c-cppbuiltin.c (c_cpp_builtins): Change _OPENMP value to 200805.

	* c-cppbuiltin.c (c_cpp_builtins): Change _OPENMP value to
	200805.
	* langhooks.h (struct lang_hooks_for_decls): Add omp_finish_clause.
	Add omp_private_outer_ref hook, add another argument to
	omp_clause_default_ctor hook.
	* langhooks-def.h (LANG_HOOKS_OMP_FINISH_CLAUSE): Define.
	(LANG_HOOKS_OMP_PRIVATE_OUTER_REF): Define.
	(LANG_HOOKS_OMP_CLAUSE_DEFAULT_CTOR): Change to
	hook_tree_tree_tree_tree_null.
	(LANG_HOOKS_DECLS): Add LANG_HOOKS_OMP_FINISH_CLAUSE and
	LANG_HOOKS_OMP_PRIVATE_OUTER_REF.
	* hooks.c (hook_tree_tree_tree_tree_null): New function.
	* hooks.h (hook_tree_tree_tree_tree_null): New prototype.
	* tree.def (OMP_TASK): New tree code.
	* tree.h (OMP_TASK_COPYFN, OMP_TASK_ARG_SIZE, OMP_TASK_ARG_ALIGN,
	OMP_CLAUSE_PRIVATE_OUTER_REF, OMP_CLAUSE_LASTPRIVATE_STMT,
	OMP_CLAUSE_COLLAPSE_ITERVAR, OMP_CLAUSE_COLLAPSE_COUNT,
	OMP_TASKREG_CHECK, OMP_TASKREG_BODY, OMP_TASKREG_CLAUSES,
	OMP_TASKREG_FN, OMP_TASKREG_DATA_ARG, OMP_TASK_BODY,
	OMP_TASK_CLAUSES, OMP_TASK_FN, OMP_TASK_DATA_ARG,
	OMP_CLAUSE_COLLAPSE_EXPR): Define.
	(enum omp_clause_default_kind): Add OMP_CLAUSE_DEFAULT_FIRSTPRIVATE.
	(OMP_DIRECTIVE_P): Add OMP_TASK.
	(OMP_CLAUSE_COLLAPSE, OMP_CLAUSE_UNTIED): New clause codes.
	(OMP_CLAUSE_SCHEDULE_AUTO): New schedule kind.
	* tree.c (omp_clause_code_name): Add OMP_CLAUSE_COLLAPSE
	and OMP_CLAUSE_UNTIED entries.
	(omp_clause_num_ops): Likewise.  Increase OMP_CLAUSE_LASTPRIVATE
	num_ops to 2.
	(walk_tree_1): Handle OMP_CLAUSE_COLLAPSE and OMP_CLAUSE_UNTIED.
	Walk OMP_CLAUSE_LASTPRIVATE_STMT.
	* tree-pretty-print.c (dump_omp_clause): Handle
	OMP_CLAUSE_SCHEDULE_AUTO, OMP_CLAUSE_UNTIED, OMP_CLAUSE_COLLAPSE,
	OMP_CLAUSE_DEFAULT_FIRSTPRIVATE.
	(dump_generic_node): Handle OMP_TASK and collapsed OMP_FOR loops.
	* c-omp.c (c_finish_omp_for): Allow pointer iterators.  Remove
	warning about unsigned iterators.  Change decl/init/cond/incr
	arguments to TREE_VECs, check arguments for all collapsed loops.
	(c_finish_omp_taskwait): New function.
	(c_split_parallel_clauses): Put OMP_CLAUSE_COLLAPSE clause to
	ws_clauses.
	* c-parser.c (c_parser_omp_for_loop): Parse collapsed loops.  Call
	default_function_array_conversion on init.  Add par_clauses argument.
	If decl is present in parallel's lastprivate clause, change it to
	shared and add lastprivate clause for decl to OMP_FOR_CLAUSES.
	Add clauses argument, on success set OMP_FOR_CLAUSES to it.  Look up
	collapse count in clauses.
	(c_parser_omp_for, c_parser_omp_parallel): Adjust
	c_parser_omp_for_loop callers.
	(OMP_FOR_CLAUSE_MASK): Add 1 << PRAGMA_OMP_CLAUSE_COLLAPSE.
	(c_parser_pragma): Handle PRAGMA_OMP_TASKWAIT.
	(c_parser_omp_clause_name): Handle collapse and untied clauses.
	(c_parser_omp_clause_collapse, c_parser_omp_clause_untied): New
	functions.
	(c_parser_omp_clause_schedule): Handle schedule(auto).
	Include correct location in the error message.
	(c_parser_omp_all_clauses): Handle PRAGMA_OMP_CLAUSE_COLLAPSE
	and PRAGMA_OMP_CLAUSE_UNTIED.
	(OMP_TASK_CLAUSE_MASK): Define.
	(c_parser_omp_task, c_parser_omp_taskwait): New functions.
	(c_parser_omp_construct): Handle PRAGMA_OMP_TASK.
	* tree-nested.c (convert_nonlocal_omp_clauses,
	convert_local_omp_clauses): Handle OMP_CLAUSE_LASTPRIVATE_STMT,
	OMP_CLAUSE_REDUCTION_INIT, OMP_CLAUSE_REDUCTION_MERGE,
	OMP_CLAUSE_COLLAPSE and OMP_CLAUSE_UNTIED.
	Don't handle TREE_STATIC or DECL_EXTERNAL VAR_DECLs in
	OMP_CLAUSE_DECL.
	(conver_nonlocal_reference, convert_local_reference,
	convert_call_expr): Handle OMP_TASK the same as OMP_PARALLEL.  Use
	OMP_TASKREG_* macros rather than OMP_PARALLEL_*.
	(walk_omp_for): Adjust for OMP_FOR_{INIT,COND,INCR} changes.
	* tree-gimple.c (is_gimple_stmt): Handle OMP_TASK.
	* c-tree.h (c_begin_omp_task, c_finish_omp_task): New prototypes.
	* c-pragma.h (PRAGMA_OMP_TASK, PRAGMA_OMP_TASKWAIT): New.
	(PRAGMA_OMP_CLAUSE_COLLAPSE, PRAGMA_OMP_CLAUSE_UNTIED): New.
	* c-typeck.c (c_begin_omp_task, c_finish_omp_task): New functions.
	(c_finish_omp_clauses): Handle OMP_CLAUSE_COLLAPSE and
	OMP_CLAUSE_UNTIED.
	* c-pragma.c (init_pragma): Init omp task and omp taskwait pragmas.
	* c-common.h (c_finish_omp_taskwait): New prototype.
	* gimple-low.c (lower_stmt): Handle OMP_TASK.
	* tree-parloops.c (create_parallel_loop): Create 1 entry
	vectors for OMP_FOR_{INIT,COND,INCR}.
	* tree-cfg.c (remove_useless_stmts_1): Handle OMP_* containers.
	(make_edges): Handle OMP_TASK.
	* tree-ssa-operands.c (get_expr_operands): Handle collapsed OMP_FOR
	loops, adjust for OMP_FOR_{INIT,COND,INCR} changes.
	* tree-inline.c (estimate_num_insns_1): Handle OMP_TASK.
	* builtin-types.def (BT_PTR_ULONGLONG, BT_PTR_FN_VOID_PTR_PTR,
	BT_FN_BOOL_ULONGLONGPTR_ULONGLONGPTR,
	BT_FN_BOOL_BOOL_ULL_ULL_ULL_ULLPTR_ULLPTR,
	BT_FN_BOOL_BOOL_ULL_ULL_ULL_ULL_ULLPTR_ULLPTR,
	BT_FN_VOID_OMPFN_PTR_OMPCPYFN_LONG_LONG_BOOL_UINT): New.
	* omp-builtins.def (BUILT_IN_GOMP_TASK, BUILT_IN_GOMP_TASKWAIT,
	BUILT_IN_GOMP_LOOP_ULL_STATIC_START,
	BUILT_IN_GOMP_LOOP_ULL_DYNAMIC_START,
	BUILT_IN_GOMP_LOOP_ULL_GUIDED_START,
	BUILT_IN_GOMP_LOOP_ULL_RUNTIME_START,
	BUILT_IN_GOMP_LOOP_ULL_ORDERED_STATIC_START,
	BUILT_IN_GOMP_LOOP_ULL_ORDERED_DYNAMIC_START,
	BUILT_IN_GOMP_LOOP_ULL_ORDERED_GUIDED_START,
	BUILT_IN_GOMP_LOOP_ULL_ORDERED_RUNTIME_START,
	BUILT_IN_GOMP_LOOP_ULL_STATIC_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_DYNAMIC_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_GUIDED_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_RUNTIME_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_ORDERED_STATIC_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_ORDERED_DYNAMIC_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_ORDERED_GUIDED_NEXT,
	BUILT_IN_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT): New builtins.
	* gimplify.c (gimplify_omp_for): Allow pointer type for decl,
	handle POINTER_PLUS_EXPR.  If loop counter has been replaced and
	original iterator is present in lastprivate clause or if
	collapse > 1, set OMP_CLAUSE_LASTPRIVATE_STMT.  Handle collapsed
	OMP_FOR loops, adjust for OMP_FOR_{INIT,COND,INCR} changes.
	(gimplify_expr): Handle OMP_SECTIONS_SWITCH and OMP_TASK.
	(enum gimplify_omp_var_data): Add GOVD_PRIVATE_OUTER_REF.
	(omp_notice_variable): Set GOVD_PRIVATE_OUTER_REF if needed,
	if it is set, lookup var in outer contexts too.  Handle
	OMP_CLAUSE_DEFAULT_FIRSTPRIVATE.  Handle vars that are supposed
	to be implicitly determined firstprivate for task regions.
	(gimplify_scan_omp_clauses): Set GOVD_PRIVATE_OUTER_REF if needed,
	if it is set, lookup var in outer contexts too.  Set
	OMP_CLAUSE_PRIVATE_OUTER_REF if GOVD_PRIVATE_OUTER_REF is set.
	Handle OMP_CLAUSE_LASTPRIVATE_STMT, OMP_CLAUSE_COLLAPSE and
	OMP_CLAUSE_UNTIED.  Take region_type as last argument
	instead of in_parallel and in_combined_parallel.
	(gimplify_omp_parallel, gimplify_omp_for, gimplify_omp_workshare):
	Adjust callers.
	(gimplify_adjust_omp_clauses_1): Set OMP_CLAUSE_PRIVATE_OUTER_REF if
	GOVD_PRIVATE_OUTER_REF is set.  Call omp_finish_clause
	langhook.
	(new_omp_context): Set default_kind to
	OMP_CLAUSE_DEFAULT_UNSPECIFIED for OMP_TASK regions.
	(omp_region_type): New enum.
	(struct gimplify_omp_ctx): Remove is_parallel and is_combined_parallel
	fields, add region_type.
	(new_omp_context): Take region_type as argument instead of is_parallel
	and is_combined_parallel.
	(gimple_add_tmp_var, omp_firstprivatize_variable, omp_notice_variable,
	omp_is_private, omp_check_private): Adjust ctx->is_parallel and
	ctx->is_combined_parallel checks.
	(gimplify_omp_task): New function.
	(gimplify_adjust_omp_clauses): Handle OMP_CLAUSE_COLLAPSE and
	OMP_CLAUSE_UNTIED.
	* omp-low.c (extract_omp_for_data): Use schedule(static)
	for schedule(auto).  Handle pointer and unsigned iterators.
	Compute fd->iter_type.  Handle POINTER_PLUS_EXPR increments.
	Add loops argument.  Extract data for collapsed OMP_FOR loops.
	(expand_parallel_call): Assert sched_kind isn't auto,
	map runtime schedule to index 3.
	(struct omp_for_data_loop): New type.
	(struct omp_for_data): Remove v, n1, n2, step, cond_code fields.
	Add loop, loops, collapse and iter_type fields.
	(workshare_safe_to_combine_p): Disallow combined for if
	iter_type is unsigned long long.  Don't combine collapse > 1 loops
	unless all bounds and steps are constant.  Adjust extract_omp_for_data
	caller.
	(expand_omp_for_generic): Handle pointer, unsigned and long long
	iterators.  Handle collapsed OMP_FOR loops.  Adjust
	for struct omp_for_data changes.  If libgomp function doesn't return
	boolean_type_node, add comparison of the return value with 0.
	(expand_omp_for_static_nochunk, expand_omp_for_static_chunk): Handle
	pointer, unsigned and long long iterators.  Adjust for struct
	omp_for_data changes.
	(expand_omp_for): Assert sched_kind isn't auto, map runtime schedule
	to index 3.  Use GOMP_loop_ull*{start,next} if iter_type is
	unsigned long long.  Allocate loops array, pass it to
	extract_omp_for_data.  For collapse > 1 loops use always
	expand_omp_for_generic.
	(omp_context): Add sfield_map and srecord_type fields.
	(is_task_ctx, lookup_sfield): New functions.
	(use_pointer_for_field): Use is_task_ctx helper.  Change first
	argument's type from const_tree to tree.  Clarify comment.
	In OMP_TASK disallow copy-in/out sharing.
	(build_sender_ref): Call lookup_sfield instead of lookup_field.
	(install_var_field): Add mask argument.  Populate both record_type
	and srecord_type if needed.
	(delete_omp_context): Destroy sfield_map, clear DECL_ABSTRACT_ORIGIN
	in srecord_type.
	(fixup_child_record_type): Also remap FIELD_DECL's DECL_SIZE{,_UNIT}
	and DECL_FIELD_OFFSET.
	(scan_sharing_clauses): Adjust install_var_field callers.  For
	firstprivate clauses on explicit tasks allocate the var by value in
	record_type unconditionally, rather than by reference.
	Handle OMP_CLAUSE_PRIVATE_OUTER_REF.  Scan OMP_CLAUSE_LASTPRIVATE_STMT.
	Use is_taskreg_ctx instead of is_parallel_ctx.
	Handle OMP_CLAUSE_COLLAPSE and OMP_CLAUSE_UNTIED.
	(create_omp_child_function_name): Add task_copy argument, use
	*_omp_cpyfn* names if it is true.
	(create_omp_child_function): Add task_copy argument, if true create
	*_omp_cpyfn* helper function.
	(scan_omp_parallel): Adjust create_omp_child_function callers.
	Rename parallel_nesting_level to taskreg_nesting_level.
	(scan_omp_task): New function.
	(lower_rec_input_clauses): Don't run constructors for firstprivate
	explicit task vars which are initialized by *_omp_cpyfn*.  
	Pass outer var ref to omp_clause_default_ctor hook if
	OMP_CLAUSE_PRIVATE_OUTER_REF or OMP_CLAUSE_LASTPRIVATE.
	Replace OMP_CLAUSE_REDUCTION_PLACEHOLDER decls in
	OMP_CLAUSE_REDUCTION_INIT.
	(lower_send_clauses): Clear DECL_ABSTRACT_ORIGIN if in task to
	avoid duplicate setting of fields.  Handle
	OMP_CLAUSE_PRIVATE_OUTER_REF.
	(lower_send_shared_vars): Use srecord_type if non-NULL.  Don't
	copy-out if TREE_READONLY, only copy-in.
	(expand_task_copyfn): New function.
	(expand_task_call): New function.
	(struct omp_taskcopy_context): New type.
	(task_copyfn_copy_decl, task_copyfn_remap_type, create_task_copyfn):
	New functions.
	(lower_omp_parallel): Rename to...
	(lower_omp_taskreg): ... this.  Use OMP_TASKREG_* macros where needed.
	Call create_task_copyfn if srecord_type is needed.  Adjust
	sender_decl type.
	(task_shared_vars): New variable.
	(check_omp_nesting_restrictions): Warn if work-sharing,
	barrier, master or ordered region is closely nested inside OMP_TASK.
	Add warnings for barrier if closely nested inside of work-sharing,
	ordered, or master region.
	(scan_omp_1): Call check_omp_nesting_restrictions even for
	GOMP_barrier calls.  Rename parallel_nesting_level to
	taskreg_nesting_level.  Handle OMP_TASK.
	(lower_lastprivate_clauses): Even if some lastprivate is found on a
	work-sharing construct, continue looking for them on parent parallel
	construct.
	(lower_omp_for_lastprivate): Add lastprivate clauses
	to the beginning of dlist rather than end.  Adjust for struct
	omp_for_data changes.
	(lower_omp_for): Add rec input clauses before OMP_FOR_PRE_BODY,
	not after it.  Handle collapsed OMP_FOR loops, adjust for
	OMP_FOR_{INIT,COND,INCR} changes, adjust extract_omp_for_data
	caller.
	(get_ws_args_for): Adjust extract_omp_for_data caller.
	(scan_omp_for): Handle collapsed OMP_FOR
	loops, adjust for OMP_FOR_{INIT,COND,INCR} changes.
	(lower_omp_single_simple): If libgomp function doesn't return
	boolean_type_node, add comparison of the return value with 0.
	(diagnose_sb_1, diagnose_sb_2): Handle collapsed OMP_FOR
	loops, adjust for OMP_FOR_{INIT,COND,INCR} changes.  Handle OMP_TASK.
	(parallel_nesting_level): Rename to...
	(taskreg_nesting_level): ... this.
	(is_taskreg_ctx): New function.
	(build_outer_var_ref, omp_copy_decl): Use is_taskreg_ctx instead
	of is_parallel_ctx.
	(execute_lower_omp): Rename parallel_nesting_level to
	taskreg_nesting_level.
	(expand_omp_parallel): Rename to...
	(expand_omp_taskreg): ... this.  Use OMP_TASKREG_* macros where needed.
	Call omp_task_call for OMP_TASK regions.
	(expand_omp): Adjust caller, handle OMP_TASK.
	(lower_omp_1): Adjust lower_omp_taskreg caller, handle OMP_TASK.

