builtin-types.def (BT_FN_VOID_BOOL, [...]): New.

	* builtin-types.def (BT_FN_VOID_BOOL, BT_FN_VOID_SIZE_SIZE_PTR,
	BT_FN_UINT_UINT_PTR_PTR, BT_FN_UINT_OMPFN_PTR_UINT_UINT,
	BT_FN_BOOL_UINT_LONGPTR_LONG_LONG_LONGPTR_LONGPTR_PTR_PTR,
	BT_FN_BOOL_UINT_ULLPTR_LONG_ULL_ULLPTR_ULLPTR_PTR_PTR,
	BT_FN_BOOL_LONG_LONG_LONG_LONG_LONG_LONGPTR_LONGPTR_PTR_PTR,
	BT_FN_BOOL_BOOL_ULL_ULL_ULL_LONG_ULL_ULLPTR_ULLPTR_PTR_PTR): New.
	* gengtype.c (open_base_files): Add omp-general.h.
	* gimple.c (gimple_build_omp_critical):
	(gimple_build_omp_taskgroup): Add CLAUSES argument.  Call
	gimple_omp_taskgroup_set_clauses.
	(gimple_build_omp_atomic_load): Add mo argument, call
	gimple_omp_atomic_set_memory_order.
	(gimple_build_omp_atomic_store): Likewise.
	(gimple_copy): Adjust handling of GIMPLE_OMP_TASKGROUP.
	* gimple.def (GIMPLE_OMP_TASKGROUP): Use GSS_OMP_SINGLE_LAYOUT
	instead of GSS_OMP.
	(GIMPLE_OMP_TEAMS): Use GSS_OMP_PARALLEL_LAYOUT instead
	of GSS_OMP_SINGLE_LAYOUT, adjust comments.
	* gimple.h (enum gf_mask): Add GF_OMP_TEAMS_HOST, GF_OMP_TASK_TASKWAIT
	and GF_OMP_ATOMIC_MEMORY_ORDER.  Remove GF_OMP_ATOMIC_SEQ_CST, use
	different value for GF_OMP_ATOMIC_NEED_VALUE.
	(struct gimple_statement_omp_taskreg): Add GIMPLE_OMP_TEAMS to
	comments.
	(struct gimple_statement_omp_single_layout): And remove here.
	(struct gomp_teams): Inherit from gimple_statement_omp_taskreg rather
	than gimple_statement_omp_single_layout.
	(is_a_helper <gimple_statement_omp_taskreg *>::test): Allow
	GIMPLE_OMP_TEAMS.
	(is_a_helper <const gimple_statement_omp_taskreg *>::test): Likewise.
	(gimple_omp_subcode): Formatting fix.
	(gimple_omp_teams_child_fn, gimple_omp_teams_child_fn_ptr,
	gimple_omp_teams_set_child_fn, gimple_omp_teams_data_arg,
	gimple_omp_teams_data_arg_ptr, gimple_omp_teams_set_data_arg,
	gimple_omp_teams_host, gimple_omp_teams_set_host,
	gimple_omp_task_taskwait_p, gimple_omp_task_set_taskwait_p,
	gimple_omp_taskgroup_clauses, gimple_omp_taskgroup_clauses_ptr,
	gimple_omp_taskgroup_set_clauses): New inline functions.
	(gimple_build_omp_atomic_load): Add enum omp_memory_order argument.
	(gimple_build_omp_atomic_store): Likewise.
	(gimple_omp_atomic_seq_cst_p): Remove.
	(gimple_omp_atomic_memory_order): New function.
	(gimple_omp_atomic_set_seq_cst): Remove.
	(gimple_omp_atomic_set_memory_order): New function.
	(gimple_build_omp_taskgroup): Add clauses argument.
	* gimple-pretty-print.c (dump_gimple_omp_taskgroup): New function.
	(dump_gimple_omp_task): Print taskwait with depend clauses.
	(dump_gimple_omp_atomic_load, dump_gimple_omp_atomic_store): Use
	dump_omp_atomic_memory_order.
	(pp_gimple_stmt_1): Handle GIMPLE_OMP_TASKGROUP.
	* gimplify.c (enum gimplify_omp_var_data): Add GOVD_MAP_ALLOC_ONLY,
	GOVD_MAP_FROM_ONLY and GOVD_NONTEMPORAL.
	(enum omp_region_type): Reserve bits 1 and 2 for auxiliary flags,
	renumber values of most of ORT_* enumerators, add ORT_HOST_TEAMS,
	ORT_COMBINED_HOST_TEAMS, ORT_TASKGROUP, ORT_TASKLOOP and
	ORT_UNTIED_TASKLOOP enumerators.
	(enum gimplify_defaultmap_kind): New.
	(struct gimplify_omp_ctx): Remove target_map_scalars_firstprivate and
	target_map_pointers_as_0len_arrays members, add defaultmap.
	(new_omp_context): Initialize defaultmap member.
	(gimple_add_tmp_var): Handle ORT_TASKGROUP like ORT_WORKSHARE.
	(maybe_fold_stmt): Don't fold even in host teams regions.
	(omp_firstprivatize_variable): Handle ORT_TASKGROUP like
	ORT_WORKSHARE.  Test ctx->defaultmap[GDMK_SCALAR] instead of
	ctx->omp_firstprivatize_variable.
	(omp_add_variable): Don't add private/firstprivate for VLAs in
	ORT_TASKGROUP.
	(omp_default_clause): Print "taskloop" rather than "task" if
	ORT_*TASKLOOP.
	(omp_notice_variable): Handle ORT_TASKGROUP like ORT_WORKSHARE.
	Handle new defaultmap clause kinds.
	(omp_is_private): Handle ORT_TASKGROUP like ORT_WORKSHARE.  Allow simd
	iterator to be lastprivate or private.  Fix up diagnostics if linear
	is used on collapse>1 simd iterator.
	(omp_check_private): Handle ORT_TASKGROUP like ORT_WORKSHARE.
	(gimplify_omp_depend): New function.
	(gimplify_scan_omp_clauses): Add shared clause on parallel for
	combined parallel master taskloop{, simd} if taskloop has
	firstprivate, lastprivate or reduction clause.  Handle
	OMP_CLAUSE_REDUCTION_TASK diagnostics.  Adjust tests for
	ORT_COMBINED_TEAMS.  Gimplify depend clauses with iterators.  Handle
	cancel and simd OMP_CLAUSE_IF_MODIFIERs.  Handle
	OMP_CLAUSE_NONTEMPORAL.  Handle new defaultmap clause kinds.  Handle
	OMP_CLAUSE_{TASK,IN}_REDUCTION.  Diagnose invalid conditional
	lastprivate.
	(gimplify_adjust_omp_clauses_1): Ignore GOVD_NONTEMPORAL.  Handle
	GOVD_MAP_ALLOC_ONLY and GOVD_MAP_FROM_ONLY.  
	(gimplify_adjust_omp_clauses): Handle OMP_CLAUSE_NONTEMPORAL.  Handle
	OMP_CLAUSE_{TASK,IN}_REDUCTION.
	(gimplify_omp_task): Handle taskwait with depend clauses.
	(gimplify_omp_for): Add shared clause on parallel for combined
	parallel master taskloop{, simd} if taskloop has firstprivate,
	lastprivate or reduction clause.  Use ORT_TASKLOOP or
	ORT_UNTIED_TASKLOOP instead of ORT_TASK or ORT_UNTIED_TASK.  Adjust
	tests for ORT_COMBINED_TEAMS.  Handle C++ range for loops with
	NULL TREE_PURPOSE in OMP_FOR_ORIG_DECLS.  Firstprivatize
	__for_end and __for_range temporaries on OMP_PARALLEL for
	distribute parallel for{, simd}.  Move OMP_CLAUSE_REDUCTION
	and OMP_CLAUSE_IN_REDUCTION from taskloop to the task construct
	sandwiched in between two taskloops.
	(computable_teams_clause): Test ctx->defaultmap[GDMK_SCALAR]
	instead of ctx->omp_firstprivatize_variable.
	(gimplify_omp_workshare): Set ort to ORT_HOST_TEAMS or
	ORT_COMBINED_HOST_TEAMS if not inside of target construct.  If
	host teams, use gimplify_and_return_first etc. for body like
	for target or target data constructs, and at the end call
	gimple_omp_teams_set_host on the GIMPLE_OMP_TEAMS object.
	(gimplify_omp_atomic): Use OMP_ATOMIC_MEMORY_ORDER instead
	of OMP_ATOMIC_SEQ_CST, pass it as new argument to
	gimple_build_omp_atomic_load and gimple_build_omp_atomic_store, remove
	gimple_omp_atomic_set_seq_cst calls.
	(gimplify_expr) <case OMP_TASKGROUP>: Move handling into a separate
	case, handle taskgroup clauses.
	* lto-streamer-out.c (hash_tree): Handle
	OMP_CLAUSE_{TASK,IN}_REDUCTION.
	* Makefile.in (GTFILES): Add omp-general.h.
	* omp-builtins.def (BUILT_IN_GOMP_TASKWAIT_DEPEND,
	BUILT_IN_GOMP_LOOP_NONMONOTONIC_RUNTIME_START,
	BUILT_IN_GOMP_LOOP_MAYBE_NONMONOTONIC_RUNTIME_START,
	BUILT_IN_GOMP_LOOP_START, BUILT_IN_GOMP_LOOP_ORDERED_START,
	BUILT_IN_GOMP_LOOP_DOACROSS_START,
	BUILT_IN_GOMP_LOOP_NONMONOTONIC_RUNTIME_NEXT,
	BUILT_IN_GOMP_LOOP_MAYBE_NONMONOTONIC_RUNTIME_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_NONMONOTONIC_RUNTIME_START,
	BUILT_IN_GOMP_LOOP_ULL_MAYBE_NONMONOTONIC_RUNTIME_START,
	BUILT_IN_GOMP_LOOP_ULL_START, BUILT_IN_GOMP_LOOP_ULL_ORDERED_START,
	BUILT_IN_GOMP_LOOP_ULL_DOACROSS_START,
	BUILT_IN_GOMP_LOOP_ULL_NONMONOTONIC_RUNTIME_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_MAYBE_NONMONOTONIC_RUNTIME_NEXT,
	BUILT_IN_GOMP_PARALLEL_LOOP_NONMONOTONIC_RUNTIME,
	BUILT_IN_GOMP_PARALLEL_LOOP_MAYBE_NONMONOTONIC_RUNTIME,
	BUILT_IN_GOMP_PARALLEL_REDUCTIONS, BUILT_IN_GOMP_SECTIONS2_START,
	BUILT_IN_GOMP_TEAMS_REG, BUILT_IN_GOMP_TASKGROUP_REDUCTION_REGISTER,
	BUILT_IN_GOMP_TASKGROUP_REDUCTION_UNREGISTER,
	BUILT_IN_GOMP_TASK_REDUCTION_REMAP,
	BUILT_IN_GOMP_WORKSHARE_TASK_REDUCTION_UNREGISTER): New builtins.
	* omp-expand.c (workshare_safe_to_combine_p): Return false for
	non-worksharing loops.
	(omp_adjust_chunk_size): Don't adjust anything if chunk_size is zero.
	(determine_parallel_type): Don't combine parallel with worksharing
	which has _reductemp_ clause.
	(expand_parallel_call): Emit the GOMP_*nonmonotonic_runtime* or
	GOMP_*maybe_nonmonotonic_runtime* builtins instead of GOMP_*runtime*
	if there is nonmonotonic modifier or if there is no modifier and no
	ordered clause.  For dynamic and guided schedule without monotonic
	and nonmonotonic modifier, default to nonmonotonic.
	(expand_omp_for): Likewise.  Adjust expand_omp_for_generic caller, use
	GOMP_loop{,_ull}{,_ordered,_doacross}_start builtins if there are
	task reductions.
	(expand_task_call): Add GOMP_TASK_FLAG_REDUCTION flag to flags if
	there are any reduction clauses.
	(expand_taskwait_call): New function.
	(expand_teams_call): New function.
	(expand_omp_taskreg): Allow GIMPLE_OMP_TEAMS and call
	expand_teams_call for it.  Formatting fix.  Handle taskwait with
	depend clauses.
	(expand_omp_for_generic): Add SCHED_ARG argument.  Handle expansion
	of worksharing loops with task reductions.
	(expand_omp_for_static_nochunk, expand_omp_for_static_chunk): Handle
	expansion of worksharing loops with task reductions.
	(expand_omp_sections): Handle expansion of sections with task
	reductions.
	(expand_omp_synch): For host teams call expand_omp_taskreg.
	(omp_memory_order_to_memmodel): New function.
	(expand_omp_atomic_load, expand_omp_atomic_store,
	expand_omp_atomic_fetch_op): Use it and gimple_omp_atomic_memory_order
	instead of gimple_omp_atomic_seq_cst_p.
	(build_omp_regions_1, omp_make_gimple_edges): Treat taskwait with
	depend clauses as a standalone directive.
	* omp-general.c (enum omp_requires): New variable.
	(omp_extract_for_data): Initialize have_reductemp member.  Allow
	NE_EXPR even in OpenMP loops, transform them into LT_EXPR or
	GT_EXPR loops depending on incr sign.  Formatting fixes.
	* omp-general.h (struct omp_for_data): Add have_reductemp member.
	(enum omp_requires): New enum.
	(omp_requires_mask): Declare.
	* omp-grid.c (grid_eliminate_combined_simd_part): Formatting fix.
	Fix comment typos.
	* omp-low.c (struct omp_context): Add task_reductions and
	task_reduction_map fields.
	(is_host_teams_ctx): New function.
	(is_taskreg_ctx): Return true also if is_host_teams_ctx.
	(use_pointer_for_field): Use is_global_var instead of
	TREE_STATIC || DECL_EXTERNAL, and apply only if not privatized
	in outer contexts.
	(build_outer_var_ref): Ignore taskgroup outer contexts.
	(delete_omp_context): Release task_reductions and task_reduction_map.
	(scan_sharing_clauses): Don't add any fields for reduction clause on
	taskloop.  Handle OMP_CLAUSE__REDUCTEMP_.  Handle
	OMP_CLAUSE_{IN,TASK}_REDUCTION and OMP_CLAUSE_REDUCTION with task
	modifier.  Don't ignore shared clauses in is_host_teams_ctx contexts.
	Handle OMP_CLAUSE_NONTEMPORAL.
	(add_taskreg_looptemp_clauses): Add OMP_CLAUSE__REDUCTEMP_ clause if
	needed.
	(scan_omp_parallel): Add _reductemp_ clause if there are any reduction
	clauses with task modifier.
	(scan_omp_task): Handle taskwait with depend clauses.
	(finish_taskreg_scan): Move field corresponding to _reductemp_ clause
	first.  Move also OMP_CLAUSE__REDUCTEMP_ clause in front if present.
	Handle GIMPLE_OMP_TEAMS like GIMPLE_OMP_PARALLEL.
	(scan_omp_for): Fix comment formatting.
	(scan_omp_teams): Handle host teams constructs.
	(check_omp_nesting_restrictions): Allow teams with no outer
