* asan.c (asan_emit_stack_protection): Update. (create_cond_insert_point): Update. * auto-profile.c (afdo_propagate_circuit): Update. * basic-block.h (struct edge_def): Turn probability to profile_probability. (EDGE_FREQUENCY): Update. * bb-reorder.c (find_traces_1_round): Update. (better_edge_p): Update. (sanitize_hot_paths): Update. * cfg.c (unchecked_make_edge): Initialize probability to uninitialized. (make_single_succ_edge): Update. (check_bb_profile): Update. (dump_edge_info): Update. (update_bb_profile_for_threading): Update. * cfganal.c (connect_infinite_loops_to_exit): Initialize new edge probabilitycount to 0. * cfgbuild.c (compute_outgoing_frequencies): Update. * cfgcleanup.c (try_forward_edges): Update. (outgoing_edges_match): Update. (try_crossjump_to_edge): Update. * cfgexpand.c (expand_gimple_cond): Update make_single_succ_edge. (expand_gimple_tailcall): Update. (construct_init_block): Use make_single_succ_edge. (construct_exit_block): Use make_single_succ_edge. * cfghooks.c (verify_flow_info): Update. (redirect_edge_succ_nodup): Update. (split_edge): Update. (account_profile_record): Update. * cfgloopanal.c (single_likely_exit): Update. * cfgloopmanip.c (scale_loop_profile): Update. (set_zero_probability): Remove. (duplicate_loop_to_header_edge): Update. * cfgloopmanip.h (loop_version): Update prototype. * cfgrtl.c (try_redirect_by_replacing_jump): Update. (force_nonfallthru_and_redirect): Update. (update_br_prob_note): Update. (rtl_verify_edges): Update. (purge_dead_edges): Update. (rtl_lv_add_condition_to_bb): Update. * cgraph.c: (cgraph_edge::redirect_call_stmt_to_calle): Update. * cgraphunit.c (init_lowered_empty_function): Update. (cgraph_node::expand_thunk): Update. * cilk-common.c: Include profile-count.h * dojump.c (inv): Remove. (jumpifnot): Update. (jumpifnot_1): Update. (do_jump_1): Update. (do_jump): Update. (do_jump_by_parts_greater_rtx): Update. (do_compare_rtx_and_jump): Update. * dojump.h (jumpifnot, jumpifnot_1, jumpif_1, jumpif, do_jump, do_jump_1. do_compare_rtx_and_jump): Update prototype. * dwarf2cfi.c: Include profile-count.h * except.c (dw2_build_landing_pads): Use make_single_succ_edge. (sjlj_emit_dispatch_table): Likewise. * explow.c: Include profile-count.h * expmed.c (emit_store_flag_force): Update. (do_cmp_and_jump): Update. * expr.c (compare_by_pieces_d::generate): Update. (compare_by_pieces_d::finish_mode): Update. (emit_block_move_via_loop): Update. (store_expr_with_bounds): Update. (store_constructor): Update. (expand_expr_real_2): Update. (expand_expr_real_1): Update. * expr.h (try_casesi, try_tablejump): Update prototypes. * gimple-pretty-print.c (dump_probability): Update. (dump_profile): New. (dump_gimple_label): Update. (dump_gimple_bb_header): Update. * graph.c (draw_cfg_node_succ_edges): Update. * hsa-gen.c (convert_switch_statements): Update. * ifcvt.c (cheap_bb_rtx_cost_p): Update. (find_if_case_1): Update. (find_if_case_2): Update. * internal-fn.c (expand_arith_overflow_result_store): Update. (expand_addsub_overflow): Update. (expand_neg_overflow): Update. (expand_mul_overflow): Update. (expand_vector_ubsan_overflow): Update. * ipa-cp.c (good_cloning_opportunity_p): Update. * ipa-split.c (split_function): Use make_single_succ_edge. * ipa-utils.c (ipa_merge_profiles): Update. * loop-doloop.c (add_test): Update. (doloop_modify): Update. * loop-unroll.c (compare_and_jump_seq): Update. (unroll_loop_runtime_iterations): Update. * lra-constraints.c (lra_inheritance): Update. * lto-streamer-in.c (input_cfg): Update. * lto-streamer-out.c (output_cfg): Update. * mcf.c (adjust_cfg_counts): Update. * modulo-sched.c (sms_schedule): Update. * omp-expand.c (expand_omp_for_init_counts): Update. (extract_omp_for_update_vars): Update. (expand_omp_ordered_sink): Update. (expand_omp_for_ordered_loops): Update. (expand_omp_for_generic): Update. (expand_omp_for_static_nochunk): Update. (expand_omp_for_static_chunk): Update. (expand_cilk_for): Update. (expand_omp_simd): Update. (expand_omp_taskloop_for_outer): Update. (expand_omp_taskloop_for_inner): Update. * omp-simd-clone.c (simd_clone_adjust): Update. * optabs.c (expand_doubleword_shift): Update. (expand_abs): Update. (emit_cmp_and_jump_insn_1): Update. (expand_compare_and_swap_loop): Update. * optabs.h (emit_cmp_and_jump_insns): Update prototype. * predict.c (predictable_edge_p): Update. (edge_probability_reliable_p): Update. (set_even_probabilities): Update. (combine_predictions_for_insn): Update. (combine_predictions_for_bb): Update. (propagate_freq): Update. (estimate_bb_frequencies): Update. (force_edge_cold): Update. * profile-count.c (profile_count::dump): Add missing space into dump. (profile_count::debug): Add newline. (profile_count::differs_from_p): Explicitly convert to unsigned. (profile_count::stream_in): Update. (profile_probability::dump): New member function. (profile_probability::debug): New member function. (profile_probability::differs_from_p): New member function. (profile_probability::differs_lot_from_p): New member function. (profile_probability::stream_in): New member function. (profile_probability::stream_out): New member function. * profile-count.h (profile_count_quality): Rename to ... (profile_quality): ... this one. (profile_probability): New. (profile_count): Update. * profile.c (compute_branch_probabilities): Update. * recog.c (peep2_attempt): Update. * sched-ebb.c (schedule_ebbs): Update. * sched-rgn.c (find_single_block_region): Update. (compute_dom_prob_ps): Update. (schedule_region): Update. * sel-sched-ir.c (compute_succs_info): Update. * stmt.c (struct case_node): Update. (do_jump_if_equal): Update. (get_outgoing_edge_probs): Update. (conditional_probability): Update. (emit_case_dispatch_table): Update. (expand_case): Update. (expand_sjlj_dispatch_table): Update. (emit_case_nodes): Update. * targhooks.c: Update. * tracer.c (better_p): Update. (find_best_successor): Update. * trans-mem.c (expand_transaction): Update. * tree-call-cdce.c: Update. * tree-cfg.c (gimple_split_edge): Upate. (move_sese_region_to_fn): Upate. * tree-cfgcleanup.c (cleanup_control_expr_graph): Upate. * tree-eh.c (lower_resx): Upate. (cleanup_empty_eh_move_lp): Upate. * tree-if-conv.c (version_loop_for_if_conversion): Update. * tree-inline.c (copy_edges_for_bb): Update. (copy_cfg_body): Update. * tree-parloops.c (gen_parallel_loop): Update. * tree-profile.c (gimple_gen_ic_func_profiler): Update. (gimple_gen_time_profiler): Update. * tree-ssa-dce.c (remove_dead_stmt): Update. * tree-ssa-ifcombine.c (update_profile_after_ifcombine): Update. * tree-ssa-loop-im.c (execute_sm_if_changed): Update. * tree-ssa-loop-ivcanon.c (remove_exits_and_undefined_stmts): Update. (unloop_loops): Update. (try_peel_loop): Update. * tree-ssa-loop-manip.c (tree_transform_and_unroll_loop): Update. * tree-ssa-loop-split.c (connect_loops): Update. (split_loop): Update. * tree-ssa-loop-unswitch.c (tree_unswitch_loop): Update. (hoist_guard): Update. * tree-ssa-phionlycprop.c (propagate_rhs_into_lhs): Update. * tree-ssa-phiopt.c (replace_phi_edge_with_variable): Update. (value_replacement): Update. * tree-ssa-reassoc.c (branch_fixup): Update. * tree-ssa-tail-merge.c (replace_block_by): Update. * tree-ssa-threadupdate.c (remove_ctrl_stmt_and_useless_edges): Update. (create_edge_and_update_destination_phis): Update. (compute_path_counts): Update. (recompute_probabilities): Update. (update_joiner_offpath_counts): Update. (freqs_to_counts_path): Update. (duplicate_thread_path): Update. * tree-switch-conversion.c (hoist_edge_and_branch_if_true): Update. (struct switch_conv_info): Update. (gen_inbound_check): Update. * tree-vect-loop-manip.c (slpeel_add_loop_guard): Update. (vect_do_peeling): Update. (vect_loop_versioning): Update. * tree-vect-loop.c (scale_profile_for_vect_loop): Update. (optimize_mask_stores): Update. * ubsan.c (ubsan_expand_null_ifn): Update. * value-prof.c (gimple_divmod_fixed_value): Update. (gimple_divmod_fixed_value_transform): Update. (gimple_mod_pow2): Update. (gimple_mod_pow2_value_transform): Update. (gimple_mod_subtract): Update. (gimple_mod_subtract_transform): Update. (gimple_ic): Update. (gimple_stringop_fixed_value): Update. (gimple_stringops_transform): Update. * value-prof.h: Update. From-SVN: r249800
572 lines
21 KiB
C
572 lines
21 KiB
C
/* This file is part of the Intel(R) Cilk(TM) Plus support
|
|
This file contains the CilkPlus Intrinsics
|
|
Copyright (C) 2013-2017 Free Software Foundation, Inc.
|
|
Contributed by Balaji V. Iyer <balaji.v.iyer@intel.com>,
|
|
Intel Corporation
|
|
|
|
This file is part of GCC.
|
|
|
|
GCC is free software; you can redistribute it and/or modify it
|
|
under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation; either version 3, or (at your option)
|
|
any later version.