	* bitmap.c (bitmap_default_obstack_depth): New variable.
	(bitmap_obstack_initialize, bitmap_obstack_release): Do nothing
	if argument is NULL and bitmap_default_obstack is already initialized.
	* ipa-struct-reorg.c (do_reorg_1): Call bitmap_obstack_release
	at the end.
	* matrix-reorg.c (matrix_reorg): Likewise.
cp/
	* cp-tree.h (cxx_omp_finish_clause, cxx_omp_create_clause_info,
	dependent_omp_for_p, begin_omp_task, finish_omp_task,
	finish_omp_taskwait): New prototypes.
	(cxx_omp_clause_default_ctor): Add outer argument.
	(finish_omp_for): Add new clauses argument.
	* cp-gimplify.c (cxx_omp_finish_clause): New function.
	(cxx_omp_predetermined_sharing): Moved from semantics.c, rewritten.
	(cxx_omp_clause_default_ctor): Add outer argument.
	(cp_genericize_r): Walk OMP_CLAUSE_LASTPRIVATE_STMT.
	* cp-objcp-common.h (LANG_HOOKS_OMP_FINISH_CLAUSE): Define.
	* parser.c (cp_parser_omp_for_loop): Parse collapsed for loops.
	Add par_clauses argument.  If decl is present in parallel's
	lastprivate clause, change that clause to shared and add
	a lastprivate clause for decl to OMP_FOR_CLAUSES.
	Fix wording of error messages.  Adjust finish_omp_for caller.
	Add clauses argument.  Parse loops with random access iterators.
	(cp_parser_omp_clause_collapse, cp_parser_omp_clause_untied): New
	functions.
	(cp_parser_omp_for, cp_parser_omp_parallel): Adjust
	cp_parser_omp_for_loop callers.
	(cp_parser_omp_for_cond, cp_parser_omp_for_incr): New helper
	functions.
	(cp_parser_omp_clause_name): Handle collapse and untied
	clauses.
	(cp_parser_omp_clause_schedule): Handle auto schedule.
	(cp_parser_omp_all_clauses): Handle PRAGMA_OMP_CLAUSE_COLLAPSE
	and PRAGMA_OMP_CLAUSE_UNTIED.
	(OMP_FOR_CLAUSE_MASK): Add PRAGMA_OMP_CLAUSE_COLLAPSE.
	(OMP_TASK_CLAUSE_MASK): Define.
	(cp_parser_omp_task, cp_parser_omp_taskwait): New functions.
	(cp_parser_omp_construct): Handle PRAGMA_OMP_TASK.
	(cp_parser_pragma): Handle PRAGMA_OMP_TASK and
	PRAGMA_OMP_TASKWAIT.
	* pt.c (tsubst_omp_clauses): Handle OMP_CLAUSE_COLLAPSE and
	OMP_CLAUSE_UNTIED.  Handle OMP_CLAUSE_LASTPRIVATE_STMT.
	(tsubst_omp_for_iterator): New function.
	(dependent_omp_for_p): New function.
	(tsubst_expr) <case OMP_FOR>: Use it.  Handle collapsed OMP_FOR
	loops.  Adjust finish_omp_for caller.  Handle loops with random
	access iterators.  Adjust for OMP_FOR_{INIT,COND,INCR} changes.
	(tsubst_expr): Handle OMP_TASK.
	* semantics.c (cxx_omp_create_clause_info): New function.
	(finish_omp_clauses): Call it.  Handle OMP_CLAUSE_UNTIED and
	OMP_CLAUSE_COLLAPSE.
	(cxx_omp_predetermined_sharing): Removed.
	* semantics.c (finish_omp_for): Allow pointer iterators.  Use
	handle_omp_for_class_iterator and dependent_omp_for_p.  Handle
	collapsed for loops.  Adjust c_finish_omp_for caller.  Add new
	clauses argument.  Fix check for type dependent cond or incr.
	Set OMP_FOR_CLAUSES to clauses.  Use cp_convert instead of
	fold_convert to convert incr amount to difference_type.  Only
	fold if not in template.  If decl is mentioned in lastprivate
	clause, set OMP_CLAUSE_LASTPRIVATE_STMT.  Handle loops with random
	access iterators.  Adjust for OMP_FOR_{INIT,COND,INCR}
	changes.
	(finish_omp_threadprivate): Allow static class members of the
	current class.
	(handle_omp_for_class_iterator, begin_omp_task, finish_omp_task,
	finish_omp_taskwait): New functions.