	OpenMP context.  Adjust diagnostics for teams strictly nested into
	some explicit OpenMP construct other than target.  Allow OpenMP atomics
	inside of simd regions.
	(scan_omp_1_stmt): Call scan_sharing_clauses for taskgroups.
	(scan_omp_1_stmt) <case GIMPLE_OMP_TEAMS>: Temporarily bump
	taskreg_nesting_level while scanning host teams construct.
	(task_reduction_read): New function.
	(lower_rec_input_clauses): Handle OMP_CLAUSE_REDUCTION on taskloop
	construct.  Handle OMP_CLAUSE_IN_REDUCTION and OMP_CLAUSE__REDUCTEMP_
	clauses.  Handle OMP_CLAUSE_REDUCTION with task modifier.  Remove
	second argument create_tmp_var if it is NULL.  Don't ignore shared
	clauses in is_host_teams_ctx contexts.  Handle
	OMP_CLAUSE_FIRSTPRIVATE_NO_REFERENCE on OMP_CLAUSE_FIRSTPRIVATE
	clauses.
	(lower_reduction_clauses): Ignore reduction clauses with task
	modifier.  Remove second argument create_tmp_var if it is NULL.
	Initialize OMP_ATOMIC_MEMORY_ORDER to relaxed.
	(lower_send_clauses): Ignore reduction clauses with task modifier.
	Handle OMP_CLAUSE__REDUCTEMP_.  Don't send anything for
	OMP_CLAUSE_REDUCTION on taskloop.  Handle OMP_CLAUSE_IN_REDUCTION.
	(maybe_add_implicit_barrier_cancel): Add OMP_RETURN argument, don't
	rely that it is the last stmt in body so far.  Ignore outer taskgroup
	contexts.
	(omp_task_reductions_find_first, omp_task_reduction_iterate,
	lower_omp_task_reductions): New functions.
	(lower_omp_sections): Handle reduction clauses with taskgroup
	modifiers.  Adjust maybe_add_implicit_barrier_cancel caller.
	(lower_omp_single): Adjust maybe_add_implicit_barrier_cancel caller.
	(lower_omp_for): Likewise.  Handle reduction clauses with taskgroup
	modifiers.
	(lower_omp_taskgroup): Handle taskgroup reductions.
	(create_task_copyfn): Copy over OMP_CLAUSE__REDUCTEMP_ pointer.
	Handle OMP_CLAUSE_IN_REDUCTION and OMP_CLAUSE_REDUCTION clauses.
	(lower_depend_clauses): If there are any
	OMP_CLAUSE_DEPEND_DEPOBJ or OMP_CLAUSE_DEPEND_MUTEXINOUTSET
	depend clauses, use a new array format.  If OMP_CLAUSE_DEPEND_LAST is
	seen, assume lowering is done already and return early.  Set kind
	on artificial depend clause to OMP_CLAUSE_DEPEND_LAST.
	(lower_omp_taskreg): Handle reduction clauses with task modifier on
	parallel construct.  Handle reduction clause on taskloop construct.
	Handle taskwait with depend clauses.
	(lower_omp_1): Use lower_omp_taskreg instead of lower_omp_teams
	for host teams constructs.
	* tree.c (omp_clause_num_ops): Add in_reduction, task_reduction,
	nontemporal and _reductemp_ clause entries.
	(omp_clause_code_name): Likewise.
	(walk_tree_1): Handle OMP_CLAUSE_{IN,TASK}_REDUCTION,
	OMP_CLAUSE_NONTEMPORAL and OMP_CLAUSE__REDUCTEMP_.
	* tree-core.h (enum omp_clause_code): Add
	OMP_CLAUSE_{{IN,TASK}_REDUCTION,NONTEMPORAL,_REDUCTEMP_}.
	(enum omp_clause_defaultmap_kind, enum omp_memory_order): New.
	(struct tree_base): Add omp_atomic_memory_order field into union.
	Remove OMP_ATOMIC_SEQ_CST comment.
	(enum omp_clause_depend_kind): Add OMP_CLAUSE_DEPEND_MUTEXINOUTSET
	and OMP_CLAUSE_DEPEND_DEPOBJ.
	(struct tree_omp_clause): Add subcode.defaultmap_kind.
	* tree.def (OMP_TASKGROUP): Add another operand, move next to other
	OpenMP constructs with body and clauses operands.
	* tree.h (OMP_BODY): Use OMP_MASTER instead of OMP_TASKGROUP.
	(OMP_CLAUSES): Use OMP_TASKGROUP instead of OMP_SINGLE.
	(OMP_TASKGROUP_CLAUSES): Define.
	(OMP_CLAUSE_DECL): Use OMP_CLAUSE__REDUCTEMP_ instead of
	OMP_CLAUSE__LOOPTEMP_.
	(OMP_ATOMIC_SEQ_CST): Remove.
	(OMP_ATOMIC_MEMORY_ORDER, OMP_CLAUSE_FIRSTPRIVATE_NO_REFERENCE,
	OMP_CLAUSE_LASTPRIVATE_CONDITIONAL): Define.
	(OMP_CLAUSE_REDUCTION_CODE, OMP_CLAUSE_REDUCTION_INIT,
	OMP_CLAUSE_REDUCTION_MERGE, OMP_CLAUSE_REDUCTION_PLACEHOLDER,
	OMP_CLAUSE_REDUCTION_DECL_PLACEHOLDER,
	OMP_CLAUSE_REDUCTION_OMP_ORIG_REF): Handle
	OMP_CLAUSE_{,IN_,TASK_}REDUCTION.
	(OMP_CLAUSE_REDUCTION_TASK, OMP_CLAUSE_REDUCTION_INSCAN,
	OMP_CLAUSE_DEFAULTMAP_KIND, OMP_CLAUSE_DEFAULTMAP_CATEGORY,
	OMP_CLAUSE_DEFAULTMAP_BEHAVIOR, OMP_CLAUSE_DEFAULTMAP_SET_KIND):
	Define.
	* tree-inline.c (remap_gimple_stmt): Remap taskgroup clauses.
	* tree-nested.c (convert_nonlocal_omp_clauses): Handle
	OMP_CLAUSE__REDUCTEMP_, OMP_CLAUSE_NONTEMPORAL.
	(convert_local_omp_clauses): Likewise.  Remove useless test.
	* tree-parloops.c (create_call_for_reduction_1): Pass
	OMP_MEMORY_ORDER_RELAXED as new argument to
	dump_gimple_omp_atomic_load and dump_gimple_omp_atomic_store.
	* tree-pretty-print.c (dump_omp_iterators): New function.
	(dump_omp_clause): Handle OMP_CLAUSE__REDUCTEMP_,
	OMP_CLAUSE_NONTEMPORAL, OMP_CLAUSE_{TASK,IN}_REDUCTION.  Print
	reduction modifiers.  Handle OMP_CLAUSE_DEPEND_DEPOBJ and
	OMP_CLAUSE_DEPEND_MUTEXINOUTSET.  Print iterators in depend clauses.
	Print __internal__ for OMP_CLAUSE_DEPEND_LAST.  Handle cancel and
	simd OMP_CLAUSE_IF_MODIFIERs.  Handle new kinds of
	OMP_CLAUSE_DEFAULTMAP. Print conditional: for
	OMP_CLAUSE_LASTPRIVATE_CONDITIONAL.
	(dump_omp_atomic_memory_order): New function.
	(dump_generic_node): Use it.  Print taskgroup clauses.  Print
	taskwait with depend clauses.
	* tree-pretty-print.h (dump_omp_atomic_memory_order): Declare.
	* tree-streamer-in.c (unpack_ts_omp_clause_value_fields):
	Handle OMP_CLAUSE_{TASK,IN}_REDUCTION.
	* tree-streamer-out.c (pack_ts_omp_clause_value_fields,
	write_ts_omp_clause_tree_pointers): Likewise.
gcc/c-family/
	* c-common.h (c_finish_omp_taskgroup): Add CLAUSES argument.
	(c_finish_omp_atomic): Replace bool SEQ_CST argument with
	enum omp_memory_order MEMORY_ORDER.
	(c_finish_omp_flush): Add MO argument.
	(c_omp_depend_t_p, c_finish_omp_depobj): Declare.
	(c_finish_omp_for): Add FINAL_P argument.
	* c-omp.c: Include memmodel.h.
	(c_finish_omp_taskgroup): Add CLAUSES argument.  Set
	OMP_TASKGROUP_CLAUSES to it.
	(c_finish_omp_atomic): Replace bool SEQ_CST argument with
	enum omp_memory_order MEMORY_ORDER.  Set OMP_ATOMIC_MEMORY_ORDER
	instead of OMP_ATOMIC_SEQ_CST.
	(c_omp_depend_t_p, c_finish_omp_depobj): New functions.
	(c_finish_omp_flush): Add MO argument, if not MEMMODEL_LAST, emit
	__atomic_thread_fence call with the given value.
	(check_omp_for_incr_expr): Formatting fixes.
	(c_finish_omp_for): Add FINAL_P argument.  Allow NE_EXPR
	even in OpenMP loops, diagnose if NE_EXPR and incr expression
	is not constant expression 1 or -1.  Transform NE_EXPR loops
	with iterators pointers to VLA into LT_EXPR or GT_EXPR loops.
	(c_omp_check_loop_iv_r): Look for orig decl of C++ range for
	loops too.
	(c_omp_split_clauses): Add support for combined
	#pragma omp parallel master and
	#pragma omp {,parallel }master taskloop{, simd} constructs.
	Handle OMP_CLAUSE_IN_REDUCTION.  Handle OMP_CLAUSE_REDUCTION_TASK.
	Handle OMP_CLAUSE_NONTEMPORAL.  Handle splitting OMP_CLAUSE_IF
	also to OMP_SIMD.  Copy OMP_CLAUSE_LASTPRIVATE_CONDITIONAL.
	(c_omp_predetermined_sharing): Don't return
	OMP_CLAUSE_DEFAULT_SHARED for const qualified decls.
	* c-pragma.c (omp_pragmas): Add PRAGMA_OMP_DEPOBJ and
	PRAGMA_OMP_REQUIRES.
	* c-pragma.h (enum pragma_kind): Likewise.
	(enum pragma_omp_clause): Add PRAGMA_OMP_CLAUSE_NONTEMPORAL
	and PRAGMA_OMP_CLAUSE_{IN,TASK}_REDUCTION.
gcc/c/
	* c-parser.c: Include memmode.h.
	(c_parser_omp_depobj, c_parser_omp_requires): New functions.
	(c_parser_pragma): Handle PRAGMA_OMP_DEPOBJ and PRAGMA_OMP_REQUIRES.
	(c_parser_omp_clause_name): Handle nontemporal, in_reduction and
	task_reduction clauses.
	(c_parser_omp_variable_list): Handle OMP_CLAUSE_{IN,TASK}_REDUCTION.
	For OMP_CLAUSE_DEPEND, parse clause operands as either an array
	section, or lvalue assignment expression.
	(c_parser_omp_clause_if): Handle cancel and simd modifiers.
	(c_parser_omp_clause_lastprivate): Parse optional
	conditional: modifier.
	(c_parser_omp_clause_hint): Require constant integer expression rather
	than just integer expression.
	(c_parser_omp_clause_defaultmap): Parse new kinds of defaultmap
	clause.
	(c_parser_omp_clause_reduction): Add IS_OMP and KIND arguments.
	Parse reduction modifiers.  Pass KIND to c_parser_omp_variable_list.
	(c_parser_omp_clause_nontemporal, c_parser_omp_iterators): New
	functions.
	(c_parser_omp_clause_depend): Parse iterator modifier and handle
	iterators.  Parse mutexinoutset and depobj kinds.
	(c_parser_oacc_all_clauses): Adjust c_parser_omp_clause_reduction
	callers.
	(c_parser_omp_all_clauses): Likewise.  Handle
	PRAGMA_OMP_CLAUSE_NONTEMPORAL and
	PRAGMA_OMP_CLAUSE_{IN,TASK}_REDUCTION.
	(c_parser_omp_atomic): Parse hint and memory order clauses.  Handle
	default memory order from requires directive if any.  Adjust
	c_finish_omp_atomic caller.
	(c_parser_omp_critical): Allow comma in between (name) and hint clause.
	(c_parser_omp_flush): Parse flush with memory-order-clause.
	(c_parser_omp_for_loop): Allow NE_EXPR even in
	OpenMP loops, adjust c_finish_omp_for caller.
	(OMP_SIMD_CLAUSE_MASK): Add if and nontemporal clauses.
	(c_parser_omp_master): Add p_name, mask and cclauses arguments.
	Allow to be called while parsing combined parallel master.
	Parse combined master taskloop{, simd}.
	(c_parser_omp_parallel): Parse combined
	parallel master{, taskloop{, simd}} constructs.
	(OMP_TASK_CLAUSE_MASK): Add in_reduction clause.
	(OMP_TASKGROUP_CLAUSE_MASK): Define.
	(c_parser_omp_taskgroup): Add LOC argument.  Parse taskgroup clauses.
	(OMP_TASKWAIT_CLAUSE_MASK): Define.
	(c_parser_omp_taskwait): Handle taskwait with depend clauses.
	(c_parser_omp_teams): Force a BIND_EXPR with BLOCK
	around teams body.  Use SET_EXPR_LOCATION.
	(c_parser_omp_target_data): Allow target data
	with only use_device_ptr clauses.
	(c_parser_omp_target): Use SET_EXPR_LOCATION.  Set
	OMP_REQUIRES_TARGET_USED bit in omp_requires_mask.
	(c_parser_omp_requires): New function.
	(c_finish_taskloop_clauses): New function.
	(OMP_TASKLOOP_CLAUSE_MASK): Add reduction and in_reduction clauses.
	(c_parser_omp_taskloop): Use c_finish_taskloop_clauses.  Add forward
	declaration.  Disallow in_reduction clause when combined with parallel
	master.
	(c_parser_omp_construct): Adjust c_parser_omp_master and
	c_parser_omp_taskgroup callers.
	* c-typeck.c (c_finish_omp_cancel): Diagnose if clause with modifier
	other than cancel.
	(handle_omp_array_sections_1): Handle OMP_CLAUSE_{IN,TASK}_REDUCTION
	like OMP_CLAUSE_REDUCTION.
	(handle_omp_array_sections): Likewise.  Call save_expr on array
	reductions before calling build_index_type.  Handle depend clauses
	with iterators.
	(struct c_find_omp_var_s): New type.
	(c_find_omp_var_r, c_omp_finish_iterators): New functions.
	(c_finish_omp_clauses): Don't diagnose nonmonotonic clause
	with static, runtime or auto schedule kinds.  Call save_expr for whole
	array reduction sizes.  Diagnose reductions with zero sized elements
	or variable length structures.  Diagnose nogroup clause used with
	reduction clause(s).  Handle depend clause with
	OMP_CLAUSE_DEPEND_DEPOBJ.  Diagnose bit-fields.  Require
	omp_depend_t type for OMP_CLAUSE_DEPEND_DEPOBJ kinds and