|
|
|
|
GCC is distributed in the hope that it will be useful, but
|
|
WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
along with GCC; see the file COPYING3. If not see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#include "config.h"
|
|
#include "system.h"
|
|
#include "coretypes.h"
|
|
#include "tm.h"
|
|
#include "function.h"
|
|
#include "rtl.h"
|
|
#include "tree.h"
|
|
#include "stringpool.h"
|
|
#include "expmed.h"
|
|
#include "optabs-query.h"
|
|
#include "insn-config.h"
|
|
#include "memmodel.h"
|
|
#include "emit-rtl.h"
|
|
#include "recog.h"
|
|
#include "fold-const.h"
|
|
#include "stor-layout.h"
|
|
#include "langhooks.h"
|
|
#include "explow.h"
|
|
#include "profile-count.h"
|
|
#include "expr.h"
|
|
#include "tree-iterator.h"
|
|
#include "gimplify.h"
|
|
#include "cilk.h"
|
|
|
|
/* This structure holds all the important fields of the internal structures,
|
|
internal built-in functions, and Cilk-specific data types. Explanation of
|
|
all the these fielsd are given in cilk.h. */
|
|
tree cilk_trees[(int) CILK_TI_MAX];
|
|
|
|
/* Returns the value in structure FRAME pointed by the FIELD_NUMBER
|
|
(e.g. X.y).
|
|
FIELD_NUMBER is an index to the structure FRAME_PTR. For details
|
|
about these fields, refer to cilk_trees structure in cilk.h and
|
|
cilk_init_builtins function in this file. Returns a TREE that is the type
|
|
of the field represented by FIELD_NUMBER. If VOLATIL parameter is set
|
|
to true then the returning field is set as volatile. */
|
|
|
|
tree
|
|
cilk_dot (tree frame, int field_number, bool volatil)
|
|
{
|
|
tree field = cilk_trees[field_number];
|
|
field = fold_build3 (COMPONENT_REF, TREE_TYPE (field), frame, field,
|
|
NULL_TREE);
|
|
TREE_THIS_VOLATILE (field) = volatil;
|
|
return field;
|
|
}
|
|
|
|
/* Returns the address of a field in FRAME_PTR, pointed by FIELD_NUMBER.
|
|
(e.g. (&X)->y). Please see cilk_dot function for explanation of the
|
|
FIELD_NUMBER. Returns a tree that is the type of the field represented
|
|
by FIELD_NUMBER. If VOLATIL parameter is set to true then the returning
|
|
field is set as volatile. */
|
|
|
|
tree
|
|
cilk_arrow (tree frame_ptr, int field_number, bool volatil)
|
|
{
|
|
return cilk_dot (build_simple_mem_ref (frame_ptr),
|
|
field_number, volatil);
|
|
}
|
|
|
|
|
|
/* This function will add FIELD of type TYPE to a defined built-in
|
|
structure. *NAME is the name of the field to be added. */
|
|
|
|
static tree
|
|
add_field (const char *name, tree type, tree fields)
|
|
{
|
|
tree t = get_identifier (name);
|
|
tree field = build_decl (BUILTINS_LOCATION, FIELD_DECL, t, type);
|
|
TREE_CHAIN (field) = fields;
|
|
return field;
|
|
}
|
|
|
|
/* This function will define a built-in function of NAME, of type FNTYPE and
|
|
register it under the built-in function code CODE. If PUBLISH is set then
|
|
the declaration is pushed into the declaration list. CODE is the index
|
|
to the cilk_trees array. *NAME is the name of the function to be added. */
|
|
|
|
static tree
|
|
install_builtin (const char *name, tree fntype, enum built_in_function code,
|
|
bool publish)
|
|
{
|
|
tree fndecl = build_fn_decl (name, fntype);
|
|
DECL_BUILT_IN_CLASS (fndecl) = BUILT_IN_NORMAL;
|
|
DECL_FUNCTION_CODE (fndecl) = code;
|
|
if (publish)
|
|
{
|
|
tree t = lang_hooks.decls.pushdecl (fndecl);
|
|
if (t)
|
|
fndecl = t;
|
|
}
|
|
set_builtin_decl (code, fndecl, true);
|
|
return fndecl;
|
|
}
|
|
|
|
/* Returns a FUNCTION_DECL of type TYPE whose name is *NAME. */
|
|
|
|
static tree
|
|
declare_cilk_for_builtin (const char *name, tree type,
|
|
enum built_in_function code)
|
|
{
|
|
tree cb, ft, fn;
|
|
|
|
cb = build_function_type_list (void_type_node,
|
|
ptr_type_node, type, type,
|
|
NULL_TREE);
|
|
cb = build_pointer_type (cb);
|
|
ft = build_function_type_list (void_type_node,
|
|
cb, ptr_type_node, type,
|
|
integer_type_node, NULL_TREE);
|
|
fn = install_builtin (name, ft, code, false);
|
|
TREE_NOTHROW (fn) = 0;
|
|
|
|
return fn;
|
|
}
|
|
|
|
/* Creates and initializes all the built-in Cilk keywords functions and three
|
|
structures: __cilkrts_stack_frame, __cilkrts_pedigree and __cilkrts_worker.
