/* Vectorizer
- Copyright (C) 2003-2019 Free Software Foundation, Inc.
+ Copyright (C) 2003-2020 Free Software Foundation, Inc.
Contributed by Dorit Naishlos <dorit@il.ibm.com>
This file is part of GCC.
#include "tree-data-ref.h"
#include "tree-hash-traits.h"
#include "target.h"
+#include <utility>
/* Used for naming of new temporaries. */
enum vect_var_kind {
vec<slp_tree> children;
/* A group of scalar stmts to be vectorized together. */
vec<stmt_vec_info> stmts;
+ /* A group of scalar operands to be vectorized together. */
+ vec<tree> ops;
/* Load permutation relative to the stores, NULL if there is no
permutation. */
vec<unsigned> load_permutation;
/* The root of SLP tree. */
slp_tree root;
+ /* For vector constructors, the constructor stmt that the SLP tree is built
+ from, NULL otherwise. */
+ stmt_vec_info root_stmt;
+
/* Size of groups of scalar stmts that will be replaced by SIMD stmt/s. */
unsigned int group_size;
#define SLP_INSTANCE_GROUP_SIZE(S) (S)->group_size
#define SLP_INSTANCE_UNROLLING_FACTOR(S) (S)->unrolling_factor
#define SLP_INSTANCE_LOADS(S) (S)->loads
+#define SLP_INSTANCE_ROOT_STMT(S) (S)->root_stmt
#define SLP_TREE_CHILDREN(S) (S)->children
#define SLP_TREE_SCALAR_STMTS(S) (S)->stmts
+#define SLP_TREE_SCALAR_OPS(S) (S)->ops
#define SLP_TREE_VEC_STMTS(S) (S)->vec_stmts
#define SLP_TREE_NUMBER_OF_VEC_STMTS(S) (S)->vec_stmts_size
#define SLP_TREE_LOAD_PERMUTATION(S) (S)->load_permutation
#define SLP_TREE_TWO_OPERATORS(S) (S)->two_operators
#define SLP_TREE_DEF_TYPE(S) (S)->def_type
+/* Key for map that records association between
+ scalar conditions and corresponding loop mask, and
+ is populated by vect_record_loop_mask. */
+
+struct scalar_cond_masked_key
+{
+ scalar_cond_masked_key (tree t, unsigned ncopies_)
+ : ncopies (ncopies_)
+ {
+ get_cond_ops_from_tree (t);
+ }
+
+ void get_cond_ops_from_tree (tree);
+
+ unsigned ncopies;
+ tree_code code;
+ tree op0;
+ tree op1;
+};
+
+template<>
+struct default_hash_traits<scalar_cond_masked_key>
+{
+ typedef scalar_cond_masked_key compare_type;
+ typedef scalar_cond_masked_key value_type;
+
+ static inline hashval_t
+ hash (value_type v)
+ {
+ inchash::hash h;
+ h.add_int (v.code);
+ inchash::add_expr (v.op0, h, 0);
+ inchash::add_expr (v.op1, h, 0);
+ h.add_int (v.ncopies);
+ return h.end ();
+ }
+
+ static inline bool
+ equal (value_type existing, value_type candidate)
+ {
+ return (existing.ncopies == candidate.ncopies
+ && existing.code == candidate.code
+ && operand_equal_p (existing.op0, candidate.op0, 0)
+ && operand_equal_p (existing.op1, candidate.op1, 0));
+ }
+
+ static inline void
+ mark_empty (value_type &v)
+ {
+ v.ncopies = 0;
+ }
+
+ static inline bool
+ is_empty (value_type v)
+ {
+ return v.ncopies == 0;
+ }
+
+ static inline void mark_deleted (value_type &) {}
+
+ static inline bool is_deleted (const value_type &)
+ {
+ return false;
+ }
+
+ static inline void remove (value_type &) {}
+};
+typedef hash_set<scalar_cond_masked_key> scalar_cond_masked_set_type;
/* Describes two objects whose addresses must be unequal for the vectorized
loop to be valid. */
/* Vectorizer state common between loop and basic-block vectorization. */
class vec_info {
public:
+ typedef hash_set<int_hash<machine_mode, E_VOIDmode, E_BLKmode> > mode_set;
enum vec_kind { bb, loop };
vec_info (vec_kind, void *, vec_info_shared *);
/* Cost data used by the target cost model. */
void *target_cost_data;
+ /* The set of vector modes used in the vectorized region. */
+ mode_set used_vector_modes;
+
+ /* The argument we should pass to related_vector_mode when looking up
+ the vector mode for a scalar mode, or VOIDmode if we haven't yet
+ made any decisions about which vector modes to use. */
+ machine_mode vector_mode;
+
private:
stmt_vec_info new_stmt_vec_info (gimple *stmt);
void set_vinfo_for_stmt (gimple *, stmt_vec_info);
typedef auto_vec<rgroup_masks> vec_loop_masks;
+typedef auto_vec<std::pair<data_reference*, tree> > drs_init_vec;
+
/*-----------------------------------------------------------------*/
/* Info on vectorized loops. */
/*-----------------------------------------------------------------*/