	* parser.c (cp_parser_binary_expression): Add prec argument.
	(cp_parser_assignment_expression): Adjust caller.
	* cp-tree.h (outer_curly_brace_block): New prototype.
	* decl.c (outer_curly_brace_block): No longer static.
fortran/
	* scanner.c (skip_free_comments, skip_fixed_comments): Handle tabs.
	* parse.c (next_free): Allow tab after !$omp.
	(decode_omp_directive): Handle !$omp task, !$omp taskwait
	and !$omp end task.
	(case_executable): Add ST_OMP_TASKWAIT.
	(case_exec_markers): Add ST_OMP_TASK.
	(gfc_ascii_statement): Handle ST_OMP_TASK, ST_OMP_END_TASK and
	ST_OMP_TASKWAIT.
	(parse_omp_structured_block, parse_executable): Handle ST_OMP_TASK.
	* gfortran.h (gfc_find_sym_in_expr): New prototype.
	(gfc_statement): Add ST_OMP_TASK, ST_OMP_END_TASK and ST_OMP_TASKWAIT.
	(gfc_omp_clauses): Add OMP_SCHED_AUTO to sched_kind,
	OMP_DEFAULT_FIRSTPRIVATE to default_sharing.  Add collapse and
	untied fields.
	(gfc_exec_op): Add EXEC_OMP_TASK and EXEC_OMP_TASKWAIT.
	* f95-lang.c (LANG_HOOKS_OMP_CLAUSE_COPY_CTOR,
	LANG_HOOKS_OMP_CLAUSE_ASSIGN_OP, LANG_HOOKS_OMP_CLAUSE_DTOR,
	LANG_HOOKS_OMP_PRIVATE_OUTER_REF): Define.
	* trans.h (gfc_omp_clause_default_ctor): Add another argument.
	(gfc_omp_clause_copy_ctor, gfc_omp_clause_assign_op,
	gfc_omp_clause_dtor, gfc_omp_private_outer_ref): New prototypes.
	* types.def (BT_ULONGLONG, BT_PTR_ULONGLONG,
	BT_FN_BOOL_ULONGLONGPTR_ULONGLONGPTR,
	BT_FN_BOOL_BOOL_ULL_ULL_ULL_ULLPTR_ULLPTR,
	BT_FN_BOOL_BOOL_ULL_ULL_ULL_ULL_ULLPTR_ULLPTR,
	BT_FN_VOID_PTR_PTR, BT_PTR_FN_VOID_PTR_PTR,
	BT_FN_VOID_OMPFN_PTR_OMPCPYFN_LONG_LONG_BOOL_UINT): New.
	(BT_BOOL): Use integer type with BOOL_TYPE_SIZE rather
	than boolean_type_node.
	* dump-parse-tree.c (gfc_show_omp_node): Handle EXEC_OMP_TASK,
	EXEC_OMP_TASKWAIT, OMP_SCHED_AUTO, OMP_DEFAULT_FIRSTPRIVATE,
	untied and collapse clauses.
	(gfc_show_code_node): Handle EXEC_OMP_TASK and EXEC_OMP_TASKWAIT.
	* trans.c (gfc_trans_code): Handle EXEC_OMP_TASK and
	EXEC_OMP_TASKWAIT.
	* st.c (gfc_free_statement): Likewise.
	* resolve.c (gfc_resolve_blocks, resolve_code): Likewise.
	(find_sym_in_expr): Rename to...
	(gfc_find_sym_in_expr): ... this.  No longer static.
	(resolve_allocate_expr, resolve_ordinary_assign): Adjust caller.
	* match.h (gfc_match_omp_task, gfc_match_omp_taskwait): New
	prototypes.
	* openmp.c (resolve_omp_clauses): Allow allocatable arrays in
	firstprivate, lastprivate, reduction, copyprivate and copyin
	clauses.
	(omp_current_do_code): Made static.
	(omp_current_do_collapse): New variable.
	(gfc_resolve_omp_do_blocks): Compute omp_current_do_collapse,
	clear omp_current_do_code and omp_current_do_collapse on return.
	(gfc_resolve_do_iterator): Handle collapsed do loops.
	(resolve_omp_do): Likewise, diagnose errorneous collapsed do loops.
	(OMP_CLAUSE_COLLAPSE, OMP_CLAUSE_UNTIED): Define.
	(gfc_match_omp_clauses): Handle default (firstprivate),
	schedule (auto), untied and collapse (n) clauses.
	(OMP_DO_CLAUSES): Add OMP_CLAUSE_COLLAPSE.
	(OMP_TASK_CLAUSES): Define.
	(gfc_match_omp_task, gfc_match_omp_taskwait): New functions.
	* trans-openmp.c (gfc_omp_private_outer_ref): New function.
	(gfc_omp_clause_default_ctor): Add outer argument.  For allocatable
	arrays allocate them with the bounds of the outer var if outer
	var is allocated.
	(gfc_omp_clause_copy_ctor, gfc_omp_clause_assign_op,
	gfc_omp_clause_dtor): New functions.
	(gfc_trans_omp_array_reduction): If decl is allocatable array,
	allocate it with outer var's bounds in OMP_CLAUSE_REDUCTION_INIT
	and deallocate it in OMP_CLAUSE_REDUCTION_MERGE.
	(gfc_omp_predetermined_sharing): Return OMP_CLAUSE_DEFAULT_SHARED
	for assumed-size arrays.
	(gfc_trans_omp_do): Add par_clauses argument.  If dovar is
	present in lastprivate clause and do loop isn't simple,
	set OMP_CLAUSE_LASTPRIVATE_STMT.  If dovar is present in
	parallel's lastprivate clause, change it to shared and add
	lastprivate clause to OMP_FOR_CLAUSES.  Handle collapsed do loops.
	(gfc_trans_omp_directive): Adjust gfc_trans_omp_do callers.
	(gfc_trans_omp_parallel_do): Likewise.  Move collapse clause to
	OMP_FOR from OMP_PARALLEL.
	(gfc_trans_omp_clauses): Handle OMP_SCHED_AUTO,
	OMP_DEFAULT_FIRSTPRIVATE, untied and collapse clauses.
	(gfc_trans_omp_task, gfc_trans_omp_taskwait): New functions.
	(gfc_trans_omp_directive): Handle EXEC_OMP_TASK and
	EXEC_OMP_TASKWAIT.
gcc/testsuite/
	* gcc.dg/gomp/collapse-1.c: New test.
	* gcc.dg/gomp/nesting-1.c: New test.
	* g++.dg/gomp/task-1.C: New test.
	* g++.dg/gomp/predetermined-1.C: New test.
	* g++.dg/gomp/tls-4.C: New test.
	* gfortran.dg/gomp/collapse1.f90: New test.
	* gfortran.dg/gomp/sharing-3.f90: New test.
	* gcc.dg/gomp/pr27499.c (foo): Remove is unsigned dg-warning.
	* g++.dg/gomp/pr27499.C (foo): Likewise.
	* g++.dg/gomp/for-16.C (foo): Likewise.
	* g++.dg/gomp/tls-3.C: Remove dg-error, add S::s definition.
	* g++.dg/gomp/pr34607.C: Adjust dg-error location.
	* g++.dg/gomp/for-16.C (foo): Add a new dg-error.
	* gcc.dg/gomp/appendix-a/a.35.4.c: Add dg-warning.
	* gcc.dg/gomp/appendix-a/a.35.6.c: Likewise.
	* gfortran.dg/gomp/appendix-a/a.35.4.f90: Likewise.
	* gfortran.dg/gomp/appendix-a/a.35.6.f90: Likewise.
	* gfortran.dg/gomp/omp_parse1.f90: Remove !$omp tab test.
	* gfortran.dg/gomp/appendix-a/a.33.4.f90: Remove dg-error
	about allocatable array.
	* gfortran.dg/gomp/reduction1.f90: Likewise.
libgomp/
	* configure.ac (LIBGOMP_GNU_SYMBOL_VERSIONING): New AC_DEFINE.
	Substitute also OMP_*LOCK_25*.
	* configure: Regenerated.
	* config.h.in: Regenerated.
	* Makefile.am (libgomp_la_SOURCES): Add loop_ull.c, iter_ull.c,
	ptrlock.c and task.c.
	* Makefile.in: Regenerated.
	* testsuite/Makefile.in: Regenerated.
	* task.c: New file.
	* loop_ull.c: New file.
	* iter_ull.c: New file.
	* libgomp.h: Include ptrlock.h.
	(enum gomp_task_kind): New type.
	(struct gomp_team): Add task_lock, task_queue, task_count,
	task_running_count, single_count fields.  Add
	work_share_list_free_lock ifndef HAVE_SYNC_BUILTINS.
	Remove work_share_lock, generation_mask,
	oldest_live_gen, num_live_gen and init_work_shares fields, add
	work work_share_list_alloc, work_share_list_free and work_share_chunk
	fields.  Change work_shares from pointer to pointers into an array.
	Change ordered_release field into gomp_sem_t ** from flexible array
	member.  Add implicit_task and initial_work_shares fields.
	Move close to the end of the struct.
	(struct gomp_team_state): Add single_count, last_work_share,
	active_level and level fields, remove work_share_generation.
	(gomp_barrier_handle_tasks): New prototype.
	(gomp_finish_task): New inline function.
	(struct gomp_work_share): Move chunk_size, end, incr into
	transparent union/struct, add chunk_size_ull, end_ll, incr_ll and
	next_ll fields.  Reshuffle fields.  Add next_alloc,
	next_ws, next_free and inline_ordered_team_ids fields, change
	ordered_team_ids into pointer from flexible array member.
	Add mode field.  Put lock and next into a different cache line
	from most of the write-once fields.
	(gomp_iter_ull_static_next, gomp_iter_ull_dynamic_next_locked,
	gomp_iter_ull_guided_next_locked, gomp_iter_ull_dynamic_next,
	gomp_iter_ull_guided_next): New prototypes.
	(gomp_new_icv): New prototype.
	(struct gomp_thread): Add thread_pool and task fields.
	(struct gomp_thread_pool): New type.
	(gomp_new_team): New prototype.
	(gomp_team_start): Change type of last argument.
	(gomp_new_work_share): Removed.
	(gomp_init_work_share, gomp_fini_work_share): New prototypes.
	(gomp_work_share_init_done): New static inline.
	(gomp_throttled_spin_count_var, gomp_available_cpus,
	gomp_managed_threads): New extern decls.
	(gomp_init_task): New prototype.
	(gomp_spin_count_var): New extern var decl.
	(LIBGOMP_GNU_SYMBOL_VERSIONING): Undef if no visibility
	or no alias support, or if not PIC.
	(gomp_init_lock_30, gomp_destroy_lock_30, gomp_set_lock_30,
	gomp_unset_lock_30, gomp_test_lock_30, gomp_init_nest_lock_30,
	gomp_destroy_nest_lock_30, gomp_set_nest_lock_30,
	gomp_unset_nest_lock_30, gomp_test_nest_lock_30, gomp_init_lock_25,
	gomp_destroy_lock_25, gomp_set_lock_25, gomp_unset_lock_25,
	gomp_test_lock_25, gomp_init_nest_lock_25, gomp_destroy_nest_lock_25,
	gomp_set_nest_lock_25, gomp_unset_nest_lock_25,