|
|
Detailed information about __cilkrts_stack_frame and
|
|
__cilkrts_worker structures are given in libcilkrts/include/internal/abi.h.
|
|
__cilkrts_pedigree is described in libcilkrts/include/cilk/common.h. */
|
|
|
|
void
|
|
cilk_init_builtins (void)
|
|
{
|
|
/* Now build the following __cilkrts_pedigree struct:
|
|
struct __cilkrts_pedigree {
|
|
uint64_t rank;
|
|
struct __cilkrts_pedigree *parent;
|
|
} */
|
|
|
|
tree pedigree_type = lang_hooks.types.make_type (RECORD_TYPE);
|
|
tree pedigree_ptr = build_pointer_type (pedigree_type);
|
|
tree field = add_field ("rank", uint64_type_node, NULL_TREE);
|
|
cilk_trees[CILK_TI_PEDIGREE_RANK] = field;
|
|
field = add_field ("parent", pedigree_ptr, field);
|
|
cilk_trees[CILK_TI_PEDIGREE_PARENT] = field;
|
|
finish_builtin_struct (pedigree_type, "__cilkrts_pedigree_GCC", field,
|
|
NULL_TREE);
|
|
lang_hooks.types.register_builtin_type (pedigree_type,
|
|
"__cilkrts_pedigree_t");
|
|
cilk_pedigree_type_decl = pedigree_type;
|
|
|
|
/* Build the Cilk Stack Frame:
|
|
struct __cilkrts_stack_frame {
|
|
uint32_t flags;
|
|
uint32_t size;
|
|
struct __cilkrts_stack_frame *call_parent;
|
|
__cilkrts_worker *worker;
|
|
void *except_data;
|
|
void *ctx[4];
|
|
uint32_t mxcsr;
|
|
uint16_t fpcsr;
|
|
uint16_t reserved;
|
|
__cilkrts_pedigree pedigree;
|
|
}; */
|
|
|
|
tree frame = lang_hooks.types.make_type (RECORD_TYPE);
|
|
tree frame_ptr = build_pointer_type (frame);
|
|
tree worker_type = lang_hooks.types.make_type (RECORD_TYPE);
|
|
tree worker_ptr = build_pointer_type (worker_type);
|
|
tree s_type_node = build_int_cst (size_type_node, 4);
|
|
|
|
tree flags = add_field ("flags", uint32_type_node, NULL_TREE);
|
|
tree size = add_field ("size", uint32_type_node, flags);
|
|
tree parent = add_field ("call_parent", frame_ptr, size);
|
|
tree worker = add_field ("worker", worker_ptr, parent);
|
|
tree except = add_field ("except_data", frame_ptr, worker);
|
|
tree context = add_field ("ctx",
|
|
build_array_type (ptr_type_node,
|
|
build_index_type (s_type_node)),
|
|
except);
|
|
tree mxcsr = add_field ("mxcsr", uint32_type_node, context);
|
|
tree fpcsr = add_field ("fpcsr", uint16_type_node, mxcsr);
|
|
tree reserved = add_field ("reserved", uint16_type_node, fpcsr);
|
|
tree pedigree = add_field ("pedigree", pedigree_type, reserved);
|
|
|
|
/* Now add them to a common structure whose fields are #defined to something
|
|
that is used at a later stage. */
|
|
cilk_trees[CILK_TI_FRAME_FLAGS] = flags;
|
|
cilk_trees[CILK_TI_FRAME_PARENT] = parent;
|
|
cilk_trees[CILK_TI_FRAME_WORKER] = worker;
|
|
cilk_trees[CILK_TI_FRAME_EXCEPTION] = except;
|
|
cilk_trees[CILK_TI_FRAME_CONTEXT] = context;
|
|
/* We don't care about reserved, so no need to store it in cilk_trees. */
|
|
cilk_trees[CILK_TI_FRAME_PEDIGREE] = pedigree;
|
|
TREE_ADDRESSABLE (frame) = 1;
|
|
|
|
finish_builtin_struct (frame, "__cilkrts_st_frame_GCC", pedigree, NULL_TREE);
|
|
cilk_frame_type_decl = frame;
|
|
lang_hooks.types.register_builtin_type (frame, "__cilkrts_frame_t");
|
|
|
|
cilk_frame_ptr_type_decl = build_qualified_type (frame_ptr,
|
|
TYPE_QUAL_VOLATILE);
|
|
/* Now let's do the following worker struct:
|
|
|
|
struct __cilkrts_worker {
|
|
__cilkrts_stack_frame *volatile *volatile tail;
|
|
__cilkrts_stack_frame *volatile *volatile head;
|
|
__cilkrts_stack_frame *volatile *volatile exc;
|
|
__cilkrts_stack_frame *volatile *volatile protected_tail;
|
|
__cilkrts_stack_frame *volatile *ltq_limit;
|
|
int32_t self;
|
|
global_state_t *g;