/* Threshold of number of iterations below which vectorization will not be
performed. It is calculated from MIN_PROFITABLE_ITERS and
- PARAM_MIN_VECT_LOOP_BOUND. */
+ param_min_vect_loop_bound. */
unsigned int th;
/* When applying loop versioning, the vector form should only be used
on inactive scalars. */
vec_loop_masks masks;
+ /* Set of scalar conditions that have loop mask applied. */
+ scalar_cond_masked_set_type scalar_cond_masked_set;
+
/* If we are using a loop mask to align memory addresses, this variable
contains the number of vector elements that we should skip in the
first iteration of the vector loop (i.e. the number of leading
/* Cost of a single scalar iteration. */
int single_scalar_iteration_cost;
+ /* The cost of the vector prologue and epilogue, including peeled
+ iterations and set-up code. */
+ int vec_outside_cost;
+
+ /* The cost of the vector loop body. */
+ int vec_inside_cost;
+
/* Is the loop vectorizable? */
bool vectorizable;
this points to the original vectorized loop. Otherwise NULL. */
_loop_vec_info *orig_loop_info;
+ /* Used to store loop_vec_infos of epilogues of this loop during
+ analysis. */
+ vec<_loop_vec_info *> epilogue_vinfos;
+
} *loop_vec_info;
/* Access Functions. */
for loop vectorization. */
vect_memory_access_type memory_access_type;
- /* For CONST_COND_REDUCTION and INTEGER_INDUC_COND_REDUCTION, the
- reduction code. */
- enum tree_code cond_reduc_code;
-
/* For INTEGER_INDUC_COND_REDUCTION, the initial value to be used. */
tree induc_cond_initial_val;
/* The vector input type relevant for reduction vectorization. */
tree reduc_vectype_in;
+ /* The vector type for performing the actual reduction. */
+ tree reduc_vectype;
+
/* Whether we force a single cycle PHI during reduction vectorization. */
bool force_single_cycle;
unsigned int operation_precision;
signop operation_sign;
+ /* If the statement produces a boolean result, this value describes
+ how we should choose the associated vector type. The possible
+ values are:
+
+ - an integer precision N if we should use the vector mask type
+ associated with N-bit integers. This is only used if all relevant
+ input booleans also want the vector mask type for N-bit integers,
+ or if we can convert them into that form by pattern-matching.
+
+ - ~0U if we considered choosing a vector mask type but decided
+ to treat the boolean as a normal integer type instead.
+
+ - 0 otherwise. This means either that the operation isn't one that
+ could have a vector mask type (and so should have a normal vector
+ type instead) or that we simply haven't made a choice either way. */
+ unsigned int mask_precision;
+
/* True if this is only suitable for SLP vectorization. */
bool slp_vect_only_p;
};
#define STMT_VINFO_STRIDED_P(S) (S)->strided_p
#define STMT_VINFO_MEMORY_ACCESS_TYPE(S) (S)->memory_access_type
#define STMT_VINFO_SIMD_LANE_ACCESS_P(S) (S)->simd_lane_access_p
-#define STMT_VINFO_VEC_COND_REDUC_CODE(S) (S)->cond_reduc_code
#define STMT_VINFO_VEC_INDUC_COND_INITIAL_VAL(S) (S)->induc_cond_initial_val
#define STMT_VINFO_REDUC_EPILOGUE_ADJUSTMENT(S) (S)->reduc_epilogue_adjustment
#define STMT_VINFO_REDUC_IDX(S) (S)->reduc_idx
#define STMT_VINFO_REDUC_CODE(S) (S)->reduc_code
#define STMT_VINFO_REDUC_FN(S) (S)->reduc_fn
#define STMT_VINFO_REDUC_DEF(S) (S)->reduc_def
+#define STMT_VINFO_REDUC_VECTYPE(S) (S)->reduc_vectype
#define STMT_VINFO_REDUC_VECTYPE_IN(S) (S)->reduc_vectype_in
#define STMT_VINFO_SLP_VECT_ONLY(S) (S)->slp_vect_only_p
&& (loop->inner == (gimple_bb (stmt_info->stmt))->loop_father));
}
+/* Return true if STMT_INFO should produce a vector mask type rather than
+ a normal nonmask type. */
+
+static inline bool
+vect_use_mask_type_p (stmt_vec_info stmt_info)
+{
+ return stmt_info->mask_precision && stmt_info->mask_precision != ~0U;
+}
+
/* Return TRUE if a statement represented by STMT_INFO is a part of a
pattern. */
static inline void
vect_update_max_nunits (poly_uint64 *max_nunits, poly_uint64 nunits)
{
- /* All unit counts have the form current_vector_size * X for some
+ /* All unit counts have the form vec_info::vector_size * X for some
rational X, so two unit sizes must have a common multiple.