	some different type for other kinds.  Use build_unary_op with
	ADDR_EXPR and build_indirect_ref instead of c_mark_addressable.
	Handle depend clauses with iterators.  Remove no longer needed special
	case that predetermined const qualified vars may be specified in
	firstprivate clause.  Complain if const qualified vars are mentioned
	in data-sharing clauses other than firstprivate or shared.  Use
	error_at with OMP_CLAUSE_LOCATION (c) as first argument instead of
	error.  Formatting fix.  Handle OMP_CLAUSE_NONTEMPORAL and
	OMP_CLAUSE_{IN,TASK}_REDUCTION.  Allow any lvalue as
	OMP_CLAUSE_DEPEND operand (besides array section), adjust diagnostics.
gcc/cp/
	* constexpr.c (potential_constant_expression_1): Handle OMP_DEPOBJ.
	* cp-gimplify.c (cp_genericize_r): Handle
	OMP_CLAUSE_{IN,TASK}_REDUCTION.
	(cxx_omp_predetermined_sharing_1): Don't return
	OMP_CLAUSE_DEFAULT_SHARED for const qualified decls with no mutable
	member.  Return OMP_CLAUSE_DEFAULT_FIRSTPRIVATE for this pointer.
	* cp-objcp-common.c (cp_common_init_ts): Handle OMP_DEPOBJ.
	* cp-tree.def (OMP_DEPOBJ): New tree code.
	* cp-tree.h (OMP_ATOMIC_DEPENDENT_P): Return true also for first
	argument being OMP_CLAUSE.
	(OMP_DEPOBJ_DEPOBJ, OMP_DEPOBJ_CLAUSES): Define.
	(cp_convert_omp_range_for, cp_finish_omp_range_for): Declare.
	(finish_omp_atomic): Add LOC, CLAUSES and MO arguments.  Remove
	SEQ_CST argument.
	(finish_omp_for_block): Declare.
	(finish_omp_flush): Add MO argument.
	(finish_omp_depobj): Declare.
	* cxx-pretty-print.c (cxx_pretty_printer::statement): Handle
	OMP_DEPOBJ.
	* dump.c (cp_dump_tree): Likewise.
	* lex.c (cxx_init): Likewise.
	* parser.c: Include memmodel.h.
	(cp_parser_for): Pass false as new is_omp argument to
	cp_parser_range_for.
	(cp_parser_range_for): Add IS_OMP argument, return before finalizing
	if it is true.
	(cp_parser_omp_clause_name): Handle nontemporal, in_reduction and
	task_reduction clauses.
        (cp_parser_omp_var_list_no_open): Handle
	OMP_CLAUSE_{IN,TASK}_REDUCTION.  For OMP_CLAUSE_DEPEND, parse clause
	operands as either an array section, or lvalue assignment expression.
	(cp_parser_omp_clause_if): Handle cancel and simd modifiers.
	(cp_parser_omp_clause_defaultmap): Parse new kinds of defaultmap
	clause.
	(cp_parser_omp_clause_reduction): Add IS_OMP and KIND arguments.
	Parse reduction modifiers.  Pass KIND to c_parser_omp_variable_list.
	(cp_parser_omp_clause_lastprivate, cp_parser_omp_iterators): New
	functions.
	(cp_parser_omp_clause_depend): Parse iterator modifier and handle
	iterators.  Parse mutexinoutset and depobj kinds.
	(cp_parser_oacc_all_clauses): Adjust cp_parser_omp_clause_reduction
	callers.
	(cp_parser_omp_all_clauses): Likewise.  Handle
	PRAGMA_OMP_CLAUSE_NONTEMPORAL and
	PRAGMA_OMP_CLAUSE_{IN,TASK}_REDUCTION.  Call
	cp_parser_omp_clause_lastprivate for OpenMP lastprivate clause.
	(cp_parser_omp_atomic): Pass pragma_tok->location as
	LOC to finish_omp_atomic.  Parse hint and memory order clauses.
	Handle default memory order from requires directive if any.  Adjust
	finish_omp_atomic caller.
	(cp_parser_omp_critical): Allow comma in between (name) and hint
	clause.
	(cp_parser_omp_depobj): New function.
	(cp_parser_omp_flush): Parse flush with memory-order-clause.
	(cp_parser_omp_for_cond): Allow NE_EXPR even in OpenMP loops.
	(cp_convert_omp_range_for, cp_finish_omp_range_for): New functions.
	(cp_parser_omp_for_loop): Parse C++11 range for loops among omp
	loops.  Handle OMP_CLAUSE_IN_REDUCTION like OMP_CLAUSE_REDUCTION.
	(OMP_SIMD_CLAUSE_MASK): Add if and nontemporal clauses.
	(cp_parser_omp_simd, cp_parser_omp_for): Call keep_next_level before
	begin_omp_structured_block and call finish_omp_for_block on
	finish_omp_structured_block result.
	(cp_parser_omp_master): Add p_name, mask and cclauses arguments.
	Allow to be called while parsing combined parallel master.
	Parse combined master taskloop{, simd}.
	(cp_parser_omp_parallel): Parse combined
	parallel master{, taskloop{, simd}} constructs.
	(cp_parser_omp_single): Use SET_EXPR_LOCATION.
	(OMP_TASK_CLAUSE_MASK): Add in_reduction clause.
	(OMP_TASKWAIT_CLAUSE_MASK): Define.
	(cp_parser_omp_taskwait): Handle taskwait with depend clauses.
	(OMP_TASKGROUP_CLAUSE_MASK): Define.
	(cp_parser_omp_taskgroup): Parse taskgroup clauses, adjust
	c_finish_omp_taskgroup caller.
	(cp_parser_omp_distribute): Call keep_next_level before
	begin_omp_structured_block and call finish_omp_for_block on
	finish_omp_structured_block result.
	(cp_parser_omp_teams): Force a BIND_EXPR with BLOCK around teams
	body.
	(cp_parser_omp_target_data): Allow target data with only
	use_device_ptr clauses.
	(cp_parser_omp_target): Set OMP_REQUIRES_TARGET_USED bit in
	omp_requires_mask.
	(cp_parser_omp_requires): New function.
	(OMP_TASKLOOP_CLAUSE_MASK): Add reduction and in_reduction clauses.
	(cp_parser_omp_taskloop): Add forward declaration.  Disallow
	in_reduction clause when combined with parallel master.  Call
	keep_next_level before begin_omp_structured_block and call
	finish_omp_for_block on finish_omp_structured_block result.
	(cp_parser_omp_construct): Adjust cp_parser_omp_master caller.
	(cp_parser_pragma): Handle PRAGMA_OMP_DEPOBJ and PRAGMA_OMP_REQUIRES.
	* pt.c (tsubst_omp_clause_decl): Add iterators_cache argument.
	Adjust recursive calls.  Handle iterators.
	(tsubst_omp_clauses): Handle OMP_CLAUSE_{IN,TASK}_REDUCTION and
	OMP_CLAUSE_NONTEMPORAL.  Adjust tsubst_omp_clause_decl callers.
	(tsubst_decomp_names):
	(tsubst_omp_for_iterator): Change orig_declv into a reference.
	Handle range for loops.  Move orig_declv handling after declv/initv
	handling.
	(tsubst_expr): Force a BIND_EXPR with BLOCK around teams body.
	Adjust finish_omp_atomic caller.  Call keep_next_level before
	begin_omp_structured_block.  Call cp_finish_omp_range_for for range
	for loops and use {begin,finish}_omp_structured_block instead of
	{push,pop}_stmt_list if there are any range for loops.  Call
	finish_omp_for_block on finish_omp_structured_block result.
	Handle OMP_DEPOBJ.  Handle taskwait with depend clauses.  For
	OMP_ATOMIC call tsubst_omp_clauses on clauses if any, adjust
	finish_omp_atomic caller.  Use OMP_ATOMIC_MEMORY_ORDER rather
	than OMP_ATOMIC_SEQ_CST.  Handle clauses on OMP_TASKGROUP.
	(dependent_omp_for_p): Always return true for range for loops if
	processing_template_decl.  Return true if class type iterator
	does not have INTEGER_CST increment.
	* semantics.c: Include memmodel.h.
	(handle_omp_array_sections_1): Handle OMP_CLAUSE_{IN,TASK}_REDUCTION
	like OMP_CLAUSE_REDUCTION.
	(handle_omp_array_sections): Likewise.  Call save_expr on array
	reductions before calling build_index_type.  Handle depend clauses
	with iterators.
	(finish_omp_reduction_clause): Call save_expr for whole array
	reduction sizes.  Don't mark OMP_CLAUSE_DECL addressable if it has
	reference type.  Do mark decl_placeholder addressable if needed.
	Use error_at with OMP_CLAUSE_LOCATION (c) as first argument instead
	of error.
	(cp_omp_finish_iterators): New function.
	(finish_omp_clauses): Don't diagnose nonmonotonic clause with static,
	runtime or auto schedule kinds.  Diagnose nogroup clause used with
	reduction clause(s).  Handle depend clause with
	OMP_CLAUSE_DEPEND_DEPOBJ.  Diagnose bit-fields.  Require
	omp_depend_t type for OMP_CLAUSE_DEPEND_DEPOBJ kinds and
	some different type for other kinds.  Use cp_build_addr_expr
	and cp_build_indirect_ref instead of cxx_mark_addressable.
	Handle depend clauses with iterators.  Only handle static data members
	in the special case that const qualified vars may be specified in
	firstprivate clause.  Complain if const qualified vars without mutable
	members are mentioned in data-sharing clauses other than firstprivate
	or shared.  Use error_at with OMP_CLAUSE_LOCATION (c) as first
	argument instead of error.  Diagnose more than one nontemporal clause
	refering to the same variable.  Use error_at rather than error for
	priority and hint clause diagnostics.  Fix pasto for hint clause.
	Diagnose hint expression that doesn't fold into INTEGER_CST.
	Diagnose if clause with modifier other than cancel.  Handle
	OMP_CLAUSE_{IN,TASK}_REDUCTION like OMP_CLAUSE_REDUCTION.  Allow any
	lvalue as OMP_CLAUSE_DEPEND operand (besides array section), adjust
	diagnostics.
	(handle_omp_for_class_iterator): Don't create a new TREE_LIST if one
	has been created already for range for, just fill TREE_PURPOSE and
	TREE_VALUE.  Call cp_fully_fold on incr.
	(finish_omp_for): Don't check cond/incr if cond is global_namespace.
	Pass to c_omp_check_loop_iv_exprs orig_declv if non-NULL.  Don't
	use IS_EMPTY_STMT on NULL pre_body.  Adjust c_finish_omp_for caller.
	(finish_omp_for_block): New function.
	(finish_omp_atomic): Add LOC argument, pass it through
	to c_finish_omp_atomic and set it as location of OMP_ATOMIC* trees.
	Remove SEQ_CST argument.  Add CLAUSES and MO arguments.  Adjust
	c_finish_omp_atomic caller.  Stick clauses if any into first argument
	of wrapping OMP_ATOMIC.
	(finish_omp_depobj): New function.
	(finish_omp_flush): Add MO argument, if not
	MEMMODEL_LAST, emit __atomic_thread_fence call with the given value.
	(finish_omp_cancel): Diagnose if clause with modifier other than
	cancel.
gcc/fortran/
	* trans-openmp.c (gfc_trans_omp_clauses): Use
	OMP_CLAUSE_DEFAULTMAP_SET_KIND.
	(gfc_trans_omp_atomic): Set OMP_ATOMIC_MEMORY_ORDER
	rather than OMP_ATOMIC_SEQ_CST.
	(gfc_trans_omp_taskgroup): Build OMP_TASKGROUP using
	make_node instead of build1_loc.
	* types.def (BT_FN_VOID_BOOL, BT_FN_VOID_SIZE_SIZE_PTR,
	BT_FN_UINT_UINT_PTR_PTR, BT_FN_UINT_OMPFN_PTR_UINT_UINT,
	BT_FN_BOOL_UINT_LONGPTR_LONG_LONG_LONGPTR_LONGPTR_PTR_PTR,
	BT_FN_BOOL_UINT_ULLPTR_LONG_ULL_ULLPTR_ULLPTR_PTR_PTR,
	BT_FN_BOOL_LONG_LONG_LONG_LONG_LONG_LONGPTR_LONGPTR_PTR_PTR,
	BT_FN_BOOL_BOOL_ULL_ULL_ULL_LONG_ULL_ULLPTR_ULLPTR_PTR_PTR): New.
	(BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_PTR): Formatting fix.
gcc/testsuite/
	* c-c++-common/gomp/atomic-17.c: New test.
	* c-c++-common/gomp/atomic-18.c: New test.
	* c-c++-common/gomp/atomic-19.c: New test.
	* c-c++-common/gomp/atomic-20.c: New test.
	* c-c++-common/gomp/atomic-21.c: New test.
	* c-c++-common/gomp/atomic-22.c: New test.
	* c-c++-common/gomp/clauses-1.c (r2): New variable.
	(foo): Add ntm argument and test if and nontemporal clauses on
	constructs with simd.
	(bar): Put taskloop simd inside of taskgroup with task_reduction,
	use in_reduction clause instead of reduction.  Add another
	taskloop simd without nogroup clause, but with reduction clause and
	a new in_reduction.  Add ntm and i3 arguments.  Test if and
	nontemporal clauses on constructs with simd.  Change if clauses on
	some constructs from specific to the particular constituents to one
	without a modifier.  Add new tests for combined host teams and for
	new parallel master and {,parallel }master taskloop{, simd} combined
	constructs.
	(baz): New function with host teams tests.