|
|
local_state *l;
|
|
cilkred_map *reducer_map;
|
|
__cilkrts_stack_frame *current_stack_frame;
|
|
void *reserved;
|
|
__cilkrts_worker_sysdep_state *sysdep;
|
|
__cilkrts_pedigree pedigree;
|
|
} */
|
|
|
|
tree fptr_volatil_type = build_qualified_type (frame_ptr, TYPE_QUAL_VOLATILE);
|
|
tree fptr_volatile_ptr = build_pointer_type (fptr_volatil_type);
|
|
tree fptr_vol_ptr_vol = build_qualified_type (fptr_volatile_ptr,
|
|
TYPE_QUAL_VOLATILE);
|
|
tree g = lang_hooks.types.make_type (RECORD_TYPE);
|
|
finish_builtin_struct (g, "__cilkrts_global_state", NULL_TREE, NULL_TREE);
|
|
tree l = lang_hooks.types.make_type (RECORD_TYPE);
|
|
finish_builtin_struct (l, "__cilkrts_local_state", NULL_TREE, NULL_TREE);
|
|
tree sysdep_t = lang_hooks.types.make_type (RECORD_TYPE);
|
|
finish_builtin_struct (sysdep_t, "__cilkrts_worker_sysdep_state", NULL_TREE,
|
|
NULL_TREE);
|
|
|
|
field = add_field ("tail", fptr_vol_ptr_vol, NULL_TREE);
|
|
cilk_trees[CILK_TI_WORKER_TAIL] = field;
|
|
field = add_field ("head", fptr_vol_ptr_vol, field);
|
|
field = add_field ("exc", fptr_vol_ptr_vol, field);
|
|
field = add_field ("protected_tail", fptr_vol_ptr_vol, field);
|
|
field = add_field ("ltq_limit", fptr_volatile_ptr, field);
|
|
field = add_field ("self", integer_type_node, field);
|
|
field = add_field ("g", build_pointer_type (g), field);
|
|
field = add_field ("l", build_pointer_type (g), field);
|
|
field = add_field ("reducer_map", ptr_type_node, field);
|
|
field = add_field ("current_stack_frame", frame_ptr, field);
|
|
cilk_trees[CILK_TI_WORKER_CUR] = field;
|
|
field = add_field ("saved_protected_tail", fptr_volatile_ptr, field);
|
|
field = add_field ("sysdep", build_pointer_type (sysdep_t), field);
|
|
field = add_field ("pedigree", pedigree_type, field);
|
|
cilk_trees[CILK_TI_WORKER_PEDIGREE] = field;
|
|
finish_builtin_struct (worker_type, "__cilkrts_worker_GCC", field,
|
|
NULL_TREE);
|
|
|
|
tree fptr_arglist = tree_cons (NULL_TREE, frame_ptr, void_list_node);
|
|
tree fptr_fun = build_function_type (void_type_node, fptr_arglist);
|
|
|
|
/* void __cilkrts_enter_frame_1 (__cilkrts_stack_frame *); */
|
|
cilk_enter_fndecl = install_builtin ("__cilkrts_enter_frame_1", fptr_fun,
|
|
BUILT_IN_CILK_ENTER_FRAME, false);
|
|
|
|
/* void __cilkrts_enter_frame_fast_1 (__cilkrts_stack_frame *); */
|
|
cilk_enter_fast_fndecl =
|
|
install_builtin ("__cilkrts_enter_frame_fast_1", fptr_fun,
|
|
BUILT_IN_CILK_ENTER_FRAME_FAST, false);
|
|
|
|
/* void __cilkrts_pop_frame (__cilkrts_stack_frame *); */
|
|
cilk_pop_fndecl = install_builtin ("__cilkrts_pop_frame", fptr_fun,
|
|
BUILT_IN_CILK_POP_FRAME, false);
|
|
|
|
/* void __cilkrts_leave_frame (__cilkrts_stack_frame *); */
|
|
cilk_leave_fndecl = install_builtin ("__cilkrts_leave_frame", fptr_fun,
|
|
BUILT_IN_CILK_LEAVE_FRAME, false);
|
|
|
|
/* void __cilkrts_sync (__cilkrts_stack_frame *); */
|
|
cilk_sync_fndecl = install_builtin ("__cilkrts_sync", fptr_fun,
|
|
BUILT_IN_CILK_SYNC, false);
|
|
|
|
/* void __cilkrts_detach (__cilkrts_stack_frame *); */
|
|
cilk_detach_fndecl = install_builtin ("__cilkrts_detach", fptr_fun,
|
|
BUILT_IN_CILK_DETACH, false);
|
|
|
|
/* __cilkrts_rethrow (struct stack_frame *); */
|
|
cilk_rethrow_fndecl = install_builtin ("__cilkrts_rethrow", fptr_fun,
|
|
BUILT_IN_CILK_RETHROW, false);
|
|
TREE_NOTHROW (cilk_rethrow_fndecl) = 0;
|
|
|
|
/* __cilkrts_save_fp_ctrl_state (__cilkrts_stack_frame *); */
|
|
cilk_save_fp_fndecl = install_builtin ("__cilkrts_save_fp_ctrl_state",
|
|