	gomp_test_nest_lock_25): New prototypes.
	(omp_lock_symver, strong_alias): Define.
	(gomp_remaining_threads_count, gomp_remaining_threads_lock): New
	decls.
	(gomp_end_task): New.
	(struct gomp_task_icv, gomp_global_icv): New.
	(gomp_thread_limit_var, gomp_max_active_levels_var): New.
	(struct gomp_task): New.
	(gomp_nthreads_var, gomp_dyn_var, gomp_nest_var,
	gomp_run_sched_var, gomp_run_sched_chunk): Remove.
	(gomp_icv): New.
	(gomp_schedule_type): Reorder enum to match
	omp_sched_t.
	* team.c (struct gomp_thread_start_data): Add thread_pool and task
	fields.
	(gomp_thread_start): Add gomp_team_barrier_wait call.
	For non-nested case remove clearing of docked thread thr fields.
	Use pool fields instead of global gomp_* variables.  Use
	gomp_barrier_wait_last when needed.  Initialize ts.active_level.
	Create tasks for each member thread.
	(free_team): Only destroy team barrier, task_lock here and free it.
	(gomp_free_thread): Free last_team if non-NULL.
	(gomp_team_end): Call gomp_team_barrier_wait instead of
	gomp_barrier_wait.  For nested case call one extra
	gomp_barrier_wait.  Move here some destruction from free_team.
	Call free_team on pool->last_team if any, rather than freeing
	current team.  Destroy work_share_list_free_lock ifndef
	HAVE_SYNC_BUILTINS.
	(gomp_new_icv): New function.
	(gomp_threads, gomp_threads_size, gomp_threads_used,
	gomp_threads_dock): Removed.
	(gomp_thread_destructor): New variable.
	(gomp_new_thread_pool, gomp_free_pool_helper, gomp_free_thread): New
	functions.
	(gomp_team_start): Create new pool if current thread doesn't have
	one.  Use pool fields instead of global gomp_* variables. 
	Initialize thread_pool field for new threads.  Clear single_count.
	Change last argument from ws to team, don't create
	new team, set ts.work_share to &team->work_shares[0] and clear
	ts.last_work_share.  Don't clear ts.work_share_generation.
	If number of threads changed, adjust atomically gomp_managed_threads.
	Use gomp_init_task instead of gomp_new_task,
	set thr->task to the corresponding implicit_task array entry.
	Create tasks for each member thread.  Initialize ts.level.
	(initialize_team): Call pthread_key_create on
	gomp_thread_destructor.
	(team_destructor): New function.
	(new_team): Removed.
	(gomp_new_team): New function.
	(free_team): Free gomp_work_share blocks chained through next_alloc,
	instead of freeing work_shares and destroying work_share_lock.
	(gomp_team_end): Call gomp_fini_work_share.  If number of threads
	changed, adjust atomically gomp_managed_threads.  Use gomp_end_task.
	* barrier.c (GOMP_barrier): Call gomp_team_barrier_wait instead
	of gomp_barrier_wait.
	* single.c (GOMP_single_copy_start): Call gomp_team_barrier_wait
	instead of gomp_barrier_wait.  Call gomp_work_share_init_done
	if gomp_work_share_start returned true.  Don't unlock ws->lock.
	(GOMP_single_copy_end): Call gomp_team_barrier_wait instead
	of gomp_barrier_wait.
	(GOMP_single_start): Rewritten if HAVE_SYNC_BUILTINS.  Call
	gomp_work_share_init_done if gomp_work_share_start returned true.
	Don't unlock ws->lock.
	* work.c: Include stddef.h.
	(free_work_share): Use work_share_list_free_lock instead
	of atomic chaining ifndef HAVE_SYNC_BUILTINS.  Add team argument.
	Call gomp_fini_work_share and then either free ws if orphaned, or
	put it into work_share_list_free list of the current team.
	(alloc_work_share, gomp_init_work_share, gomp_fini_work_share): New
	functions.
	(gomp_work_share_start, gomp_work_share_end,
	gomp_work_share_end_nowait): Rewritten.
	* omp_lib.f90.in Change some tabs to spaces to prevent warnings.
	(openmp_version): Set to 200805.
	(omp_sched_kind, omp_sched_static, omp_sched_dynamic,
	omp_sched_guided, omp_sched_auto): New parameters.
	(omp_set_schedule, omp_get_schedule, omp_get_thread_limit,
	omp_set_max_active_levels, omp_get_max_active_levels,
	omp_get_level, omp_get_ancestor_thread_num, omp_get_team_size,
	omp_get_active_level): New interfaces.
	* omp_lib.h.in (openmp_version): Set to 200805.
	(omp_sched_kind, omp_sched_static, omp_sched_dynamic,
	omp_sched_guided, omp_sched_auto): New parameters.
	(omp_set_schedule, omp_get_schedule, omp_get_thread_limit,
	omp_set_max_active_levels, omp_get_max_active_levels,
	omp_get_level, omp_get_ancestor_thread_num, omp_get_team_size,
	omp_get_active_level): New externals.
	* loop.c: Include limits.h.
	(GOMP_loop_runtime_next, GOMP_loop_ordered_runtime_next): Handle
	GFS_AUTO.
	(GOMP_loop_runtime_start, GOMP_loop_ordered_runtime_start):
	Likewise.  Use gomp_icv.
	(gomp_loop_static_start, gomp_loop_dynamic_start): Clear
	ts.static_trip here.
	(gomp_loop_static_start, gomp_loop_ordered_static_start): Call
	gomp_work_share_init_done after gomp_loop_init.  Don't unlock ws->lock.
	(gomp_loop_dynamic_start, gomp_loop_guided_start): Call
	gomp_work_share_init_done after gomp_loop_init.  If HAVE_SYNC_BUILTINS,
	don't unlock ws->lock, otherwise lock it.
	(gomp_loop_ordered_dynamic_start, gomp_loop_ordered_guided_start): Call
	gomp_work_share_init_done after gomp_loop_init.  Lock ws->lock.
	(gomp_parallel_loop_start): Call gomp_new_team instead of
	gomp_new_work_share.  Call gomp_loop_init on &team->work_shares[0].
	Adjust gomp_team_start caller.  Pass 0 as second argument to
	gomp_resolve_num_threads.
	(gomp_loop_init): For GFS_DYNAMIC, multiply ws->chunk_size by incr.
	If adding ws->chunk_size nthreads + 1 times after end won't
	overflow, set ws->mode to 1.
	* libgomp_g.h (GOMP_loop_ull_static_start, GOMP_loop_ull_dynamic_start,
	GOMP_loop_ull_guided_start, GOMP_loop_ull_runtime_start,
	GOMP_loop_ull_ordered_static_start,
	GOMP_loop_ull_ordered_dynamic_start,
	GOMP_loop_ull_ordered_guided_start,
	GOMP_loop_ull_ordered_runtime_start, GOMP_loop_ull_static_next,
	GOMP_loop_ull_dynamic_next, GOMP_loop_ull_guided_next,
	GOMP_loop_ull_runtime_next, GOMP_loop_ull_ordered_static_next,
	GOMP_loop_ull_ordered_dynamic_next, GOMP_loop_ull_ordered_guided_next,
	GOMP_loop_ull_ordered_runtime_next, GOMP_task, GOMP_taskwait): New
	prototypes.
	* libgomp.map: Export lock routines also @@OMP_2.0.
	(GOMP_loop_ordered_dynamic_first,
	GOMP_loop_ordered_guided_first, GOMP_loop_ordered_runtime_first,
	GOMP_loop_ordered_static_first): Remove.
	(GOMP_loop_ull_dynamic_next, GOMP_loop_ull_dynamic_start,
	GOMP_loop_ull_guided_next, GOMP_loop_ull_guided_start,
	GOMP_loop_ull_ordered_dynamic_next,
	GOMP_loop_ull_ordered_dynamic_start,
	GOMP_loop_ull_ordered_guided_next,
	GOMP_loop_ull_ordered_guided_start,
	GOMP_loop_ull_ordered_runtime_next,
	GOMP_loop_ull_ordered_runtime_start,
	GOMP_loop_ull_ordered_static_next,
	GOMP_loop_ull_ordered_static_start,
	GOMP_loop_ull_runtime_next, GOMP_loop_ull_runtime_start,
	GOMP_loop_ull_static_next, GOMP_loop_ull_static_start,
	GOMP_task, GOMP_taskwait): Export @@GOMP_2.0.
	(omp_set_schedule, omp_get_schedule,
	omp_get_thread_limit, omp_set_max_active_levels,
	omp_get_max_active_levels, omp_get_level,
	omp_get_ancestor_thread_num, omp_get_team_size, omp_get_active_level,
	omp_set_schedule_, omp_set_schedule_8_,
	omp_get_schedule_, omp_get_schedule_8_, omp_get_thread_limit_,
	omp_set_max_active_levels_, omp_set_max_active_levels_8_,
	omp_get_max_active_levels_, omp_get_level_,
	omp_get_ancestor_thread_num_, omp_get_ancestor_thread_num_8_,
	omp_get_team_size_, omp_get_team_size_8_, omp_get_active_level_):
	New exports @@OMP_3.0.
	* omp.h.in (omp_sched_t): New type.
	(omp_set_schedule, omp_get_schedule, omp_get_thread_limit,
	omp_set_max_active_levels, omp_get_max_active_levels,
	omp_get_level, omp_get_ancestor_thread_num, omp_get_team_size,
	omp_get_active_level): New prototypes.
	* env.c (gomp_spin_count_var, gomp_throttled_spin_count_var,
	gomp_available_cpus, gomp_managed_threads, gomp_max_active_levels_var,
	gomp_thread_limit_var, gomp_remaining_threads_count,
	gomp_remaining_threads_lock): New variables.
	(parse_spincount): New function.
	(initialize_env): Call gomp_init_num_threads unconditionally.
	Initialize gomp_available_cpus.  Call parse_spincount,
	initialize gomp_{,throttled_}spin_count_var
	depending on presence and value of OMP_WAIT_POLICY and
	GOMP_SPINCOUNT env vars.  Handle GOMP_BLOCKTIME env var.
	Handle OMP_WAIT_POLICY, OMP_MAX_ACTIVE_LEVELS,