	* gcc.dg/gomp/combined-1.c: Moved to ...
	* c-c++-common/gomp/combined-1.c: ... here.  Adjust expected library
	call.
	* c-c++-common/gomp/combined-2.c: New test.
	* c-c++-common/gomp/combined-3.c: New test.
	* c-c++-common/gomp/critical-1.c: New test.
	* c-c++-common/gomp/critical-2.c: New test.
	* c-c++-common/gomp/default-1.c: New test.
	* c-c++-common/gomp/defaultmap-1.c: New test.
	* c-c++-common/gomp/defaultmap-2.c: New test.
	* c-c++-common/gomp/defaultmap-3.c: New test.
	* c-c++-common/gomp/depend-5.c: New test.
	* c-c++-common/gomp/depend-6.c: New test.
	* c-c++-common/gomp/depend-iterator-1.c: New test.
	* c-c++-common/gomp/depend-iterator-2.c: New test.
	* c-c++-common/gomp/depobj-1.c: New test.
	* c-c++-common/gomp/flush-1.c: New test.
	* c-c++-common/gomp/flush-2.c: New test.
	* c-c++-common/gomp/for-1.c: New test.
	* c-c++-common/gomp/for-2.c: New test.
	* c-c++-common/gomp/for-3.c: New test.
	* c-c++-common/gomp/for-4.c: New test.
	* c-c++-common/gomp/for-5.c: New test.
	* c-c++-common/gomp/for-6.c: New test.
	* c-c++-common/gomp/for-7.c: New test.
	* c-c++-common/gomp/if-1.c (foo): Add some further tests.
	* c-c++-common/gomp/if-2.c (foo): Likewise.  Expect slightly different
	diagnostics wording in one case.
	* c-c++-common/gomp/if-3.c: New test.
	* c-c++-common/gomp/master-combined-1.c: New test.
	* c-c++-common/gomp/master-combined-2.c: New test.
	* c-c++-common/gomp/nontemporal-1.c: New test.
	* c-c++-common/gomp/nontemporal-2.c: New test.
	* c-c++-common/gomp/reduction-task-1.c: New test.
	* c-c++-common/gomp/reduction-task-2.c: New test.
	* c-c++-common/gomp/requires-1.c: New test.
	* c-c++-common/gomp/requires-2.c: New test.
	* c-c++-common/gomp/requires-3.c: New test.
	* c-c++-common/gomp/requires-4.c: New test.
	* c-c++-common/gomp/schedule-modifiers-1.c (bar): Don't expect
	diagnostics for nonmonotonic modifier with static, runtime or auto
	schedule kinds.
	* c-c++-common/gomp/simd7.c: New test.
	* c-c++-common/gomp/target-data-1.c: New test.
	* c-c++-common/gomp/taskloop-reduction-1.c: New test.
	* c-c++-common/gomp/taskwait-depend-1.c: New test.
	* c-c++-common/gomp/teams-1.c: New test.
	* c-c++-common/gomp/teams-2.c: New test.
	* gcc.dg/gomp/appendix-a/a.24.1.c: Update from OpenMP examples.  Add
	shared(c) clause.
	* gcc.dg/gomp/atomic-5.c (f1): Add another expected error.
	* gcc.dg/gomp/clause-1.c: Adjust expected diagnostics for const
	qualified vars without mutable member no longer being predeterined
	shared.
	* gcc.dg/gomp/sharing-1.c: Likewise.
	* g++.dg/gomp/clause-3.C: Likewise.
	* g++.dg/gomp/member-2.C: Likewise.
	* g++.dg/gomp/predetermined-1.C: Likewise.
	* g++.dg/gomp/private-1.C: Likewise.
	* g++.dg/gomp/sharing-1.C: Likewise.
	* g++.dg/gomp/sharing-2.C: Likewise.  Add a few tests with aggregate
	const static data member without mutable elements.
	* gcc.dg/gomp/for-4.c: Expected nonmonotonic functions in the dumps.
	* gcc.dg/gomp/for-5.c: Likewise.
	* gcc.dg/gomp/for-6.c: Change expected library call.
	* gcc.dg/gomp/pr39495-2.c (foo): Don't expect errors on !=.
	* gcc.dg/gomp/reduction-2.c: New test.
	* gcc.dg/gomp/simd-1.c: New test.
	* gcc.dg/gomp/teams-1.c: Adjust expected diagnostic lines.
	* g++.dg/gomp/atomic-18.C: New test.
	* g++.dg/gomp/atomic-19.C: New test.
	* g++.dg/gomp/atomic-5.C (f1): Adjust expected lines of read-only
	variable messages.  Add another expected error.
	* g++.dg/gomp/critical-3.C: New test.
	* g++.dg/gomp/depend-iterator-1.C: New test.
	* g++.dg/gomp/depend-iterator-2.C: New test.
	* g++.dg/gomp/depobj-1.C: New test.
	* g++.dg/gomp/doacross-1.C: New test.
	* g++.dg/gomp/for-21.C: New test.
	* g++.dg/gomp/for-4.C: Expected nonmonotonic functions in the dumps.
	* g++.dg/gomp/for-5.C: Likewise.
	* g++.dg/gomp/for-6.C: Change expected library call.
	* g++.dg/gomp/loop-4.C: New test.
	* g++.dg/gomp/pr33372-1.C: Adjust location of the expected
	diagnostics.
	* g++.dg/gomp/pr33372-3.C: Likewise.
	* g++.dg/gomp/pr39495-2.C (foo): Don't expect errors on !=.
	* g++.dg/gomp/simd-2.C: New test.
	* g++.dg/gomp/tpl-atomic-2.C: Adjust expected diagnostic lines.
include/
	* gomp-constants.h (GOMP_TASK_FLAG_REDUCTION,
	GOMP_DEPEND_IN, GOMP_DEPEND_OUT, GOMP_DEPEND_INOUT,
	GOMP_DEPEND_MUTEXINOUTSET): Define.
libgomp/
	* affinity.c (gomp_display_affinity_place): New function.
	* affinity-fmt.c: New file.
	* alloc.c (gomp_aligned_alloc, gomp_aligned_free): New functions.
	* config/linux/affinity.c (gomp_display_affinity_place): New function.
	* config/nvptx/icv-device.c (omp_get_num_teams, omp_get_team_num):
	Move these functions to ...
	* config/nvptx/teams.c: ... here.  New file.
	* config/nvptx/target.c (omp_pause_resource, omp_pause_resource_all):
	New functions.
	* config/nvptx/team.c (gomp_team_start, gomp_pause_host): New
	functions.
	* configure.ac: Check for aligned_alloc, posix_memalign, memalign
	and _aligned_malloc.
	(HAVE_UNAME, HAVE_GETHOSTNAME, HAVE_GETPID): Add new tests.
	* configure.tgt: Add -DUSING_INITIAL_EXEC_TLS to XCFLAGS for Linux.
	* env.c (gomp_display_affinity_var, gomp_affinity_format_var,
	gomp_affinity_format_len): New variables.
	(parse_schedule): Parse monotonic and nonmonotonic modifiers in
	OMP_SCHEDULE variable.  Set GFS_MONOTONIC for monotonic schedules.
	(handle_omp_display_env): Display monotonic/nonmonotonic schedule
	modifiers.  Display (non-default) chunk sizes.  Print
	OMP_DISPLAY_AFFINITY and OMP_AFFINITY_FORMAT.
	(initialize_env): Don't call pthread_attr_setdetachstate.  Handle
	OMP_DISPLAY_AFFINITY and OMP_AFFINITY_FORMAT env vars.
	* fortran.c: Include stdio.h and string.h.
	(omp_pause_resource, omp_pause_resource_all): Add ialias_redirect.
	(omp_get_schedule_, omp_get_schedule_8_): Mask off GFS_MONOTONIC bit.
	(omp_set_affinity_format_, omp_get_affinity_format_,
	omp_display_affinity_, omp_capture_affinity_, omp_pause_resource_,
	omp_pause_resource_all_): New functions.
	* icv.c (omp_set_schedule): Mask off omp_sched_monotonic bit in
	switch.
	* icv-device.c (omp_get_num_teams, omp_get_team_num): Move these
	functions to ...
	* teams.c: ... here.  New file.
	* libgomp_g.h: Include gstdint.h.
	(GOMP_loop_nonmonotonic_runtime_start,
	GOMP_loop_maybe_nonmonotonic_runtime_start, GOMP_loop_start,
	GOMP_loop_ordered_start, GOMP_loop_nonmonotonic_runtime_next,
	GOMP_loop_maybe_nonmonotonic_runtime_next, GOMP_loop_doacross_start,
	GOMP_parallel_loop_nonmonotonic_runtime,
	GOMP_parallel_loop_maybe_nonmonotonic_runtime,
	GOMP_loop_ull_nonmonotonic_runtime_start,
	GOMP_loop_ull_maybe_nonmonotonic_runtime_start, GOMP_loop_ull_start,
	GOMP_loop_ull_ordered_start, GOMP_loop_ull_nonmonotonic_runtime_next,
	GOMP_loop_ull_maybe_nonmonotonic_runtime_next,
	GOMP_loop_ull_doacross_start, GOMP_parallel_reductions,
	GOMP_taskwait_depend, GOMP_taskgroup_reduction_register,
	GOMP_taskgroup_reduction_unregister, GOMP_task_reduction_remap,
	GOMP_workshare_task_reduction_unregister, GOMP_sections2_start,
	GOMP_teams_reg): Declare.
	* libgomp.h (GOMP_HAVE_EFFICIENT_ALIGNED_ALLOC): Define unless
	gomp_aligned_alloc uses fallback implementation.
	(gomp_aligned_alloc, gomp_aligned_free): Declare.
	(enum gomp_schedule_type): Add GFS_MONOTONIC.
	(struct gomp_doacross_work_share): Add extra field.
	(struct gomp_work_share): Add task_reductions field.
	(struct gomp_taskgroup): Add workshare and reductions fields.
	(GOMP_NEEDS_THREAD_HANDLE): Define if needed.
	(gomp_thread_handle): New typedef.
	(gomp_display_affinity_place, gomp_set_affinity_format,
	gomp_display_string, gomp_display_affinity,
	gomp_display_affinity_thread): Declare.
	(gomp_doacross_init, gomp_doacross_ull_init): Add size_t argument.
	(gomp_parallel_reduction_register, gomp_workshare_taskgroup_start,
	gomp_workshare_task_reduction_register): Declare.
	(gomp_team_start): Add taskgroup argument.
	(gomp_pause_host): Declare.
	(gomp_init_work_share, gomp_work_share_start): Change bool argument
	to size_t.
	(gomp_thread_self, gomp_thread_to_pthread_t): New inline functions.
	* libgomp.map (GOMP_5.0): Export GOMP_loop_start,
	GOMP_loop_ordered_start, GOMP_loop_doacross_start,
	GOMP_loop_ull_start, GOMP_loop_ull_ordered_start,
	GOMP_loop_ull_doacross_start,
	GOMP_workshare_task_reduction_unregister, GOMP_sections2_start,
	GOMP_loop_maybe_nonmonotonic_runtime_next,
	GOMP_loop_maybe_nonmonotonic_runtime_start,
	GOMP_loop_nonmonotonic_runtime_next,
	GOMP_loop_nonmonotonic_runtime_start,
	GOMP_loop_ull_maybe_nonmonotonic_runtime_next,
	GOMP_loop_ull_maybe_nonmonotonic_runtime_start,
	GOMP_loop_ull_nonmonotonic_runtime_next,
	GOMP_loop_ull_nonmonotonic_runtime_start,
	GOMP_parallel_loop_maybe_nonmonotonic_runtime,
	GOMP_parallel_loop_nonmonotonic_runtime, GOMP_parallel_reductions,
	GOMP_taskgroup_reduction_register,
	GOMP_taskgroup_reduction_unregister, GOMP_task_reduction_remap,
	GOMP_teams_reg and GOMP_taskwait_depend.
	(OMP_5.0): Export omp_pause_resource{,_all}{,_},
	omp_{capture,display}_affinity{,_}, and
	omp_[gs]et_affinity_format{,_}.
	* loop.c: Include string.h.
	(GOMP_loop_runtime_next): Add ialias.
	(GOMP_taskgroup_reduction_register): Add ialias_redirect.
	(gomp_loop_static_start, gomp_loop_dynamic_start,
	gomp_loop_guided_start, gomp_loop_ordered_static_start,
	gomp_loop_ordered_dynamic_start, gomp_loop_ordered_guided_start,
	gomp_loop_doacross_static_start, gomp_loop_doacross_dynamic_start,
	gomp_loop_doacross_guided_start): Adjust gomp_work_share_start
	or gomp_doacross_init callers.
	(gomp_adjust_sched, GOMP_loop_start, GOMP_loop_ordered_start,
	GOMP_loop_doacross_start): New functions.
	(GOMP_loop_runtime_start, GOMP_loop_ordered_runtime_start,
	GOMP_loop_doacross_runtime_start, GOMP_parallel_loop_runtime_start):
	Mask off GFS_MONOTONIC bit.
	(GOMP_loop_maybe_nonmonotonic_runtime_next,
	GOMP_loop_maybe_nonmonotonic_runtime_start,
	GOMP_loop_nonmonotonic_runtime_next,
	GOMP_loop_nonmonotonic_runtime_start,
	GOMP_parallel_loop_maybe_nonmonotonic_runtime,
	GOMP_parallel_loop_nonmonotonic_runtime): New aliases or wrapper
	functions.
	(gomp_parallel_loop_start): Pass NULL as taskgroup to
	gomp_team_start.
	* loop_ull.c: Include string.h.
	(GOMP_loop_ull_runtime_next): Add ialias.
	(GOMP_taskgroup_reduction_register): Add ialias_redirect.
	(gomp_loop_ull_static_start, gomp_loop_ull_dynamic_start,
	gomp_loop_ull_guided_start, gomp_loop_ull_ordered_static_start,
	gomp_loop_ull_ordered_dynamic_start,
	gomp_loop_ull_ordered_guided_start,
	gomp_loop_ull_doacross_static_start,
	gomp_loop_ull_doacross_dynamic_start,
	gomp_loop_ull_doacross_guided_start): Adjust gomp_work_share_start
	and gomp_doacross_ull_init callers.
	(gomp_adjust_sched, GOMP_loop_ull_start, GOMP_loop_ull_ordered_start,
	GOMP_loop_ull_doacross_start): New functions.
	(GOMP_loop_ull_runtime_start,
	GOMP_loop_ull_ordered_runtime_start,
	GOMP_loop_ull_doacross_runtime_start): Mask off GFS_MONOTONIC bit.
	(GOMP_loop_ull_maybe_nonmonotonic_runtime_next,
	GOMP_loop_ull_maybe_nonmonotonic_runtime_start,