fptr_fun, BUILT_IN_CILK_SAVE_FP,
|
|
false);
|
|
/* __cilkrts_cilk_for_32 (...); */
|
|
cilk_for_32_fndecl = declare_cilk_for_builtin ("__cilkrts_cilk_for_32",
|
|
unsigned_intSI_type_node,
|
|
BUILT_IN_CILK_FOR_32);
|
|
/* __cilkrts_cilk_for_64 (...); */
|
|
cilk_for_64_fndecl = declare_cilk_for_builtin ("__cilkrts_cilk_for_64",
|
|
unsigned_intDI_type_node,
|
|
BUILT_IN_CILK_FOR_64);
|
|
}
|
|
|
|
/* Get the appropriate frame arguments for CALL that is of type CALL_EXPR. */
|
|
|
|
static tree
|
|
get_frame_arg (tree call)
|
|
{
|
|
tree arg, argtype;
|
|
|
|
gcc_assert (call_expr_nargs (call) >= 1);
|
|
|
|
arg = CALL_EXPR_ARG (call, 0);
|
|
argtype = TREE_TYPE (arg);
|
|
gcc_assert (TREE_CODE (argtype) == POINTER_TYPE);
|
|
|
|
argtype = TREE_TYPE (argtype);
|
|
|
|
/* If it is passed in as an address, then just use the value directly
|
|
since the function is inlined. */
|
|
if (TREE_CODE (arg) == ADDR_EXPR)
|
|
return TREE_OPERAND (arg, 0);
|
|
return arg;
|
|
}
|
|
|
|
/* Expands the __cilkrts_pop_frame function call stored in EXP. */
|
|
|
|
void
|
|
expand_builtin_cilk_pop_frame (tree exp)
|
|
{
|
|
tree frame = get_frame_arg (exp);
|
|
tree parent = cilk_dot (frame, CILK_TI_FRAME_PARENT, 0);
|
|
|
|
tree clear_parent = build2 (MODIFY_EXPR, void_type_node, parent,
|
|
build_int_cst (TREE_TYPE (parent), 0));
|
|
expand_expr (clear_parent, const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
|
|
/* During LTO, the is_cilk_function flag gets cleared.
|
|
If __cilkrts_pop_frame is called, then this definitely must be a
|
|
cilk function. */
|
|
if (cfun)
|
|
cfun->is_cilk_function = 1;
|
|
}
|
|
|
|
/* Expands the cilk_detach function call stored in EXP. */
|
|
|
|
void
|
|
expand_builtin_cilk_detach (tree exp)
|
|
{
|
|
rtx_insn *insn;
|
|
tree fptr = get_frame_arg (exp);
|
|
|
|
if (fptr == NULL_TREE)
|
|
return;
|
|
|
|
tree parent = cilk_dot (fptr, CILK_TI_FRAME_PARENT, 0);
|
|
tree worker = cilk_dot (fptr, CILK_TI_FRAME_WORKER, 0);
|
|
tree tail = cilk_arrow (worker, CILK_TI_WORKER_TAIL, 1);
|
|
|
|
tree faddr = build1 (ADDR_EXPR, cilk_frame_ptr_type_decl, fptr);
|
|
tree enter_frame = build_call_expr (cilk_enter_fast_fndecl, 1, faddr);
|
|
expand_expr (enter_frame, const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
|
|
tree pedigree = cilk_dot (fptr, CILK_TI_FRAME_PEDIGREE, 0);
|
|
tree pedigree_rank = cilk_dot (pedigree, CILK_TI_PEDIGREE_RANK, 0);
|
|
tree parent_pedigree = cilk_dot (pedigree, CILK_TI_PEDIGREE_PARENT, 0);
|
|
tree pedigree_parent = cilk_arrow (parent, CILK_TI_FRAME_PEDIGREE, 0);
|
|
tree pedigree_parent_rank = cilk_dot (pedigree_parent,
|
|
CILK_TI_PEDIGREE_RANK, 0);
|
|
tree pedigree_parent_parent = cilk_dot (pedigree_parent,
|
|
CILK_TI_PEDIGREE_PARENT, 0);
|
|
tree worker_pedigree = cilk_arrow (worker, CILK_TI_WORKER_PEDIGREE, 1);
|
|
tree w_pedigree_rank = cilk_dot (worker_pedigree, CILK_TI_PEDIGREE_RANK, 0);
|
|
tree w_pedigree_parent = cilk_dot (worker_pedigree,
|
|
CILK_TI_PEDIGREE_PARENT, 0);
|
|
|
|
rtx wreg = expand_expr (worker, NULL_RTX, Pmode, EXPAND_NORMAL);
|
|
if (GET_CODE (wreg) != REG)
|
|
wreg = copy_to_reg (wreg);
|
|
rtx preg = expand_expr (parent, NULL_RTX, Pmode, EXPAND_NORMAL);
|
|
|
|
/* sf.pedigree.rank = worker->pedigree.rank. */
|
|
tree exp1 = build2 (MODIFY_EXPR, void_type_node, pedigree_rank,
|
|
w_pedigree_rank);
|
|
expand_expr (exp1, const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
|
|
/* sf.pedigree.parent = worker->pedigree.parent. */
|
|
exp1 = build2 (MODIFY_EXPR, void_type_node, parent_pedigree,