	OMP_THREAD_LIMIT, OMP_STACKSIZE env vars.  Handle unit specification
	for GOMP_STACKSIZE.  Initialize gomp_remaining_threads_count and
	gomp_remaining_threads_lock if needed.  Use gomp_global_icv.
	(gomp_nthreads_var, gomp_dyn_var, gomp_nest_var,
	gomp_run_sched_var, gomp_run_sched_chunk): Remove.
	(gomp_global_icv): New.
	(parse_schedule): Use it.  Parse "auto".
	(omp_set_num_threads): Use gomp_icv.
	(omp_set_dynamic, omp_get_dynamic, omp_set_nested, omp_get_nested):
	Likewise.
	(omp_get_max_threads): Move from parallel.c.
	(omp_set_schedule, omp_get_schedule, omp_get_thread_limit,
	omp_set_max_active_levels, omp_get_max_active_levels): New functions,
	add ialias.
	(parse_stacksize, parse_wait_policy): New functions.
	* fortran.c: Rewrite lock wrappers, if symbol versioning provide
	both wrappers for compatibility and new locks.
	(omp_set_schedule, omp_get_schedule,
	omp_get_thread_limit, omp_set_max_active_levels,
	omp_get_max_active_levels, omp_get_level,
	omp_get_ancestor_thread_num, omp_get_team_size,
	omp_get_active_level): New ialias_redirect.
	(omp_set_schedule_, omp_set_schedule_8_,
	omp_get_schedule_, omp_get_schedule_8_, omp_get_thread_limit_,
	omp_set_max_active_levels_, omp_set_max_active_levels_8_,
	omp_get_max_active_levels_, omp_get_level_,
	omp_get_ancestor_thread_num_, omp_get_ancestor_thread_num_8_,
	omp_get_team_size_, omp_get_team_size_8_, omp_get_active_level_):
	New functions.
	* parallel.c: Include limits.h.
	(gomp_resolve_num_threads): Add count argument.  Rewritten.
	(GOMP_parallel_start): Call gomp_new_team and pass that as last
	argument to gomp_team_start.  Pass 0 as second argument to
	gomp_resolve_num_threads.
	(GOMP_parallel_end): Decrease gomp_remaining_threads_count
	if gomp_thread_limit_var != ULONG_MAX.
	(omp_in_parallel): Implement using ts.active_level.
	(omp_get_max_threads): Move to env.c.
	(omp_get_level, omp_get_ancestor_thread_num,
	omp_get_team_size, omp_get_active_level): New functions,
	add ialias.
	* sections.c (GOMP_sections_start): Call gomp_work_share_init_done
	after gomp_sections_init.  If HAVE_SYNC_BUILTINS, call
	gomp_iter_dynamic_next instead of the _locked variant and don't take
	lock around it, otherwise acquire it before calling
	gomp_iter_dynamic_next_locked.
	(GOMP_sections_next): If HAVE_SYNC_BUILTINS, call
	gomp_iter_dynamic_next instead of the _locked variant and don't take
	lock around it.
	(GOMP_parallel_sections_start): Call gomp_new_team instead of
	gomp_new_work_share.  Call gomp_sections_init on &team->work_shares[0].
	Adjust gomp_team_start caller.  Pass count as second argument to
	gomp_resolve_num_threads, don't adjust num_threads after the call.
	Use gomp_icv.
	* iter.c (gomp_iter_dynamic_next_locked): Don't multiply
	ws->chunk_size by incr.
	(gomp_iter_dynamic_next): Likewise.  If ws->mode, use more efficient
	code.
	* libgomp_f.h.in (omp_lock_25_arg_t, omp_nest_lock_25_arg_t): New
	types.
	(omp_lock_25_arg, omp_nest_lock_25_arg): New macros.
	(omp_check_defines): Check even the compat defines.
	* config/linux/ptrlock.c: New file.
	* config/linux/ptrlock.h: New file.
	* config/linux/wait.h: New file.
	* config/posix/ptrlock.c: New file.
	* config/posix/ptrlock.h: New file.
	* config/linux/bar.h (gomp_team_barrier_wait,
	gomp_team_barrier_wait_end, gomp_team_barrier_wake): New prototypes.
	(gomp_team_barrier_set_task_pending,
	gomp_team_barrier_clear_task_pending,
	gomp_team_barrier_set_waiting_for_tasks,
	gomp_team_barrier_waiting_for_tasks,
	gomp_team_barrier_done): New inlines.
	(gomp_barrier_t): Rewritten.
	(gomp_barrier_state_t): New typedef.
	(gomp_barrier_init, gomp_barrier_reinit, gomp_barrier_destroy,
	gomp_barrier_wait_start): Rewritten.
	(gomp_barrier_wait_end): Change second argument to
	gomp_barrier_state_t.
	(gomp_barrier_last_thread, gomp_barrier_wait_last): New static
	inlines.
	* config/linux/bar.c: Include wait.h instead of libgomp.h and
	futex.h.
	(gomp_barrier_wait_end): Rewritten.
	(gomp_team_barrier_wait, gomp_team_barrier_wait_end,
	gomp_team_barrier_wake, gomp_barrier_wait_last): New functions.
	* config/posix/bar.h (gomp_barrier_t): Add generation field.
	(gomp_barrier_state_t): New typedef.
	(gomp_team_barrier_wait,
	gomp_team_barrier_wait_end, gomp_team_barrier_wake): New prototypes.
	(gomp_barrier_wait_start): Or all but low 2 bits from generation
	into the return value.  Return gomp_barrier_state_t.
	(gomp_team_barrier_set_task_pending,
	gomp_team_barrier_clear_task_pending,
	gomp_team_barrier_set_waiting_for_tasks,
	gomp_team_barrier_waiting_for_tasks,
	gomp_team_barrier_done): New inlines.
	(gomp_barrier_wait_end): Change second argument to
	gomp_barrier_state_t.
	(gomp_barrier_last_thread, gomp_barrier_wait_last): New static
	inlines.
	* config/posix/bar.c (gomp_barrier_init): Clear generation field.
	(gomp_barrier_wait_end): Change second argument to
	gomp_barrier_state_t. 
	(gomp_team_barrier_wait, gomp_team_barrier_wait_end,
	gomp_team_barrier_wake): New functions.
	* config/linux/mutex.c: Include wait.h instead of libgomp.h and
	futex.h.
	(gomp_futex_wake, gomp_futex_wait): New variables.
	(gomp_mutex_lock_slow): Call do_wait instead of futex_wait.
	* config/linux/lock.c: Rewrite to make locks task owned,
	for backwards compatibility provide the old entrypoints
	if symbol versioning.  Include wait.h instead of libgomp.h and
	futex.h.
	(gomp_set_nest_lock_25): Call do_wait instead of futex_wait.
	* config/posix95/lock.c: Rewrite to make locks task owned,
	for backwards compatibility provide the old entrypoints
	if symbol versioning.
	* config/posix/lock.c: Rewrite to make locks task owned,
	for backwards compatibility provide the old entrypoints
	if symbol versioning.
	* config/linux/proc.c (gomp_init_num_threads): Use gomp_global_icv.
	(get_num_procs, gomp_dynamic_max_threads): Use gomp_icv.
	* config/posix/proc.c, config/mingw32/proc.c: Similarly.
	* config/linux/powerpc/futex.h (FUTEX_WAIT, FUTEX_WAKE): Remove.
	(sys_futex0): Return error code.
	(futex_wake, futex_wait): If ENOSYS was returned, clear
	FUTEX_PRIVATE_FLAG in gomp_futex_wa{ke,it} and retry.
	(cpu_relax, atomic_write_barrier): New static inlines.
	* config/linux/alpha/futex.h (FUTEX_WAIT, FUTEX_WAKE): Remove.
	(futex_wake, futex_wait): If ENOSYS was returned, clear
	FUTEX_PRIVATE_FLAG in gomp_futex_wa{ke,it} and retry.
	(cpu_relax, atomic_write_barrier): New static inlines.
	* config/linux/x86/futex.h (FUTEX_WAIT, FUTEX_WAKE): Remove.
	(sys_futex0): Return error code.
	(futex_wake, futex_wait): If ENOSYS was returned, clear
	FUTEX_PRIVATE_FLAG in gomp_futex_wa{ke,it} and retry.
	(cpu_relax, atomic_write_barrier): New static inlines.
	* config/linux/s390/futex.h (FUTEX_WAIT, FUTEX_WAKE): Remove.
	(sys_futex0): Return error code.
	(futex_wake, futex_wait): If ENOSYS was returned, clear
	FUTEX_PRIVATE_FLAG in gomp_futex_wa{ke,it} and retry.
	(cpu_relax, atomic_write_barrier): New static inlines.
	* config/linux/ia64/futex.h (FUTEX_WAIT, FUTEX_WAKE): Remove.
	(sys_futex0): Return error code.
	(futex_wake, futex_wait): If ENOSYS was returned, clear
	FUTEX_PRIVATE_FLAG in gomp_futex_wa{ke,it} and retry.
	(cpu_relax, atomic_write_barrier): New static inlines.
	* config/linux/sparc/futex.h (FUTEX_WAIT, FUTEX_WAKE): Remove.
	(sys_futex0): Return error code.
	(futex_wake, futex_wait): If ENOSYS was returned, clear
	FUTEX_PRIVATE_FLAG in gomp_futex_wa{ke,it} and retry.
	(cpu_relax, atomic_write_barrier): New static inlines.
	* config/linux/sem.c: Include wait.h instead of libgomp.h and
	futex.h.
	(gomp_sem_wait_slow): Call do_wait instead of futex_wait.
	* config/linux/affinity.c: Assume HAVE_SYNC_BUILTINS.
	* config/linux/omp-lock.h (omp_lock_25_t, omp_nest_lock_25_t): New
	types.
	(omp_nest_lock_t): Change owner into void *, add lock field.
	* config/posix95/omp-lock.h: Include semaphore.h.
	(omp_lock_25_t, omp_nest_lock_25_t): New types.
	(omp_lock_t): Use sem_t instead of mutex if semaphores
	aren't broken.
	(omp_nest_lock_t): Likewise.  Change owner to void *.
	* config/posix/omp-lock.h: Include semaphore.h.
	(omp_lock_25_t, omp_nest_lock_25_t): New types.
	(omp_lock_t): Use sem_t instead of mutex if semaphores
	aren't broken.
	(omp_nest_lock_t): Likewise.  Add owner field.