	GOMP_loop_ull_nonmonotonic_runtime_next,
	GOMP_loop_ull_nonmonotonic_runtime_start): Likewise.
	* Makefile.am (libgomp_la_SOURCES): Add teams.c and affinity-fmt.c.
	* omp.h.in (enum omp_sched_t): Add omp_sched_monotonic.
	(omp_pause_resource_t, omp_depend_t): New typedefs.
	(enum omp_lock_hint_t): Renamed to ...
	(enum omp_sync_hint_t): ... this.  Define omp_sync_hint_*
	enumerators using numbers and omp_lock_hint_* as their aliases.
	(omp_lock_hint_t): New typedef.  Rename to ...
	(omp_sync_hint_t): ... this.
	(omp_init_lock_with_hint, omp_init_nest_lock_with_hint): Use
	omp_sync_hint_t instead of omp_lock_hint_t.
	(omp_pause_resource, omp_pause_resource_all, omp_set_affinity_format,
	omp_get_affinity_format, omp_display_affinity, omp_capture_affinity):
	Declare.
	(omp_target_is_present, omp_target_disassociate_ptr):
	Change first argument from void * to const void *.
	(omp_target_memcpy, omp_target_memcpy_rect): Change second argument
	from void * to const void *.
	(omp_target_associate_ptr): Change first and second arguments from
	void * to const void *.
	* omp_lib.f90.in (omp_pause_resource_kind, omp_pause_soft,
	omp_pause_hard): New parameters.
	(omp_pause_resource, omp_pause_resource_all, omp_set_affinity_format,
	omp_get_affinity_format, omp_display_affinity, omp_capture_affinity):
	New interfaces.
	* omp_lib.h.in (omp_pause_resource_kind, omp_pause_soft,
	omp_pause_hard): New parameters.
	(omp_pause_resource, omp_pause_resource_all, omp_set_affinity_format,
	omp_get_affinity_format, omp_display_affinity, omp_capture_affinity):
	New externals.
	* ordered.c (gomp_doacross_init, gomp_doacross_ull_init): Add
	EXTRA argument.  If not needed to prepare array, if extra is 0,
	clear ws->doacross, otherwise allocate just doacross structure and
	extra payload.  If array is needed, allocate also extra payload.
	(GOMP_doacross_post, GOMP_doacross_wait, GOMP_doacross_ull_post,
	GOMP_doacross_ull_wait): Handle doacross->array == NULL like
	doacross == NULL.
	* parallel.c (GOMP_parallel_start): Pass NULL as taskgroup to
	gomp_team_start.
	(GOMP_parallel): Likewise.  Formatting fix.
	(GOMP_parallel_reductions): New function.
	(GOMP_cancellation_point): If taskgroup has workshare
	flag set, check cancelled of prev taskgroup if any.
	(GOMP_cancel): If taskgroup has workshare flag set, set cancelled
	on prev taskgroup if any.
	* sections.c: Include string.h.
	(GOMP_taskgroup_reduction_register): Add ialias_redirect.
	(GOMP_sections_start): Adjust gomp_work_share_start caller.
	(GOMP_sections2_start): New function.
	(GOMP_parallel_sections_start, GOMP_parallel_sections):
	Pass NULL as taskgroup to gomp_team_start.
	* single.c (GOMP_single_start, GOMP_single_copy_start): Adjust
	gomp_work_share_start callers.
	* target.c (GOMP_target_update_ext, GOMP_target_enter_exit_data):
	If taskgroup has workshare flag set, check cancelled on prev
	taskgroup if any.  Guard all cancellation tests with
	gomp_cancel_var test.
	(omp_target_is_present, omp_target_disassociate_ptr):
	Change ptr argument from void * to const void *.
	(omp_target_memcpy): Change src argument from void * to const void *.
	(omp_target_memcpy_rect): Likewise.
	(omp_target_memcpy_rect_worker): Likewise.  Use const char * casts
	instead of char * where needed.
	(omp_target_associate_ptr): Change host_ptr and device_ptr arguments
	from void * to const void *.
	(omp_pause_resource, omp_pause_resource_all): New functions.
	* task.c (gomp_task_handle_depend): Handle new depend array format
	in addition to the old.  Handle mutexinoutset kinds the same as
	inout for now, handle unspecified kinds.
	(gomp_create_target_task): If taskgroup has workshare flag set, check
	cancelled on prev taskgroup if any.  Guard all cancellation tests with
	gomp_cancel_var test.  Handle new depend array format count in
	addition to the old.
	(GOMP_task): Likewise.  Adjust function comment.
	(gomp_task_run_pre): If taskgroup has workshare flag set, check
	cancelled on prev taskgroup if any.  Guard all cancellation tests with
	gomp_cancel_var test.
	(GOMP_taskwait_depend): New function.
	(gomp_task_maybe_wait_for_dependencies): Handle new depend array
	format in addition to the old.  Handle mutexinoutset kinds the same as
	inout for now, handle unspecified kinds.  Fix a function comment typo.
	(gomp_taskgroup_init): New function.
	(GOMP_taskgroup_start): Use it.
	(gomp_reduction_register, gomp_create_artificial_team,
	GOMP_taskgroup_reduction_register,
	GOMP_taskgroup_reduction_unregister, GOMP_task_reduction_remap,
	gomp_parallel_reduction_register,
	gomp_workshare_task_reduction_register,
	gomp_workshare_taskgroup_start,
	GOMP_workshare_task_reduction_unregister): New functions.
	* taskloop.c (GOMP_taskloop): If taskgroup has workshare flag set,
	check cancelled on prev taskgroup if any.  Guard all cancellation
	tests with gomp_cancel_var test.  Handle GOMP_TASK_FLAG_REDUCTION flag
	by calling GOMP_taskgroup_reduction_register.
	* team.c (gomp_thread_attr): Remove comment.
	(struct gomp_thread_start_data): Add handle field.
	(gomp_thread_start): Call pthread_detach.
	(gomp_new_team): Adjust gomp_init_work_share caller.
	(gomp_free_pool_helper): Call pthread_detach.
	(gomp_team_start): Add taskgroup argument, initialize implicit
	tasks' taskgroup field to that.  Don't call
	pthread_attr_setdetachstate.  Handle OMP_DISPLAY_AFFINITY env var.
	(gomp_team_end): Determine nesting by thr->ts.level != 0
	rather than thr->ts.team != NULL.
	(gomp_pause_pool_helper, gomp_pause_host): New functions.
	* work.c (alloc_work_share): Use gomp_aligned_alloc instead of
	gomp_malloc if GOMP_HAVE_EFFICIENT_ALIGNED_ALLOC is defined.
	(gomp_init_work_share): Change ORDERED argument from bool to size_t,
	if more than 1 allocate also extra payload at the end of array.  Never
	keep ordered_team_ids NULL, set it to inline_ordered_team_ids instead.
	(gomp_work_share_start): Change ORDERED argument from bool to size_t,
	return true instead of ws.
	* Makefile.in: Regenerated.
	* configure: Regenerated.
	* config.h.in: Regenerated.
	* testsuite/libgomp.c/cancel-for-2.c (foo): Use cancel modifier
	in some cases.
	* testsuite/libgomp.c-c++-common/cancel-parallel-1.c: New test.
	* testsuite/libgomp.c-c++-common/cancel-taskgroup-3.c: New test.
	* testsuite/libgomp.c-c++-common/depend-iterator-1.c: New test.
	* testsuite/libgomp.c-c++-common/depend-iterator-2.c: New test.
	* testsuite/libgomp.c-c++-common/depend-mutexinout-1.c: New test.
	* testsuite/libgomp.c-c++-common/depend-mutexinout-2.c: New test.
	* testsuite/libgomp.c-c++-common/depobj-1.c: New test.
	* testsuite/libgomp.c-c++-common/display-affinity-1.c: New test.
	* testsuite/libgomp.c-c++-common/for-10.c: New test.
	* testsuite/libgomp.c-c++-common/for-11.c: New test.
	* testsuite/libgomp.c-c++-common/for-12.c: New test.
	* testsuite/libgomp.c-c++-common/for-13.c: New test.
	* testsuite/libgomp.c-c++-common/for-14.c: New test.
	* testsuite/libgomp.c-c++-common/for-15.c: New test.
	* testsuite/libgomp.c-c++-common/for-2.h: If CONDNE macro is defined,
	define a different N(test), don't define N(f0) to N(f14), but instead
	define N(f20) to N(f34) using != comparisons.
	* testsuite/libgomp.c-c++-common/for-7.c: New test.
	* testsuite/libgomp.c-c++-common/for-8.c: New test.
	* testsuite/libgomp.c-c++-common/for-9.c: New test.
	* testsuite/libgomp.c-c++-common/master-combined-1.c: New test.
	* testsuite/libgomp.c-c++-common/pause-1.c: New test.
	* testsuite/libgomp.c-c++-common/pause-2.c: New test.
	* testsuite/libgomp.c-c++-common/pr66199-10.c: New test.
	* testsuite/libgomp.c-c++-common/pr66199-11.c: New test.
	* testsuite/libgomp.c-c++-common/pr66199-12.c: New test.
	* testsuite/libgomp.c-c++-common/pr66199-13.c: New test.
	* testsuite/libgomp.c-c++-common/pr66199-14.c: New test.
	* testsuite/libgomp.c-c++-common/simd-1.c: New test.
	* testsuite/libgomp.c-c++-common/taskloop-reduction-1.c: New test.
	* testsuite/libgomp.c-c++-common/taskloop-reduction-2.c: New test.
	* testsuite/libgomp.c-c++-common/taskloop-reduction-3.c: New test.
	* testsuite/libgomp.c-c++-common/taskloop-reduction-4.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-11.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-12.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-1.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-2.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-3.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-4.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-5.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-6.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-7.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-8.c: New test.
	* testsuite/libgomp.c-c++-common/task-reduction-9.c: New test.
	* testsuite/libgomp.c-c++-common/taskwait-depend-1.c: New test.
	* testsuite/libgomp.c++/depend-1.C: New test.
	* testsuite/libgomp.c++/depend-iterator-1.C: New test.
	* testsuite/libgomp.c++/depobj-1.C: New test.
	* testsuite/libgomp.c++/for-16.C: New test.
	* testsuite/libgomp.c++/for-21.C: New test.
	* testsuite/libgomp.c++/for-22.C: New test.
	* testsuite/libgomp.c++/for-23.C: New test.
	* testsuite/libgomp.c++/for-24.C: New test.
	* testsuite/libgomp.c++/for-25.C: New test.
	* testsuite/libgomp.c++/for-26.C: New test.
	* testsuite/libgomp.c++/taskloop-reduction-1.C: New test.
	* testsuite/libgomp.c++/taskloop-reduction-2.C: New test.
	* testsuite/libgomp.c++/taskloop-reduction-3.C: New test.
	* testsuite/libgomp.c++/taskloop-reduction-4.C: New test.
	* testsuite/libgomp.c++/task-reduction-10.C: New test.
	* testsuite/libgomp.c++/task-reduction-11.C: New test.
	* testsuite/libgomp.c++/task-reduction-12.C: New test.
	* testsuite/libgomp.c++/task-reduction-13.C: New test.
	* testsuite/libgomp.c++/task-reduction-14.C: New test.
	* testsuite/libgomp.c++/task-reduction-15.C: New test.
	* testsuite/libgomp.c++/task-reduction-16.C: New test.
	* testsuite/libgomp.c++/task-reduction-17.C: New test.
	* testsuite/libgomp.c++/task-reduction-18.C: New test.
	* testsuite/libgomp.c++/task-reduction-19.C: New test.
	* testsuite/libgomp.c/task-reduction-1.c: New test.
	* testsuite/libgomp.c++/task-reduction-1.C: New test.
	* testsuite/libgomp.c/task-reduction-2.c: New test.
	* testsuite/libgomp.c++/task-reduction-2.C: New test.
	* testsuite/libgomp.c++/task-reduction-3.C: New test.
	* testsuite/libgomp.c++/task-reduction-4.C: New test.
	* testsuite/libgomp.c++/task-reduction-5.C: New test.
	* testsuite/libgomp.c++/task-reduction-6.C: New test.
	* testsuite/libgomp.c++/task-reduction-7.C: New test.
	* testsuite/libgomp.c++/task-reduction-8.C: New test.
	* testsuite/libgomp.c++/task-reduction-9.C: New test.
	* testsuite/libgomp.c/teams-1.c: New test.
	* testsuite/libgomp.c/teams-2.c: New test.
	* testsuite/libgomp.c/thread-limit-4.c: New test.
	* testsuite/libgomp.c/thread-limit-5.c: New test.
	* testsuite/libgomp.fortran/display-affinity-1.f90: New test.