Everything is a multiple of the initial value of 1. */
*max_nunits = force_common_multiple (*max_nunits, nunits);
return tree_to_uhwi (TYPE_SIZE_UNIT (TREE_TYPE (DR_REF (dr_info->dr))));
}
+/* Return true if LOOP_VINFO requires a runtime check for whether the
+ vector loop is profitable. */
+
+inline bool
+vect_apply_runtime_profitability_check_p (loop_vec_info loop_vinfo)
+{
+ unsigned int th = LOOP_VINFO_COST_MODEL_THRESHOLD (loop_vinfo);
+ return (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
+ && th >= vect_vf_for_cost (loop_vinfo));
+}
+
/* Source location + hotness information. */
extern dump_user_location_t vect_location;
extern bool slpeel_can_duplicate_loop_p (const class loop *, const_edge);
class loop *slpeel_tree_duplicate_loop_to_edge_cfg (class loop *,
class loop *, edge);
-class loop *vect_loop_versioning (loop_vec_info, unsigned int, bool,
- poly_uint64);
+class loop *vect_loop_versioning (loop_vec_info);
extern class loop *vect_do_peeling (loop_vec_info, tree, tree,
- tree *, tree *, tree *, int, bool, bool);
+ tree *, tree *, tree *, int, bool, bool,
+ tree *, drs_init_vec &);
extern void vect_prepare_for_masked_peels (loop_vec_info);
extern dump_user_location_t find_loop_location (class loop *);
extern bool vect_can_advance_ivs_p (loop_vec_info);
+extern void vect_update_inits_of_drs (loop_vec_info, tree, tree_code);
/* In tree-vect-stmts.c. */
-extern poly_uint64 current_vector_size;
-extern tree get_vectype_for_scalar_type (tree);
-extern tree get_vectype_for_scalar_type_and_size (tree, poly_uint64);
-extern tree get_mask_type_for_scalar_type (tree);
+extern tree get_related_vectype_for_scalar_type (machine_mode, tree,
+ poly_uint64 = 0);
+extern tree get_vectype_for_scalar_type (vec_info *, tree, unsigned int = 0);
+extern tree get_vectype_for_scalar_type (vec_info *, tree, slp_tree);
+extern tree get_mask_type_for_scalar_type (vec_info *, tree, unsigned int = 0);
extern tree get_same_sized_vectype (tree, tree);
+extern bool vect_chooses_same_modes_p (vec_info *, machine_mode);
extern bool vect_get_loop_mask_type (loop_vec_info);
extern bool vect_is_simple_use (tree, vec_info *, enum vect_def_type *,
stmt_vec_info * = NULL, gimple ** = NULL);
enum tree_code *, int *,
vec<tree> *);
extern bool supportable_narrowing_operation (enum tree_code, tree, tree,
- enum tree_code *,
- int *, vec<tree> *);
+ enum tree_code *, int *,
+ vec<tree> *);
extern unsigned record_stmt_cost (stmt_vector_for_cost *, int,
enum vect_cost_for_stmt, stmt_vec_info,
int, enum vect_cost_model_location);
extern bool vect_transform_stmt (stmt_vec_info, gimple_stmt_iterator *,
slp_tree, slp_instance);
extern void vect_remove_stores (stmt_vec_info);
+extern bool vect_nop_conversion_p (stmt_vec_info);
extern opt_result vect_analyze_stmt (stmt_vec_info, bool *, slp_tree,
slp_instance, stmt_vector_for_cost *);
extern void vect_get_load_cost (stmt_vec_info, int, bool,
stmt_vector_for_cost *, bool);
extern void vect_get_store_cost (stmt_vec_info, int,
unsigned int *, stmt_vector_for_cost *);
-extern bool vect_supportable_shift (enum tree_code, tree);
+extern bool vect_supportable_shift (vec_info *, enum tree_code, tree);
extern tree vect_gen_perm_mask_any (tree, const vec_perm_indices &);
extern tree vect_gen_perm_mask_checked (tree, const vec_perm_indices &);
extern void optimize_mask_stores (class loop*);