	* testsuite/libgomp.c/collapse-1.c: New test.
	* testsuite/libgomp.c/collapse-2.c: New test.
	* testsuite/libgomp.c/collapse-3.c: New test.
	* testsuite/libgomp.c/icv-1.c: New test.
	* testsuite/libgomp.c/icv-2.c: New test.
	* testsuite/libgomp.c/lib-2.c: New test.
	* testsuite/libgomp.c/lock-1.c: New test.
	* testsuite/libgomp.c/lock-2.c: New test.
	* testsuite/libgomp.c/lock-3.c: New test.
	* testsuite/libgomp.c/loop-4.c: New test.
	* testsuite/libgomp.c/loop-5.c: New test.
	* testsuite/libgomp.c/loop-6.c: New test.
	* testsuite/libgomp.c/loop-7.c: New test.
	* testsuite/libgomp.c/loop-8.c: New test.
	* testsuite/libgomp.c/loop-9.c: New test.
	* testsuite/libgomp.c/nested-3.c: New test.
	* testsuite/libgomp.c/nestedfn-6.c: New test.
	* testsuite/libgomp.c/sort-1.c: New test.
	* testsuite/libgomp.c/task-1.c: New test.
	* testsuite/libgomp.c/task-2.c: New test.
	* testsuite/libgomp.c/task-3.c: New test.
	* testsuite/libgomp.c/task-4.c: New test.
	* testsuite/libgomp.c++/c++.exp: Add libstdc++-v3 build includes
	to C++ testsuite default compiler options.
	* testsuite/libgomp.c++/collapse-1.C: New test.
	* testsuite/libgomp.c++/collapse-2.C: New test.
	* testsuite/libgomp.c++/ctor-10.C: New test.
	* testsuite/libgomp.c++/for-1.C: New test.
	* testsuite/libgomp.c++/for-2.C: New test.
	* testsuite/libgomp.c++/for-3.C: New test.
	* testsuite/libgomp.c++/for-4.C: New test.
	* testsuite/libgomp.c++/for-5.C: New test.
	* testsuite/libgomp.c++/loop-8.C: New test.
	* testsuite/libgomp.c++/loop-9.C: New test.
	* testsuite/libgomp.c++/loop-10.C: New test.
	* testsuite/libgomp.c++/task-1.C: New test.
	* testsuite/libgomp.c++/task-2.C: New test.
	* testsuite/libgomp.c++/task-3.C: New test.
	* testsuite/libgomp.c++/task-4.C: New test.
	* testsuite/libgomp.c++/task-5.C: New test.
	* testsuite/libgomp.c++/task-6.C: New test.
	* testsuite/libgomp.fortran/allocatable1.f90: New test.
	* testsuite/libgomp.fortran/allocatable2.f90: New test.
	* testsuite/libgomp.fortran/allocatable3.f90: New test.
	* testsuite/libgomp.fortran/allocatable4.f90: New test.
	* testsuite/libgomp.fortran/collapse1.f90: New test.
	* testsuite/libgomp.fortran/collapse2.f90: New test.
	* testsuite/libgomp.fortran/collapse3.f90: New test.
	* testsuite/libgomp.fortran/collapse4.f90: New test.
	* testsuite/libgomp.fortran/lastprivate1.f90: New test.
	* testsuite/libgomp.fortran/lastprivate2.f90: New test.
	* testsuite/libgomp.fortran/lib4.f90: New test.
	* testsuite/libgomp.fortran/lock-1.f90: New test.
	* testsuite/libgomp.fortran/lock-2.f90: New test.
	* testsuite/libgomp.fortran/nested1.f90: New test.
	* testsuite/libgomp.fortran/nestedfn4.f90: New test.
	* testsuite/libgomp.fortran/strassen.f90: New test.
	* testsuite/libgomp.fortran/tabs1.f90: New test.
	* testsuite/libgomp.fortran/tabs2.f: New test.
	* testsuite/libgomp.fortran/task1.f90: New test.
	* testsuite/libgomp.fortran/task2.f90: New test.
	* testsuite/libgomp.fortran/vla4.f90: Add dg-warning.
	* testsuite/libgomp.fortran/vla5.f90: Likewise.
	* testsuite/libgomp.c/pr26943-2.c: Likewise.
	* testsuite/libgomp.c/pr26943-3.c: Likewise.
	* testsuite/libgomp.c/pr26943-4.c: Likewise.