From-SVN: r265930

1 files changed, 398 insertions, 51 deletions

diff --git a/gcc/omp-expand.c b/gcc/omp-expand.c
index 1185a26619a..95b89a6dd45 100644
--- a/gcc/omp-expand.c
+++ b/gcc/omp-expand.c
@@ -174,6 +174,8 @@ workshare_safe_to_combine_p (basic_block ws_entry_bb)
     return true;
 
   gcc_assert (gimple_code (ws_stmt) == GIMPLE_OMP_FOR);
+  if (gimple_omp_for_kind (ws_stmt) != GF_OMP_FOR_KIND_FOR)
+    return false;
 
   omp_extract_for_data (as_a <gomp_for *> (ws_stmt), &fd, NULL);
 
@@ -202,7 +204,7 @@ workshare_safe_to_combine_p (basic_block ws_entry_bb)
 static tree
 omp_adjust_chunk_size (tree chunk_size, bool simd_schedule)
 {
-  if (!simd_schedule)
+  if (!simd_schedule || integer_zerop (chunk_size))
     return chunk_size;
 
   poly_uint64 vf = omp_max_vf ();
@@ -310,6 +312,13 @@ determine_parallel_type (struct omp_region *region)
   ws_entry_bb = region->inner->entry;
   ws_exit_bb = region->inner->exit;
 
+  /* Give up for task reductions on the parallel, while it is implementable,
+     adding another big set of APIs or slowing down the normal paths is
+     not acceptable.  */
+  tree pclauses = gimple_omp_parallel_clauses (last_stmt (par_entry_bb));
+  if (omp_find_clause (pclauses, OMP_CLAUSE__REDUCTEMP_))
+    return;
+
   if (single_succ (par_entry_bb) == ws_entry_bb
       && single_succ (ws_exit_bb) == par_exit_bb
       && workshare_safe_to_combine_p (ws_entry_bb)
@@ -336,13 +345,14 @@ determine_parallel_type (struct omp_region *region)
 	  if (c == NULL
 	      || ((OMP_CLAUSE_SCHEDULE_KIND (c) & OMP_CLAUSE_SCHEDULE_MASK)
 		  == OMP_CLAUSE_SCHEDULE_STATIC)
-	      || omp_find_clause (clauses, OMP_CLAUSE_ORDERED))
-	    {
-	      region->is_combined_parallel = false;
-	      region->inner->is_combined_parallel = false;
-	      return;
-	    }
+	      || omp_find_clause (clauses, OMP_CLAUSE_ORDERED)
+	      || omp_find_clause (clauses, OMP_CLAUSE__REDUCTEMP_))
+	    return;
 	}
+      else if (region->inner->type == GIMPLE_OMP_SECTIONS
+	       && omp_find_clause (gimple_omp_sections_clauses (ws_stmt),
+				   OMP_CLAUSE__REDUCTEMP_))
+	return;
 
       region->is_combined_parallel = true;
       region->inner->is_combined_parallel = true;
@@ -534,7 +544,7 @@ adjust_context_and_scope (tree entry_block, tree child_fndecl)
     }
 }
 
-/* Build the function calls to GOMP_parallel_start etc to actually
+/* Build the function calls to GOMP_parallel etc to actually
    generate the parallel operation.  REGION is the parallel region
    being expanded.  BB is the block where to insert the code.  WS_ARGS
    will be set if this is a call to a combined parallel+workshare
@@ -559,7 +569,10 @@ expand_parallel_call (struct omp_region *region, basic_block bb,
   /* Determine what flavor of GOMP_parallel we will be
      emitting.  */
   start_ix = BUILT_IN_GOMP_PARALLEL;
-  if (is_combined_parallel (region))
+  tree rtmp = omp_find_clause (clauses, OMP_CLAUSE__REDUCTEMP_);
+  if (rtmp)
+    start_ix = BUILT_IN_GOMP_PARALLEL_REDUCTIONS;
+  else if (is_combined_parallel (region))
     {
       switch (region->inner->type)
 	{
@@ -568,12 +581,19 @@ expand_parallel_call (struct omp_region *region, basic_block bb,
 	  switch (region->inner->sched_kind)
 	    {
 	    case OMP_CLAUSE_SCHEDULE_RUNTIME:
-	      start_ix2 = 3;
+	      if ((region->inner->sched_modifiers
+		   & OMP_CLAUSE_SCHEDULE_NONMONOTONIC) != 0)
+		start_ix2 = 6;
+	      else if ((region->inner->sched_modifiers
+			& OMP_CLAUSE_SCHEDULE_MONOTONIC) == 0)
+		start_ix2 = 7;
+	      else
+		start_ix2 = 3;
 	      break;
 	    case OMP_CLAUSE_SCHEDULE_DYNAMIC:
 	    case OMP_CLAUSE_SCHEDULE_GUIDED:
-	      if (region->inner->sched_modifiers
-		  & OMP_CLAUSE_SCHEDULE_NONMONOTONIC)
+	      if ((region->inner->sched_modifiers
+		   & OMP_CLAUSE_SCHEDULE_MONOTONIC) == 0)
 		{
 		  start_ix2 = 3 + region->inner->sched_kind;
 		  break;
@@ -716,6 +736,13 @@ expand_parallel_call (struct omp_region *region, basic_block bb,
   t = build_call_expr_loc_vec (UNKNOWN_LOCATION,
 			       builtin_decl_explicit (start_ix), args);
 
+  if (rtmp)
+    {
+      tree type = TREE_TYPE (OMP_CLAUSE_DECL (rtmp));
+      t = build2 (MODIFY_EXPR, type, OMP_CLAUSE_DECL (rtmp),
+		  fold_convert (type,
+				fold_convert (pointer_sized_int_node, t)));
+    }
   force_gimple_operand_gsi (&gsi, t, true, NULL_TREE,
 			    false, GSI_CONTINUE_LINKING);
 
@@ -792,6 +819,8 @@ expand_task_call (struct omp_region *region, basic_block bb,
       if (omp_find_clause (tclauses, OMP_CLAUSE_NOGROUP))
 	iflags |= GOMP_TASK_FLAG_NOGROUP;
       ull = fd.iter_type == long_long_unsigned_type_node;
+      if (omp_find_clause (clauses, OMP_CLAUSE_REDUCTION))
+	iflags |= GOMP_TASK_FLAG_REDUCTION;
     }
   else if (priority)
     iflags |= GOMP_TASK_FLAG_PRIORITY;
@@ -866,6 +895,82 @@ expand_task_call (struct omp_region *region, basic_block bb,
 			    false, GSI_CONTINUE_LINKING);
 }
 
+/* Build the function call to GOMP_taskwait_depend to actually
+   generate the taskwait operation.  BB is the block where to insert the
+   code.  */
+
+static void
+expand_taskwait_call (basic_block bb, gomp_task *entry_stmt)
+{
+  tree clauses = gimple_omp_task_clauses (entry_stmt);
+  tree depend = omp_find_clause (clauses, OMP_CLAUSE_DEPEND);
+  if (depend == NULL_TREE)
+    return;
+
+  depend = OMP_CLAUSE_DECL (depend);
+
+  gimple_stmt_iterator gsi = gsi_last_nondebug_bb (bb);
+  tree t
+    = build_call_expr (builtin_decl_explicit (BUILT_IN_GOMP_TASKWAIT_DEPEND),
+		       1, depend);
+
+  force_gimple_operand_gsi (&gsi, t, true, NULL_TREE,
+			    false, GSI_CONTINUE_LINKING);
+}
+
+/* Build the function call to GOMP_teams_reg to actually
+   generate the host teams operation.  REGION is the teams region
+   being expanded.  BB is the block where to insert the code.  */
+
+static void
+expand_teams_call (basic_block bb, gomp_teams *entry_stmt)
+{
+  tree clauses = gimple_omp_teams_clauses (entry_stmt);
+  tree num_teams = omp_find_clause (clauses, OMP_CLAUSE_NUM_TEAMS);
+  if (num_teams == NULL_TREE)
+    num_teams = build_int_cst (unsigned_type_node, 0);
+  else
+    {
+      num_teams = OMP_CLAUSE_NUM_TEAMS_EXPR (num_teams);
+      num_teams = fold_convert (unsigned_type_node, num_teams);
+    }
+  tree thread_limit = omp_find_clause (clauses, OMP_CLAUSE_THREAD_LIMIT);
+  if (thread_limit == NULL_TREE)
+    thread_limit = build_int_cst (unsigned_type_node, 0);
+  else
+    {
+      thread_limit = OMP_CLAUSE_THREAD_LIMIT_EXPR (thread_limit);
+      thread_limit = fold_convert (unsigned_type_node, thread_limit);
+    }
+
+  gimple_stmt_iterator gsi = gsi_last_nondebug_bb (bb);
+  tree t = gimple_omp_teams_data_arg (entry_stmt), t1;
+  if (t == NULL)
+    t1 = null_pointer_node;
+  else
+    t1 = build_fold_addr_expr (t);
+  tree child_fndecl = gimple_omp_teams_child_fn (entry_stmt);
+  tree t2 = build_fold_addr_expr (child_fndecl);
+
+  adjust_context_and_scope (gimple_block (entry_stmt), child_fndecl);
+
+  vec<tree, va_gc> *args;
+  vec_alloc (args, 5);
+  args->quick_push (t2);
+  args->quick_push (t1);
+  args->quick_push (num_teams);
+  args->quick_push (thread_limit);
+  /* For future extensibility.  */
+  args->quick_push (build_zero_cst (unsigned_type_node));
+
+  t = build_call_expr_loc_vec (UNKNOWN_LOCATION,
+			       builtin_decl_explicit (BUILT_IN_GOMP_TEAMS_REG),
+			       args);
+
+  force_gimple_operand_gsi (&gsi, t, true, NULL_TREE,
+			    false, GSI_CONTINUE_LINKING);
+}
+
 /* Chain all the DECLs in LIST by their TREE_CHAIN fields.  */
 
 static tree
@@ -1112,6 +1217,17 @@ expand_omp_taskreg (struct omp_region *region)
   vec<tree, va_gc> *ws_args;
 
   entry_stmt = last_stmt (region->entry);
+  if (gimple_code (entry_stmt) == GIMPLE_OMP_TASK
+      && gimple_omp_task_taskwait_p (entry_stmt))
+    {
+      new_bb = region->entry;
+      gsi = gsi_last_nondebug_bb (region->entry);
+      gcc_assert (gimple_code (gsi_stmt (gsi)) == GIMPLE_OMP_TASK);
+      gsi_remove (&gsi, true);
+      expand_taskwait_call (new_bb, as_a <gomp_task *> (entry_stmt));
+      return;
+    }
+
   child_fn = gimple_omp_taskreg_child_fn (entry_stmt);
   child_cfun = DECL_STRUCT_FUNCTION (child_fn);
 