extern gcall *vect_gen_while (tree, tree, tree);
extern tree vect_gen_while_not (gimple_seq *, tree, tree, tree);
extern opt_result vect_get_vector_types_for_stmt (stmt_vec_info, tree *,
- tree *);
-extern opt_tree vect_get_mask_type_for_stmt (stmt_vec_info);
+ tree *, unsigned int = 0);
+extern opt_tree vect_get_mask_type_for_stmt (stmt_vec_info, unsigned int = 0);
/* In tree-vect-data-refs.c. */
extern bool vect_can_force_dr_alignment_p (const_tree, poly_uint64);
extern bool vect_slp_analyze_and_verify_instance_alignment (slp_instance);
extern opt_result vect_analyze_data_ref_accesses (vec_info *);
extern opt_result vect_prune_runtime_alias_test_list (loop_vec_info);
-extern bool vect_gather_scatter_fn_p (bool, bool, tree, tree, unsigned int,
- signop, int, internal_fn *, tree *);
+extern bool vect_gather_scatter_fn_p (vec_info *, bool, bool, tree, tree,
+ tree, int, internal_fn *, tree *);
extern bool vect_check_gather_scatter (stmt_vec_info, loop_vec_info,
gather_scatter_info *);
extern opt_result vect_find_stmt_data_reference (loop_p, gimple *,
/* In tree-vect-loop.c. */
extern widest_int vect_iv_limit_for_full_masking (loop_vec_info loop_vinfo);
+/* Used in tree-vect-loop-manip.c */
+extern void determine_peel_for_niter (loop_vec_info);
/* Used in gimple-loop-interchange.c and tree-parloops.c. */
extern bool check_reduction_path (dump_user_location_t, loop_p, gphi *, tree,
enum tree_code);
extern bool needs_fold_left_reduction_p (tree, tree_code);
/* Drive for loop analysis stage. */
-extern opt_loop_vec_info vect_analyze_loop (class loop *,
- loop_vec_info,
- vec_info_shared *);
+extern opt_loop_vec_info vect_analyze_loop (class loop *, vec_info_shared *);
extern tree vect_build_loop_niters (loop_vec_info, bool * = NULL);
extern void vect_gen_vector_loop_niters (loop_vec_info, tree, tree *,
tree *, bool);
-extern tree vect_halve_mask_nunits (tree);
-extern tree vect_double_mask_nunits (tree);
+extern tree vect_halve_mask_nunits (tree, machine_mode);
+extern tree vect_double_mask_nunits (tree, machine_mode);
extern void vect_record_loop_mask (loop_vec_info, vec_loop_masks *,
- unsigned int, tree);
+ unsigned int, tree, tree);
extern tree vect_get_loop_mask (gimple_stmt_iterator *, vec_loop_masks *,
unsigned int, tree, unsigned int);
extern stmt_vec_info info_for_reduction (stmt_vec_info);
extern opt_result vect_analyze_slp (vec_info *, unsigned);
extern bool vect_make_slp_decision (loop_vec_info);
extern void vect_detect_hybrid_slp (loop_vec_info);
-extern void vect_get_slp_defs (vec<tree> , slp_tree, vec<vec<tree> > *);
+extern void vect_get_slp_defs (slp_tree, vec<vec<tree> > *, unsigned n = -1U);
extern bool vect_slp_bb (basic_block);
extern stmt_vec_info vect_find_last_scalar_stmt_in_slp (slp_tree);
extern bool is_simple_and_all_uses_invariant (stmt_vec_info, loop_vec_info);
-extern bool can_duplicate_and_interleave_p (unsigned int, machine_mode,
+extern bool can_duplicate_and_interleave_p (vec_info *, unsigned int, tree,
unsigned int * = NULL,
tree * = NULL, tree * = NULL);
-extern void duplicate_and_interleave (gimple_seq *, tree, vec<tree>,
- unsigned int, vec<tree> &);
+extern void duplicate_and_interleave (vec_info *, gimple_seq *, tree,
+ vec<tree>, unsigned int, vec<tree> &);
extern int vect_get_place_in_interleaving_chain (stmt_vec_info, stmt_vec_info);
/* In tree-vect-patterns.c. */
projects / thirdparty / gcc.git / blobdiff