Co-Authored-By: Jakob Blomer <jakob.blomer@ira.uka.de>
Co-Authored-By: Richard Henderson <rth@redhat.com>
Co-Authored-By: Ulrich Drepper <drepper@redhat.com>

From-SVN: r136433

1 files changed, 431 insertions, 104 deletions

diff --git a/gcc/fortran/trans-openmp.c b/gcc/fortran/trans-openmp.c
index c6c4bae..6f99800 100644
--- a/gcc/fortran/trans-openmp.c
+++ b/gcc/fortran/trans-openmp.c
@@ -84,6 +84,17 @@ gfc_omp_predetermined_sharing (tree decl)
   if (GFC_DECL_CRAY_POINTEE (decl))
     return OMP_CLAUSE_DEFAULT_PRIVATE;
 
+  /* Assumed-size arrays are predetermined to inherit sharing
+     attributes of the associated actual argument, which is shared
+     for all we care.  */
+  if (TREE_CODE (decl) == PARM_DECL
+      && GFC_ARRAY_TYPE_P (TREE_TYPE (decl))
+      && GFC_TYPE_ARRAY_AKIND (TREE_TYPE (decl)) == GFC_ARRAY_UNKNOWN
+      && GFC_TYPE_ARRAY_UBOUND (TREE_TYPE (decl),
+				GFC_TYPE_ARRAY_RANK (TREE_TYPE (decl)) - 1)
+	 == NULL)
+    return OMP_CLAUSE_DEFAULT_SHARED;
+
   /* COMMON and EQUIVALENCE decls are shared.  They
      are only referenced through DECL_VALUE_EXPR of the variables
      contained in them.  If those are privatized, they will not be
@@ -98,27 +109,179 @@ gfc_omp_predetermined_sharing (tree decl)
 }
 
 
+/* Return true if DECL in private clause needs
+   OMP_CLAUSE_PRIVATE_OUTER_REF on the private clause.  */
+bool
+gfc_omp_private_outer_ref (tree decl)
+{
+  tree type = TREE_TYPE (decl);
+
+  if (GFC_DESCRIPTOR_TYPE_P (type)
+      && GFC_TYPE_ARRAY_AKIND (type) == GFC_ARRAY_ALLOCATABLE)
+    return true;
+
+  return false;
+}
+
 /* Return code to initialize DECL with its default constructor, or
    NULL if there's nothing to do.  */
 
 tree
-gfc_omp_clause_default_ctor (tree clause ATTRIBUTE_UNUSED, tree decl)
+gfc_omp_clause_default_ctor (tree clause, tree decl, tree outer)
 {
-  tree type = TREE_TYPE (decl);
-  stmtblock_t block;
+  tree type = TREE_TYPE (decl), rank, size, esize, ptr, cond, then_b, else_b;
+  stmtblock_t block, cond_block;
 
-  if (! GFC_DESCRIPTOR_TYPE_P (type))
+  if (! GFC_DESCRIPTOR_TYPE_P (type)
+      || GFC_TYPE_ARRAY_AKIND (type) != GFC_ARRAY_ALLOCATABLE)
     return NULL;
 
+  gcc_assert (outer != NULL);
+  gcc_assert (OMP_CLAUSE_CODE (clause) == OMP_CLAUSE_PRIVATE
+	      || OMP_CLAUSE_CODE (clause) == OMP_CLAUSE_LASTPRIVATE);
+
   /* Allocatable arrays in PRIVATE clauses need to be set to
-     "not currently allocated" allocation status.  */
-  gfc_init_block (&block);
+     "not currently allocated" allocation status if outer
+     array is "not currently allocated", otherwise should be allocated.  */
+  gfc_start_block (&block);
+
+  gfc_init_block (&cond_block);
+
+  gfc_add_modify_expr (&cond_block, decl, outer);
+  rank = gfc_rank_cst[GFC_TYPE_ARRAY_RANK (type) - 1];
+  size = gfc_conv_descriptor_ubound (decl, rank);
+  size = fold_build2 (MINUS_EXPR, gfc_array_index_type, size,
+		      gfc_conv_descriptor_lbound (decl, rank));
+  size = fold_build2 (PLUS_EXPR, gfc_array_index_type, size,
+		      gfc_index_one_node);
+  if (GFC_TYPE_ARRAY_RANK (type) > 1)
+    size = fold_build2 (MULT_EXPR, gfc_array_index_type, size,
+			gfc_conv_descriptor_stride (decl, rank));
+  esize = fold_convert (gfc_array_index_type,
+			TYPE_SIZE_UNIT (gfc_get_element_type (type)));
+  size = fold_build2 (MULT_EXPR, gfc_array_index_type, size, esize);
+  size = gfc_evaluate_now (fold_convert (size_type_node, size), &cond_block);
+  ptr = gfc_allocate_array_with_status (&cond_block,
+					build_int_cst (pvoid_type_node, 0),
+					size, NULL);
+  gfc_conv_descriptor_data_set_tuples (&cond_block, decl, ptr);
+  then_b = gfc_finish_block (&cond_block);
+
+  gfc_init_block (&cond_block);
+  gfc_conv_descriptor_data_set_tuples (&cond_block, decl, null_pointer_node);
+  else_b = gfc_finish_block (&cond_block);
+
+  cond = fold_build2 (NE_EXPR, boolean_type_node,
+		      fold_convert (pvoid_type_node,
+				    gfc_conv_descriptor_data_get (outer)),
+		      null_pointer_node);
+  gfc_add_expr_to_block (&block, build3 (COND_EXPR, void_type_node,
+			 cond, then_b, else_b));
 
-  gfc_conv_descriptor_data_set_tuples (&block, decl, null_pointer_node);
+  return gfc_finish_block (&block);
+}
+
+/* Build and return code for a copy constructor from SRC to DEST.  */
+
+tree
+gfc_omp_clause_copy_ctor (tree clause, tree dest, tree src)
+{
+  tree type = TREE_TYPE (dest), ptr, size, esize, rank, call;
+  stmtblock_t block;
+
+  if (! GFC_DESCRIPTOR_TYPE_P (type)
+      || GFC_TYPE_ARRAY_AKIND (type) != GFC_ARRAY_ALLOCATABLE)
+    return build_gimple_modify_stmt (dest, src);
+
+  gcc_assert (OMP_CLAUSE_CODE (clause) == OMP_CLAUSE_FIRSTPRIVATE);
+
+  /* Allocatable arrays in FIRSTPRIVATE clauses need to be allocated
+     and copied from SRC.  */
+  gfc_start_block (&block);
+
+  gfc_add_modify_expr (&block, dest, src);
+  rank = gfc_rank_cst[GFC_TYPE_ARRAY_RANK (type) - 1];
+  size = gfc_conv_descriptor_ubound (dest, rank);
+  size = fold_build2 (MINUS_EXPR, gfc_array_index_type, size,
+		      gfc_conv_descriptor_lbound (dest, rank));
+  size = fold_build2 (PLUS_EXPR, gfc_array_index_type, size,
+		      gfc_index_one_node);
+  if (GFC_TYPE_ARRAY_RANK (type) > 1)
+    size = fold_build2 (MULT_EXPR, gfc_array_index_type, size,
+			gfc_conv_descriptor_stride (dest, rank));
+  esize = fold_convert (gfc_array_index_type,
+			TYPE_SIZE_UNIT (gfc_get_element_type (type)));
+  size = fold_build2 (MULT_EXPR, gfc_array_index_type, size, esize);
+  size = gfc_evaluate_now (fold_convert (size_type_node, size), &block);
+  ptr = gfc_allocate_array_with_status (&block,
+					build_int_cst (pvoid_type_node, 0),
+					size, NULL);
+  gfc_conv_descriptor_data_set_tuples (&block, dest, ptr);
+  call = build_call_expr (built_in_decls[BUILT_IN_MEMCPY], 3, ptr,
+			  fold_convert (pvoid_type_node,
+					gfc_conv_descriptor_data_get (src)),
+			  size);
+  gfc_add_expr_to_block (&block, fold_convert (void_type_node, call));
 