@@ -1137,7 +1253,8 @@ expand_omp_taskreg (struct omp_region *region)
 
       gsi = gsi_last_nondebug_bb (entry_bb);
       gcc_assert (gimple_code (gsi_stmt (gsi)) == GIMPLE_OMP_PARALLEL
-		  || gimple_code (gsi_stmt (gsi)) == GIMPLE_OMP_TASK);
+		  || gimple_code (gsi_stmt (gsi)) == GIMPLE_OMP_TASK
+		  || gimple_code (gsi_stmt (gsi)) == GIMPLE_OMP_TEAMS);
       gsi_remove (&gsi, true);
 
       new_bb = entry_bb;
@@ -1190,8 +1307,8 @@ expand_omp_taskreg (struct omp_region *region)
 		     effectively doing a STRIP_NOPS.  */
 
 		  if (TREE_CODE (arg) == ADDR_EXPR
-		      && TREE_OPERAND (arg, 0)
-			== gimple_omp_taskreg_data_arg (entry_stmt))
+		      && (TREE_OPERAND (arg, 0)
+			  == gimple_omp_taskreg_data_arg (entry_stmt)))
 		    {
 		      parcopy_stmt = stmt;
 		      break;
@@ -1251,12 +1368,13 @@ expand_omp_taskreg (struct omp_region *region)
       gsi = gsi_last_nondebug_bb (entry_bb);
       stmt = gsi_stmt (gsi);
       gcc_assert (stmt && (gimple_code (stmt) == GIMPLE_OMP_PARALLEL
-			   || gimple_code (stmt) == GIMPLE_OMP_TASK));
+			   || gimple_code (stmt) == GIMPLE_OMP_TASK
+			   || gimple_code (stmt) == GIMPLE_OMP_TEAMS));
       e = split_block (entry_bb, stmt);
       gsi_remove (&gsi, true);
       entry_bb = e->dest;
       edge e2 = NULL;
-      if (gimple_code (entry_stmt) == GIMPLE_OMP_PARALLEL)
+      if (gimple_code (entry_stmt) != GIMPLE_OMP_TASK)
 	single_succ_edge (entry_bb)->flags = EDGE_FALLTHRU;
       else
 	{
@@ -1382,6 +1500,8 @@ expand_omp_taskreg (struct omp_region *region)
   if (gimple_code (entry_stmt) == GIMPLE_OMP_PARALLEL)
     expand_parallel_call (region, new_bb,
 			  as_a <gomp_parallel *> (entry_stmt), ws_args);
+  else if (gimple_code (entry_stmt) == GIMPLE_OMP_TEAMS)
+    expand_teams_call (new_bb, as_a <gomp_teams *> (entry_stmt));
   else
     expand_task_call (region, new_bb, as_a <gomp_task *> (entry_stmt));
   if (gimple_in_ssa_p (cfun))
@@ -2499,6 +2619,7 @@ expand_omp_for_generic (struct omp_region *region,
 			struct omp_for_data *fd,
 			enum built_in_function start_fn,
 			enum built_in_function next_fn,
+			tree sched_arg,
 			gimple *inner_stmt)
 {
   tree type, istart0, iend0, iend;
@@ -2546,6 +2667,30 @@ expand_omp_for_generic (struct omp_region *region,
       && omp_find_clause (gimple_omp_for_clauses (gsi_stmt (gsi)),
 			  OMP_CLAUSE_LASTPRIVATE))
     ordered_lastprivate = false;
+  tree reductions = NULL_TREE;
+  tree mem = NULL_TREE;
+  if (sched_arg)
+    {
+      if (fd->have_reductemp)
+	{
+	  tree c = omp_find_clause (gimple_omp_for_clauses (gsi_stmt (gsi)),
+				    OMP_CLAUSE__REDUCTEMP_);
+	  reductions = OMP_CLAUSE_DECL (c);
+	  gcc_assert (TREE_CODE (reductions) == SSA_NAME);
+	  gimple *g = SSA_NAME_DEF_STMT (reductions);
+	  reductions = gimple_assign_rhs1 (g);
+	  OMP_CLAUSE_DECL (c) = reductions;
+	  entry_bb = gimple_bb (g);
+	  edge e = split_block (entry_bb, g);
+	  if (region->entry == entry_bb)
+	    region->entry = e->dest;
+	  gsi = gsi_last_bb (entry_bb);
+	}
+      else
+	reductions = null_pointer_node;
+      /* For now.  */
+      mem = null_pointer_node;
+    }
   if (fd->collapse > 1 || fd->ordered)
     {
       int first_zero_iter1 = -1, first_zero_iter2 = -1;
@@ -2732,7 +2877,18 @@ expand_omp_for_generic (struct omp_region *region,
 	    {
 	      t = fold_convert (fd->iter_type, fd->chunk_size);
 	      t = omp_adjust_chunk_size (t, fd->simd_schedule);
-	      if (fd->ordered)
+	      if (sched_arg)
+		{
+		  if (fd->ordered)
+		    t = build_call_expr (builtin_decl_explicit (start_fn),
+					 8, t0, t1, sched_arg, t, t3, t4,
+					 reductions, mem);
+		  else
+		    t = build_call_expr (builtin_decl_explicit (start_fn),
+					 9, t0, t1, t2, sched_arg, t, t3, t4,
+					 reductions, mem);
+		}
+	      else if (fd->ordered)
 		t = build_call_expr (builtin_decl_explicit (start_fn),
 				     5, t0, t1, t, t3, t4);
 	      else
@@ -2765,7 +2921,11 @@ expand_omp_for_generic (struct omp_region *region,
 	      tree bfn_decl = builtin_decl_explicit (start_fn);
 	      t = fold_convert (fd->iter_type, fd->chunk_size);
 	      t = omp_adjust_chunk_size (t, fd->simd_schedule);
-	      t = build_call_expr (bfn_decl, 7, t5, t0, t1, t2, t, t3, t4);
+	      if (sched_arg)
+		t = build_call_expr (bfn_decl, 10, t5, t0, t1, t2, sched_arg,
+				     t, t3, t4, reductions, mem);
+	      else
+		t = build_call_expr (bfn_decl, 7, t5, t0, t1, t2, t, t3, t4);
 	    }
 	  else
 	    t = build_call_expr (builtin_decl_explicit (start_fn),
@@ -2784,6 +2944,17 @@ expand_omp_for_generic (struct omp_region *region,
       gsi_insert_before (&gsi, gimple_build_assign (arr, clobber),
 			 GSI_SAME_STMT);
     }
+  if (fd->have_reductemp)
+    {
+      gimple *g = gsi_stmt (gsi);
+      gsi_remove (&gsi, true);
+      release_ssa_name (gimple_assign_lhs (g));
+
+      entry_bb = region->entry;
+      gsi = gsi_last_nondebug_bb (entry_bb);
+
+      gcc_assert (gimple_code (gsi_stmt (gsi)) == GIMPLE_OMP_FOR);
+    }
   gsi_insert_after (&gsi, gimple_build_cond_empty (t), GSI_SAME_STMT);
 
   /* Remove the GIMPLE_OMP_FOR statement.  */
@@ -3082,9 +3253,6 @@ expand_omp_for_generic (struct omp_region *region,
   else
     t = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END);
   gcall *call_stmt = gimple_build_call (t, 0);
-  if (gimple_omp_return_lhs (gsi_stmt (gsi)))
-    gimple_call_set_lhs (call_stmt, gimple_omp_return_lhs (gsi_stmt (gsi)));
-  gsi_insert_after (&gsi, call_stmt, GSI_SAME_STMT);
   if (fd->ordered)
     {
       tree arr = counts[fd->ordered];
@@ -3093,6 +3261,17 @@ expand_omp_for_generic (struct omp_region *region,
       gsi_insert_after (&gsi, gimple_build_assign (arr, clobber),
 			GSI_SAME_STMT);
     }
+  if (gimple_omp_return_lhs (gsi_stmt (gsi)))
+    {
+      gimple_call_set_lhs (call_stmt, gimple_omp_return_lhs (gsi_stmt (gsi)));
+      if (fd->have_reductemp)
+	{
+	  gimple *g = gimple_build_assign (reductions, NOP_EXPR,
+					   gimple_call_lhs (call_stmt));
+	  gsi_insert_after (&gsi, g, GSI_SAME_STMT);
+	}
+    }
+  gsi_insert_after (&gsi, call_stmt, GSI_SAME_STMT);
   gsi_remove (&gsi, true);
 
   /* Connect the new blocks.  */
@@ -3275,6 +3454,7 @@ expand_omp_for_static_nochunk (struct omp_region *region,
   bool broken_loop = region->cont == NULL;
   tree *counts = NULL;
   tree n1, n2, step;
+  tree reductions = NULL_TREE;
 
   itype = type = TREE_TYPE (fd->loop.v);
   if (POINTER_TYPE_P (type))
@@ -3358,6 +3538,29 @@ expand_omp_for_static_nochunk (struct omp_region *region,
       gsi = gsi_last_bb (entry_bb);
     }
 
+  if (fd->have_reductemp)
+    {
+      tree t1 = build_int_cst (long_integer_type_node, 0);
+      tree t2 = build_int_cst (long_integer_type_node, 1);
+      tree t3 = build_int_cstu (long_integer_type_node,
+				(HOST_WIDE_INT_1U << 31) + 1);
+      tree clauses = gimple_omp_for_clauses (fd->for_stmt);
+      clauses = omp_find_clause (clauses, OMP_CLAUSE__REDUCTEMP_);
+      reductions = OMP_CLAUSE_DECL (clauses);
+      gcc_assert (TREE_CODE (reductions) == SSA_NAME);
+      gimple *g = SSA_NAME_DEF_STMT (reductions);
+      reductions = gimple_assign_rhs1 (g);
+      OMP_CLAUSE_DECL (clauses) = reductions;
+      gimple_stmt_iterator gsi2 = gsi_for_stmt (g);
+      tree t
+	= build_call_expr (builtin_decl_explicit (BUILT_IN_GOMP_LOOP_START),
+			   9, t1, t2, t2, t3, t1, null_pointer_node,
+			   null_pointer_node, reductions, null_pointer_node);
+      force_gimple_operand_gsi (&gsi2, t, true, NULL_TREE,
+				true, GSI_SAME_STMT);
+      gsi_remove (&gsi2, true);
+      release_ssa_name (gimple_assign_lhs (g));
+    }
   switch (gimple_omp_for_kind (fd->for_stmt))
     {
     case GF_OMP_FOR_KIND_FOR:
@@ -3628,7 +3831,25 @@ expand_omp_for_static_nochunk (struct omp_region *region,
   if (!gimple_omp_return_nowait_p (gsi_stmt (gsi)))
     {
       t = gimple_omp_return_lhs (gsi_stmt (gsi));
-      gsi_insert_after (&gsi, omp_build_barrier (t), GSI_SAME_STMT);
+      if (fd->have_reductemp)
+	{
+	  tree fn;
+	  if (t)
+	    fn = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END_CANCEL);
+	  else
+	    fn = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END);
+	  gcall *g = gimple_build_call (fn, 0);
+	  if (t)
+	    {
+	      gimple_call_set_lhs (g, t);
+	      gsi_insert_after (&gsi, gimple_build_assign (reductions,
+							   NOP_EXPR, t),
+				GSI_SAME_STMT);
+	    }
+	  gsi_insert_after (&gsi, g, GSI_SAME_STMT);
+	}
+      else
+	gsi_insert_after (&gsi, omp_build_barrier (t), GSI_SAME_STMT);
     }
   gsi_remove (&gsi, true);
 
@@ -3765,6 +3986,7 @@ expand_omp_for_static_chunk (struct omp_region *region,
   bool broken_loop = region->cont == NULL;
   tree *counts = NULL;
   tree n1, n2, step;
+  tree reductions = NULL_TREE;
 
   itype = type = TREE_TYPE (fd->loop.v);
   if (POINTER_TYPE_P (type))
@@ -3852,6 +4074,29 @@ expand_omp_for_static_chunk (struct omp_region *region,
       gsi = gsi_last_bb (entry_bb);
     }
 
+  if (fd->have_reductemp)
+    {
+      tree t1 = build_int_cst (long_integer_type_node, 0);
+      tree t2 = build_int_cst (long_integer_type_node, 1);
+      tree t3 = build_int_cstu (long_integer_type_node,
+				(HOST_WIDE_INT_1U << 31) + 1);
+      tree clauses = gimple_omp_for_clauses (fd->for_stmt);
+      clauses = omp_find_clause (clauses, OMP_CLAUSE__REDUCTEMP_);
+      reductions = OMP_CLAUSE_DECL (clauses);
+      gcc_assert (TREE_CODE (reductions) == SSA_NAME);
+      gimple *g = SSA_NAME_DEF_STMT (reductions);
+      reductions = gimple_assign_rhs1 (g);
+      OMP_CLAUSE_DECL (clauses) = reductions;
+      gimple_stmt_iterator gsi2 = gsi_for_stmt (g);
+      tree t
+	= build_call_expr (builtin_decl_explicit (BUILT_IN_GOMP_LOOP_START),
+			   9, t1, t2, t2, t3, t1, null_pointer_node,
+			   null_pointer_node, reductions, null_pointer_node);
+      force_gimple_operand_gsi (&gsi2, t, true, NULL_TREE,
+				true, GSI_SAME_STMT);
+      gsi_remove (&gsi2, true);
+      release_ssa_name (gimple_assign_lhs (g));
+    }
   switch (gimple_omp_for_kind (fd->for_stmt))
     {
     case GF_OMP_FOR_KIND_FOR:
@@ -4155,7 +4400,25 @@ expand_omp_for_static_chunk (struct omp_region *region,
   if (!gimple_omp_return_nowait_p (gsi_stmt (gsi)))
     {
       t = gimple_omp_return_lhs (gsi_stmt (gsi));
-      gsi_insert_after (&gsi, omp_build_barrier (t), GSI_SAME_STMT);
+      if (fd->have_reductemp)
+	{
+	  tree fn;
+	  if (t)
+	    fn = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END_CANCEL);
+	  else
+	    fn = builtin_decl_explicit (BUILT_IN_GOMP_LOOP_END);
+	  gcall *g = gimple_build_call (fn, 0);
+	  if (t)
+	    {
+	      gimple_call_set_lhs (g, t);
+	      gsi_insert_after (&gsi, gimple_build_assign (reductions,
+							   NOP_EXPR, t),
+				GSI_SAME_STMT);
+	    }
+	  gsi_insert_after (&gsi, g, GSI_SAME_STMT);
+	}
+      else
+	gsi_insert_after (&gsi, omp_build_barrier (t), GSI_SAME_STMT);
     }
   gsi_remove (&gsi, true);
 