|
|
w_pedigree_parent);
|
|
expand_expr (exp1, const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
|
|
/* sf.call_parent->pedigree.rank = worker->pedigree.rank. */
|
|
exp1 = build2 (MODIFY_EXPR, void_type_node, pedigree_parent_rank,
|
|
w_pedigree_rank);
|
|
expand_expr (exp1, const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
|
|
/* sf.call_parent->pedigree.parent = worker->pedigree.parent. */
|
|
exp1 = build2 (MODIFY_EXPR, void_type_node, pedigree_parent_parent,
|
|
w_pedigree_parent);
|
|
expand_expr (exp1, const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
|
|
/* sf->worker.pedigree.rank = 0. */
|
|
exp1 = build2 (MODIFY_EXPR, void_type_node, w_pedigree_rank,
|
|
build_zero_cst (uint64_type_node));
|
|
expand_expr (exp1, const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
|
|
/* sf->pedigree.parent = &sf->pedigree. */
|
|
exp1 = build2 (MODIFY_EXPR, void_type_node, w_pedigree_parent,
|
|
build1 (ADDR_EXPR,
|
|
build_pointer_type (cilk_pedigree_type_decl),
|
|
pedigree));
|
|
expand_expr (exp1, const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
|
|
/* TMP <- WORKER.TAIL
|
|
*TMP <- PARENT
|
|
TMP <- TMP + 1
|
|
WORKER.TAIL <- TMP */
|
|
|
|
HOST_WIDE_INT worker_tail_offset =
|
|
tree_to_shwi (DECL_FIELD_OFFSET (cilk_trees[CILK_TI_WORKER_TAIL])) +
|
|
tree_to_shwi (DECL_FIELD_BIT_OFFSET (cilk_trees[CILK_TI_WORKER_TAIL])) /
|
|
BITS_PER_UNIT;
|
|
rtx tmem0 = gen_rtx_MEM (Pmode,
|
|
plus_constant (Pmode, wreg, worker_tail_offset));
|
|
set_mem_attributes (tmem0, tail, 0);
|
|
MEM_NOTRAP_P (tmem0) = 1;
|
|
gcc_assert (MEM_VOLATILE_P (tmem0));
|
|
rtx treg = copy_to_mode_reg (Pmode, tmem0);
|
|
rtx tmem1 = gen_rtx_MEM (Pmode, treg);
|
|
set_mem_attributes (tmem1, TREE_TYPE (TREE_TYPE (tail)), 0);
|
|
MEM_NOTRAP_P (tmem1) = 1;
|
|
emit_move_insn (tmem1, preg);
|
|
emit_move_insn (treg, plus_constant (Pmode, treg, GET_MODE_SIZE (Pmode)));
|
|
|
|
/* There is a release barrier (st8.rel, membar #StoreStore,
|
|
sfence, lwsync, etc.) between the two stores. On x86
|
|
normal volatile stores have proper semantics; the sfence
|
|
would only be needed for nontemporal stores (which we
|
|
could generate using the storent optab, for no benefit
|
|
in this case).
|
|
|
|
The predicate may return false even for a REG if this is
|
|
the limited release operation that only stores 0. */
|
|
enum insn_code icode = direct_optab_handler (sync_lock_release_optab, Pmode);
|
|
if (icode != CODE_FOR_nothing
|
|
&& insn_data[icode].operand[1].predicate (treg, Pmode)
|
|
&& (insn = GEN_FCN (icode) (tmem0, treg)) != NULL_RTX)
|
|
emit_insn (insn);
|
|
else
|
|
emit_move_insn (tmem0, treg);
|
|
|
|
/* The memory barrier inserted above should not prevent
|
|
the load of flags from being moved before the stores,
|
|
but in practice it does because it is implemented with
|
|
unspec_volatile. In-order RISC machines should
|
|
explicitly load flags earlier. */
|
|
|
|
tree flags = cilk_dot (fptr, CILK_TI_FRAME_FLAGS, 0);
|
|
expand_expr (build2 (MODIFY_EXPR, void_type_node, flags,
|
|
build2 (BIT_IOR_EXPR, TREE_TYPE (flags), flags,
|
|
build_int_cst (TREE_TYPE (flags),
|
|
CILK_FRAME_DETACHED))),
|
|
const0_rtx, VOIDmode, EXPAND_NORMAL);
|
|
}
|
|
|
|
/* Returns a setjmp CALL_EXPR with FRAME->context as its parameter. */
|
|
|
|
tree
|
|
cilk_call_setjmp (tree frame)
|
|
{
|
|
tree c = cilk_dot (frame, CILK_TI_FRAME_CONTEXT, false);
|
|
c = build1 (ADDR_EXPR, build_pointer_type (ptr_type_node), c);
|
|
