(vectorizable_store): Update call to vect_supportable_dr_alignment.
	(vectorizable_load): Likewise.
	* config/spu/spu.c (spu_builtin_vectorization_cost): Add new
	arguments. 
	* config/i386/i386.c (ix86_builtin_vectorization_cost): Add new
	arguments. Handle unaligned store.
	* config/rs6000/rs6000.c (rs6000_builtin_vectorization_cost): New.
	(rs6000_builtin_support_vector_misalignment): Return true for word and
	double word alignments for VSX.
	* tree-vect-slp.c (vect_build_slp_tree): Update calls to 
	vect_supportable_dr_alignment and builtin_vectorization_cost.


Co-Authored-By: Revital Eres <eres@il.ibm.com>

From-SVN: r161797

1 files changed, 28 insertions, 2 deletions

diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index bf6769c..ed8ff58 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -170,6 +170,21 @@ DEF_VEC_ALLOC_P(slp_instance, heap);
 #define SLP_TREE_OUTSIDE_OF_LOOP_COST(S)         (S)->cost.outside_of_loop
 #define SLP_TREE_INSIDE_OF_LOOP_COST(S)          (S)->cost.inside_of_loop
 
+
+typedef struct _vect_peel_info
+{
+  int npeel;
+  struct data_reference *dr;
+  unsigned int count;
+} *vect_peel_info;
+
+typedef struct _vect_peel_extended_info
+{
+  struct _vect_peel_info peel_info;
+  unsigned int inside_cost;
+  unsigned int outside_cost;
+} *vect_peel_extended_info;
+
 /*-----------------------------------------------------------------*/
 /* Info on vectorized loops.                                       */
 /*-----------------------------------------------------------------*/
@@ -245,6 +260,10 @@ typedef struct _loop_vec_info {
 
   /* Reduction cycles detected in the loop. Used in loop-aware SLP.  */
   VEC (gimple, heap) *reductions;
+
+  /* Hash table used to choose the best peeling option.  */
+  htab_t peeling_htab;
+
 } *loop_vec_info;
 
 /* Access Functions.  */
@@ -270,6 +289,7 @@ typedef struct _loop_vec_info {
 #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_VINFO_PEELING_HTAB(L)         (L)->peeling_htab
 
 #define LOOP_REQUIRES_VERSIONING_FOR_ALIGNMENT(L) \
 VEC_length (gimple, (L)->may_misalign_stmts) > 0
@@ -543,6 +563,8 @@ typedef struct _stmt_vec_info {
 #define PURE_SLP_STMT(S)                  ((S)->slp_type == pure_slp)
 #define STMT_SLP_TYPE(S)                   (S)->slp_type
 
+#define VECT_MAX_COST 1000
+
 /* The maximum number of intermediate steps required in multi-step type
    conversion.  */
 #define MAX_INTERM_CVT_STEPS         3
@@ -743,11 +765,14 @@ extern void vect_remove_stores (gimple);
 extern bool vect_analyze_stmt (gimple, bool *, slp_tree);
 extern bool vectorizable_condition (gimple, gimple_stmt_iterator *, gimple *,
                                     tree, int);
+extern void vect_get_load_cost (struct data_reference *, int, bool,
+                                unsigned int *, unsigned int *);
+extern void vect_get_store_cost (struct data_reference *, int, unsigned int *);
 
 /* In tree-vect-data-refs.c.  */
 extern bool vect_can_force_dr_alignment_p (const_tree, unsigned int);
 extern enum dr_alignment_support vect_supportable_dr_alignment
-                                           (struct data_reference *);
+                                           (struct data_reference *, bool);
 extern tree vect_get_smallest_scalar_type (gimple, HOST_WIDE_INT *,
                                            HOST_WIDE_INT *);
 extern bool vect_analyze_data_ref_dependences (loop_vec_info, bb_vec_info,
@@ -795,7 +820,8 @@ 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 *);
 extern int vect_min_worthwhile_factor (enum tree_code);
-
+extern int vect_get_known_peeling_cost (loop_vec_info, int, int *, int);
+extern int vect_get_single_scalar_iteraion_cost (loop_vec_info);
 
 /* In tree-vect-slp.c.  */
 extern void vect_free_slp_instance (slp_instance);