@@ -5690,39 +5953,72 @@ expand_omp_for (struct omp_region *region, gimple *inner_stmt)
   else
     {
       int fn_index, start_ix, next_ix;
+      unsigned HOST_WIDE_INT sched = 0;
+      tree sched_arg = NULL_TREE;
 
       gcc_assert (gimple_omp_for_kind (fd.for_stmt)
 		  == GF_OMP_FOR_KIND_FOR);
       if (fd.chunk_size == NULL
 	  && fd.sched_kind == OMP_CLAUSE_SCHEDULE_STATIC)
 	fd.chunk_size = integer_zero_node;
-      gcc_assert (fd.sched_kind != OMP_CLAUSE_SCHEDULE_AUTO);
       switch (fd.sched_kind)
 	{
 	case OMP_CLAUSE_SCHEDULE_RUNTIME:
-	  fn_index = 3;
+	  if ((fd.sched_modifiers & OMP_CLAUSE_SCHEDULE_NONMONOTONIC) != 0)
+	    {
+	      gcc_assert (!fd.have_ordered);
+	      fn_index = 6;
+	      sched = 4;
+	    }
+	  else if ((fd.sched_modifiers & OMP_CLAUSE_SCHEDULE_MONOTONIC) == 0
+		   && !fd.have_ordered)
+	    fn_index = 7;
+	  else
+	    {
+	      fn_index = 3;
+	      sched = (HOST_WIDE_INT_1U << 31);
+	    }
 	  break;
 	case OMP_CLAUSE_SCHEDULE_DYNAMIC:
 	case OMP_CLAUSE_SCHEDULE_GUIDED:
-	  if ((fd.sched_modifiers & OMP_CLAUSE_SCHEDULE_NONMONOTONIC)
-	      && !fd.ordered
+	  if ((fd.sched_modifiers & OMP_CLAUSE_SCHEDULE_MONOTONIC) == 0
 	      && !fd.have_ordered)
 	    {
 	      fn_index = 3 + fd.sched_kind;
+	      sched = (fd.sched_kind == OMP_CLAUSE_SCHEDULE_GUIDED) + 2;
 	      break;
 	    }
-	  /* FALLTHRU */
-	default:
 	  fn_index = fd.sched_kind;
+	  sched = (fd.sched_kind == OMP_CLAUSE_SCHEDULE_GUIDED) + 2;
+	  sched += (HOST_WIDE_INT_1U << 31);
 	  break;
+	case OMP_CLAUSE_SCHEDULE_STATIC:
+	  gcc_assert (fd.have_ordered);
+	  fn_index = 0;
+	  sched = (HOST_WIDE_INT_1U << 31) + 1;
+	  break;
+	default:
+	  gcc_unreachable ();
 	}
       if (!fd.ordered)
-	fn_index += fd.have_ordered * 6;
+	fn_index += fd.have_ordered * 8;
       if (fd.ordered)
 	start_ix = ((int)BUILT_IN_GOMP_LOOP_DOACROSS_STATIC_START) + fn_index;
       else
 	start_ix = ((int)BUILT_IN_GOMP_LOOP_STATIC_START) + fn_index;
       next_ix = ((int)BUILT_IN_GOMP_LOOP_STATIC_NEXT) + fn_index;
+      if (fd.have_reductemp)
+	{
+	  if (fd.ordered)
+	    start_ix = (int)BUILT_IN_GOMP_LOOP_DOACROSS_START;
+	  else if (fd.have_ordered)
+	    start_ix = (int)BUILT_IN_GOMP_LOOP_ORDERED_START;
+	  else
+	    start_ix = (int)BUILT_IN_GOMP_LOOP_START;
+	  sched_arg = build_int_cstu (long_integer_type_node, sched);
+	  if (!fd.chunk_size)
+	    fd.chunk_size = integer_zero_node;
+	}
       if (fd.iter_type == long_long_unsigned_type_node)
 	{
 	  start_ix += ((int)BUILT_IN_GOMP_LOOP_ULL_STATIC_START
@@ -5731,7 +6027,8 @@ expand_omp_for (struct omp_region *region, gimple *inner_stmt)
 		      - (int)BUILT_IN_GOMP_LOOP_STATIC_NEXT);
 	}
       expand_omp_for_generic (region, &fd, (enum built_in_function) start_ix,
-			      (enum built_in_function) next_ix, inner_stmt);
+			      (enum built_in_function) next_ix, sched_arg,
+			      inner_stmt);
     }
 
   if (gimple_in_ssa_p (cfun))
@@ -5831,7 +6128,25 @@ expand_omp_sections (struct omp_region *region)
   sections_stmt = as_a <gomp_sections *> (gsi_stmt (si));
   gcc_assert (gimple_code (sections_stmt) == GIMPLE_OMP_SECTIONS);
   vin = gimple_omp_sections_control (sections_stmt);
-  if (!is_combined_parallel (region))
+  tree clauses = gimple_omp_sections_clauses (sections_stmt);
+  tree reductmp = omp_find_clause (clauses, OMP_CLAUSE__REDUCTEMP_);
+  if (reductmp)
+    {
+      tree reductions = OMP_CLAUSE_DECL (reductmp);
+      gcc_assert (TREE_CODE (reductions) == SSA_NAME);
+      gimple *g = SSA_NAME_DEF_STMT (reductions);
+      reductions = gimple_assign_rhs1 (g);
+      OMP_CLAUSE_DECL (reductmp) = reductions;
+      gimple_stmt_iterator gsi = gsi_for_stmt (g);
+      t = build_int_cst (unsigned_type_node, len - 1);
+      u = builtin_decl_explicit (BUILT_IN_GOMP_SECTIONS2_START);
+      stmt = gimple_build_call (u, 3, t, reductions, null_pointer_node);
+      gimple_call_set_lhs (stmt, vin);
+      gsi_insert_before (&gsi, stmt, GSI_SAME_STMT);
+      gsi_remove (&gsi, true);
+      release_ssa_name (gimple_assign_lhs (g));
+    }
+  else if (!is_combined_parallel (region))
     {
       /* If we are not inside a combined parallel+sections region,
 	 call GOMP_sections_start.  */
@@ -5845,8 +6160,11 @@ expand_omp_sections (struct omp_region *region)
       u = builtin_decl_explicit (BUILT_IN_GOMP_SECTIONS_NEXT);
       stmt = gimple_build_call (u, 0);
     }
-  gimple_call_set_lhs (stmt, vin);
-  gsi_insert_after (&si, stmt, GSI_SAME_STMT);
+  if (!reductmp)
+    {
+      gimple_call_set_lhs (stmt, vin);
+      gsi_insert_after (&si, stmt, GSI_SAME_STMT);
+    }
   gsi_remove (&si, true);
 
   /* The switch() statement replacing GIMPLE_OMP_SECTIONS_SWITCH goes in
@@ -6004,6 +6322,12 @@ expand_omp_synch (struct omp_region *region)
 	      || gimple_code (gsi_stmt (si)) == GIMPLE_OMP_ORDERED
 	      || gimple_code (gsi_stmt (si)) == GIMPLE_OMP_CRITICAL
 	      || gimple_code (gsi_stmt (si)) == GIMPLE_OMP_TEAMS);
+  if (gimple_code (gsi_stmt (si)) == GIMPLE_OMP_TEAMS
+      && gimple_omp_teams_host (as_a <gomp_teams *> (gsi_stmt (si))))
+    {
+      expand_omp_taskreg (region);
+      return;
+    }
   gsi_remove (&si, true);
   single_succ_edge (entry_bb)->flags = EDGE_FALLTHRU;
 
@@ -6016,6 +6340,24 @@ expand_omp_synch (struct omp_region *region)
     }
 }
 
+/* Translate enum omp_memory_order to enum memmodel.  The two enums
+   are using different numbers so that OMP_MEMORY_ORDER_UNSPECIFIED
+   is 0.  */
+
+static enum memmodel
+omp_memory_order_to_memmodel (enum omp_memory_order mo)
+{
+  switch (mo)
+    {
+    case OMP_MEMORY_ORDER_RELAXED: return MEMMODEL_RELAXED;
+    case OMP_MEMORY_ORDER_ACQUIRE: return MEMMODEL_ACQUIRE;
+    case OMP_MEMORY_ORDER_RELEASE: return MEMMODEL_RELEASE;
+    case OMP_MEMORY_ORDER_ACQ_REL: return MEMMODEL_ACQ_REL;
+    case OMP_MEMORY_ORDER_SEQ_CST: return MEMMODEL_SEQ_CST;
+    default: gcc_unreachable ();
+    }
+}
+
 /* A subroutine of expand_omp_atomic.  Attempt to implement the atomic
    operation as a normal volatile load.  */
 
@@ -6047,11 +6389,9 @@ expand_omp_atomic_load (basic_block load_bb, tree addr,
   type = TREE_TYPE (loaded_val);
   itype = TREE_TYPE (TREE_TYPE (decl));
 
-  call = build_call_expr_loc (loc, decl, 2, addr,
-			      build_int_cst (NULL,
-					     gimple_omp_atomic_seq_cst_p (stmt)
-					     ? MEMMODEL_SEQ_CST
-					     : MEMMODEL_RELAXED));
+  enum omp_memory_order omo = gimple_omp_atomic_memory_order (stmt);
+  tree mo = build_int_cst (NULL, omp_memory_order_to_memmodel (omo));
+  call = build_call_expr_loc (loc, decl, 2, addr, mo);
   if (!useless_type_conversion_p (type, itype))
     call = fold_build1_loc (loc, VIEW_CONVERT_EXPR, type, call);
   call = build2_loc (loc, MODIFY_EXPR, void_type_node, loaded_val, call);
@@ -6122,11 +6462,9 @@ expand_omp_atomic_store (basic_block load_bb, tree addr,
 
   if (!useless_type_conversion_p (itype, type))
     stored_val = fold_build1_loc (loc, VIEW_CONVERT_EXPR, itype, stored_val);
-  call = build_call_expr_loc (loc, decl, 3, addr, stored_val,
-			      build_int_cst (NULL,
-					     gimple_omp_atomic_seq_cst_p (stmt)
-					     ? MEMMODEL_SEQ_CST
-					     : MEMMODEL_RELAXED));
+  enum omp_memory_order omo = gimple_omp_atomic_memory_order (stmt);
+  tree mo = build_int_cst (NULL, omp_memory_order_to_memmodel (omo));
+  call = build_call_expr_loc (loc, decl, 3, addr, stored_val, mo);
   if (exchange)
     {
       if (!useless_type_conversion_p (type, itype))
@@ -6167,7 +6505,6 @@ expand_omp_atomic_fetch_op (basic_block load_bb,
   enum tree_code code;
   bool need_old, need_new;
   machine_mode imode;
-  bool seq_cst;
 
   /* We expect to find the following sequences:
 
@@ -6200,7 +6537,9 @@ expand_omp_atomic_fetch_op (basic_block load_bb,
     return false;
   need_new = gimple_omp_atomic_need_value_p (gsi_stmt (gsi));
   need_old = gimple_omp_atomic_need_value_p (last_stmt (load_bb));
-  seq_cst = gimple_omp_atomic_seq_cst_p (last_stmt (load_bb));
+  enum omp_memory_order omo
+    = gimple_omp_atomic_memory_order (last_stmt (load_bb));
+  enum memmodel mo = omp_memory_order_to_memmodel (omo);
   gcc_checking_assert (!need_old || !need_new);
 
   if (!operand_equal_p (gimple_assign_lhs (stmt), stored_val, 0))
@@ -6267,9 +6606,7 @@ expand_omp_atomic_fetch_op (basic_block load_bb,
      use the RELAXED memory model.  */
   call = build_call_expr_loc (loc, decl, 3, addr,
 			      fold_convert_loc (loc, itype, rhs),
-			      build_int_cst (NULL,
-					     seq_cst ? MEMMODEL_SEQ_CST
-						     : MEMMODEL_RELAXED));
+			      build_int_cst (NULL, mo));
 
   if (need_old || need_new)
     {
@@ -7921,6 +8258,10 @@ build_omp_regions_1 (basic_block bb, struct omp_region *parent,
 	    /* #pragma omp ordered depend is also just a stand-alone
 	       directive.  */
 	    region = NULL;
+	  else if (code == GIMPLE_OMP_TASK
+		   && gimple_omp_task_taskwait_p (stmt))
+	    /* #pragma omp taskwait depend(...) is a stand-alone directive.  */
+	    region = NULL;
 	  /* ..., this directive becomes the parent for a new region.  */
 	  if (region)
 	    parent = region;
@@ -8111,7 +8452,6 @@ omp_make_gimple_edges (basic_block bb, struct omp_region **region,
   switch (code)
     {
     case GIMPLE_OMP_PARALLEL:
-    case GIMPLE_OMP_TASK:
     case GIMPLE_OMP_FOR:
     case GIMPLE_OMP_SINGLE:
     case GIMPLE_OMP_TEAMS:
@@ -8124,6 +8464,13 @@ omp_make_gimple_edges (basic_block bb, struct omp_region **region,
       fallthru = true;
       break;
 
+    case GIMPLE_OMP_TASK:
+      cur_region = new_omp_region (bb, code, cur_region);
+      fallthru = true;
+      if (gimple_omp_task_taskwait_p (last))
+	cur_region = cur_region->outer;
+      break;
+
     case GIMPLE_OMP_ORDERED:
       cur_region = new_omp_region (bb, code, cur_region);
       fallthru = true;