return build_call_expr (builtin_decl_implicit (BUILT_IN_SETJMP), 1, c);
|
|
}
|
|
|
|
/* This function will expand the _Cilk_sync keyword. */
|
|
|
|
static tree
|
|
expand_cilk_sync (void)
|
|
{
|
|
tree frame = cfun->cilk_frame_decl;
|
|
|
|
/* Cilk_sync is converted to the following code:
|
|
|
|
sf.pedigree = sf.worker->pedigree;
|
|
if (frame.flags & CILK_FRAME_UNSYNCHED)
|
|
{
|
|
__cilkrts_save_fp_state (&sf);
|
|
if (!builtin_setjmp (sf.ctx)
|
|
__cilkrts_sync (&sf);
|
|
else
|
|
if (sf.flags & CILK_FRAME_EXCEPTING)
|
|
__cilkrts_rethrow (&sf);
|
|
}
|
|
sf.worker->pedigree.rank = sf.worker->pedigree.rank + 1; */
|
|
|
|
tree flags = cilk_dot (frame, CILK_TI_FRAME_FLAGS, false);
|
|
|
|
tree unsynched = fold_build2 (BIT_AND_EXPR, TREE_TYPE (flags), flags,
|
|
build_int_cst (TREE_TYPE (flags),
|
|
CILK_FRAME_UNSYNCHED));
|
|
|
|
unsynched = fold_build2 (NE_EXPR, TREE_TYPE (unsynched), unsynched,
|
|
build_int_cst (TREE_TYPE (unsynched), 0));
|
|
|
|
tree frame_addr = build1 (ADDR_EXPR, cilk_frame_ptr_type_decl, frame);
|
|
|
|
/* Check if exception (0x10) bit is set in the sf->flags. */
|
|
tree except_flag = fold_build2 (BIT_AND_EXPR, TREE_TYPE (flags), flags,
|
|
build_int_cst (TREE_TYPE (flags),
|
|
CILK_FRAME_EXCEPTING));
|
|
except_flag = fold_build2 (NE_EXPR, TREE_TYPE (except_flag), except_flag,
|
|
build_int_cst (TREE_TYPE (except_flag), 0));
|
|
|
|
/* If the exception flag is set then call the __cilkrts_rethrow (&sf). */
|
|
tree except_cond = fold_build3 (COND_EXPR, void_type_node, except_flag,
|
|
build_call_expr (cilk_rethrow_fndecl, 1,
|
|
frame_addr),
|
|
build_empty_stmt (EXPR_LOCATION (unsynched)));
|
|
|
|
tree sync_expr = build_call_expr (cilk_sync_fndecl, 1, frame_addr);
|
|
tree setjmp_expr = cilk_call_setjmp (frame);
|
|
setjmp_expr = fold_build2 (EQ_EXPR, TREE_TYPE (setjmp_expr), setjmp_expr,
|
|
build_int_cst (TREE_TYPE (setjmp_expr), 0));
|
|
|
|
setjmp_expr = fold_build3 (COND_EXPR, void_type_node, setjmp_expr,
|
|
sync_expr, except_cond);
|
|
tree sync_list = alloc_stmt_list ();
|
|
append_to_statement_list (build_call_expr (cilk_save_fp_fndecl, 1,
|
|
frame_addr), &sync_list);
|
|
append_to_statement_list (setjmp_expr, &sync_list);
|
|
tree sync = fold_build3 (COND_EXPR, void_type_node, unsynched, sync_list,
|
|
build_empty_stmt (EXPR_LOCATION (unsynched)));
|
|
tree parent_pedigree = cilk_dot (frame, CILK_TI_FRAME_PEDIGREE, false);
|
|
tree worker = cilk_dot (frame, CILK_TI_FRAME_WORKER, false);
|
|
tree worker_pedigree = cilk_arrow (worker, CILK_TI_WORKER_PEDIGREE, false);
|
|
tree assign_pedigree = fold_build2 (MODIFY_EXPR, void_type_node,
|
|
parent_pedigree, worker_pedigree);
|
|
tree w_ped_rank = cilk_dot (unshare_expr (worker_pedigree),
|
|
CILK_TI_PEDIGREE_RANK, false);
|
|
tree incr_ped_rank = fold_build2 (PLUS_EXPR, TREE_TYPE (w_ped_rank),
|
|
w_ped_rank,
|
|
build_one_cst (TREE_TYPE (w_ped_rank)));
|
|
incr_ped_rank = fold_build2 (MODIFY_EXPR, void_type_node, w_ped_rank,
|
|
incr_ped_rank);
|
|
tree ret_sync_exp = alloc_stmt_list ();
|
|
append_to_statement_list (assign_pedigree, &ret_sync_exp);
|
|
append_to_statement_list (sync, &ret_sync_exp);
|
|
append_to_statement_list (incr_ped_rank, &ret_sync_exp);
|
|
return ret_sync_exp;
|
|
}
|
|
|
|
/* Gimplifies the cilk_sync expression passed in *EXPR_P. Returns GS_ALL_DONE
|
|
when finished. */
|
|
|
|
void
|
|
gimplify_cilk_sync (tree *expr_p, gimple_seq *pre_p)
|
|
{
|
|
tree sync_expr = expand_cilk_sync ();
|
|
*expr_p = NULL_TREE;
|
|
gimplify_and_add (sync_expr, pre_p);
|
|
}
|