   return gfc_finish_block (&block);
 }
 
+/* Similarly, except use an assignment operator instead.  */
+
+tree
+gfc_omp_clause_assign_op (tree clause ATTRIBUTE_UNUSED, tree dest, tree src)
+{
+  tree type = TREE_TYPE (dest), rank, size, esize, call;
+  stmtblock_t block;
+
+  if (! GFC_DESCRIPTOR_TYPE_P (type)
+      || GFC_TYPE_ARRAY_AKIND (type) != GFC_ARRAY_ALLOCATABLE)
+    return build_gimple_modify_stmt (dest, src);
+
+  /* Handle copying allocatable arrays.  */
+  gfc_start_block (&block);
+
+  rank = gfc_rank_cst[GFC_TYPE_ARRAY_RANK (type) - 1];
+  size = gfc_conv_descriptor_ubound (dest, rank);
+  size = fold_build2 (MINUS_EXPR, gfc_array_index_type, size,
+		      gfc_conv_descriptor_lbound (dest, rank));
+  size = fold_build2 (PLUS_EXPR, gfc_array_index_type, size,
+		      gfc_index_one_node);
+  if (GFC_TYPE_ARRAY_RANK (type) > 1)
+    size = fold_build2 (MULT_EXPR, gfc_array_index_type, size,
+			gfc_conv_descriptor_stride (dest, rank));
+  esize = fold_convert (gfc_array_index_type,
+			TYPE_SIZE_UNIT (gfc_get_element_type (type)));
+  size = fold_build2 (MULT_EXPR, gfc_array_index_type, size, esize);
+  size = gfc_evaluate_now (fold_convert (size_type_node, size), &block);
+  call = build_call_expr (built_in_decls[BUILT_IN_MEMCPY], 3,
+			  fold_convert (pvoid_type_node,
+					gfc_conv_descriptor_data_get (dest)),
+			  fold_convert (pvoid_type_node,
+					gfc_conv_descriptor_data_get (src)),
+			  size);
+  gfc_add_expr_to_block (&block, fold_convert (void_type_node, call));
+
+  return gfc_finish_block (&block);
+}
+
+/* Build and return code destructing DECL.  Return NULL if nothing
+   to be done.  */
+
+tree
+gfc_omp_clause_dtor (tree clause ATTRIBUTE_UNUSED, tree decl)
+{
+  tree type = TREE_TYPE (decl);
+
+  if (! GFC_DESCRIPTOR_TYPE_P (type)
+      || GFC_TYPE_ARRAY_AKIND (type) != GFC_ARRAY_ALLOCATABLE)
+    return NULL;
+
+  /* Allocatable arrays in FIRSTPRIVATE/LASTPRIVATE etc. clauses need
+     to be deallocated if they were allocated.  */
+  return gfc_trans_dealloc_allocated (decl);
+}
+
 
 /* Return true if DECL's DECL_VALUE_EXPR (if any) should be
    disregarded in OpenMP construct, because it is going to be
@@ -429,7 +592,39 @@ gfc_trans_omp_array_reduction (tree c, gfc_symbol *sym, locus where)
 
   /* Create the init statement list.  */
   pushlevel (0);
-  stmt = gfc_trans_assignment (e1, e2, false);
+  if (GFC_DESCRIPTOR_TYPE_P (TREE_TYPE (decl))
+      && GFC_TYPE_ARRAY_AKIND (TREE_TYPE (decl)) == GFC_ARRAY_ALLOCATABLE)
+    {
+      /* If decl is an allocatable array, it needs to be allocated
+	 with the same bounds as the outer var.  */
+      tree type = TREE_TYPE (decl), rank, size, esize, ptr;
+      stmtblock_t block;
+
+      gfc_start_block (&block);
+
+      gfc_add_modify_expr (&block, decl, outer_sym.backend_decl);
+      rank = gfc_rank_cst[GFC_TYPE_ARRAY_RANK (type) - 1];
+      size = gfc_conv_descriptor_ubound (decl, rank);
+      size = fold_build2 (MINUS_EXPR, gfc_array_index_type, size,
+			  gfc_conv_descriptor_lbound (decl, rank));
+      size = fold_build2 (PLUS_EXPR, gfc_array_index_type, size,
+			  gfc_index_one_node);
+      if (GFC_TYPE_ARRAY_RANK (type) > 1)
+	size = fold_build2 (MULT_EXPR, gfc_array_index_type, size,
+			    gfc_conv_descriptor_stride (decl, rank));
+      esize = fold_convert (gfc_array_index_type,
+			    TYPE_SIZE_UNIT (gfc_get_element_type (type)));
+      size = fold_build2 (MULT_EXPR, gfc_array_index_type, size, esize);
+      size = gfc_evaluate_now (fold_convert (size_type_node, size), &block);
+      ptr = gfc_allocate_array_with_status (&block,
+					    build_int_cst (pvoid_type_node, 0),
+					    size, NULL);
+      gfc_conv_descriptor_data_set_tuples (&block, decl, ptr);
+      gfc_add_expr_to_block (&block, gfc_trans_assignment (e1, e2, false));
+      stmt = gfc_finish_block (&block);
+    }
+  else
+    stmt = gfc_trans_assignment (e1, e2, false);
   if (TREE_CODE (stmt) != BIND_EXPR)
     stmt = build3_v (BIND_EXPR, NULL, stmt, poplevel (1, 0, 0));
   else
@@ -438,7 +633,20 @@ gfc_trans_omp_array_reduction (tree c, gfc_symbol *sym, locus where)
 
   /* Create the merge statement list.  */
   pushlevel (0);
-  stmt = gfc_trans_assignment (e3, e4, false);
+  if (GFC_DESCRIPTOR_TYPE_P (TREE_TYPE (decl))
+      && GFC_TYPE_ARRAY_AKIND (TREE_TYPE (decl)) == GFC_ARRAY_ALLOCATABLE)
+    {
+      /* If decl is an allocatable array, it needs to be deallocated
+	 afterwards.  */
+      stmtblock_t block;
+
+      gfc_start_block (&block);
+      gfc_add_expr_to_block (&block, gfc_trans_assignment (e3, e4, false));
+      gfc_add_expr_to_block (&block, gfc_trans_dealloc_allocated (decl));
+      stmt = gfc_finish_block (&block);
+    }
+  else
+    stmt = gfc_trans_assignment (e3, e4, false);
   if (TREE_CODE (stmt) != BIND_EXPR)
     stmt = build3_v (BIND_EXPR, NULL, stmt, poplevel (1, 0, 0));
   else
@@ -639,6 +847,9 @@ gfc_trans_omp_clauses (stmtblock_t *block, gfc_omp_clauses *clauses,
 	case OMP_SCHED_RUNTIME:
 	  OMP_CLAUSE_SCHEDULE_KIND (c) = OMP_CLAUSE_SCHEDULE_RUNTIME;
 	  break;
+	case OMP_SCHED_AUTO:
+	  OMP_CLAUSE_SCHEDULE_KIND (c) = OMP_CLAUSE_SCHEDULE_AUTO;
+	  break;
 	default:
 	  gcc_unreachable ();
 	}
@@ -659,6 +870,9 @@ gfc_trans_omp_clauses (stmtblock_t *block, gfc_omp_clauses *clauses,
 	case OMP_DEFAULT_PRIVATE:
 	  OMP_CLAUSE_DEFAULT_KIND (c) = OMP_CLAUSE_DEFAULT_PRIVATE;
 	  break;
+	case OMP_DEFAULT_FIRSTPRIVATE:
+	  OMP_CLAUSE_DEFAULT_KIND (c) = OMP_CLAUSE_DEFAULT_FIRSTPRIVATE;
+	  break;
 	default:
 	  gcc_unreachable ();
 	}
@@ -677,6 +891,19 @@ gfc_trans_omp_clauses (stmtblock_t *block, gfc_omp_clauses *clauses,
       omp_clauses = gfc_trans_add_clause (c, omp_clauses);
     }
 
+  if (clauses->untied)
+    {
+      c = build_omp_clause (OMP_CLAUSE_UNTIED);
+      omp_clauses = gfc_trans_add_clause (c, omp_clauses);
+    }
+
+  if (clauses->collapse)
+    {
+      c = build_omp_clause (OMP_CLAUSE_COLLAPSE);
+      OMP_CLAUSE_COLLAPSE_EXPR (c) = build_int_cst (NULL, clauses->collapse);
+      omp_clauses = gfc_trans_add_clause (c, omp_clauses);
+    }
+
   return omp_clauses;
 }
 
@@ -893,20 +1120,28 @@ gfc_trans_omp_critical (gfc_code *code)
 
 static tree
 gfc_trans_omp_do (gfc_code *code, stmtblock_t *pblock,
-		  gfc_omp_clauses *do_clauses)
+		  gfc_omp_clauses *do_clauses, tree par_clauses)
 {
   gfc_se se;
   tree dovar, stmt, from, to, step, type, init, cond, incr;
   tree count = NULL_TREE, cycle_label, tmp, omp_clauses;
   stmtblock_t block;
   stmtblock_t body;
-  int simple = 0;
-  bool dovar_found = false;
   gfc_omp_clauses *clauses = code->ext.omp_clauses;
+  gfc_code *outermost;
+  int i, collapse = clauses->collapse;
+  tree dovar_init = NULL_TREE;
 
-  code = code->block->next;
+  if (collapse <= 0)
+    collapse = 1;
+
+  outermost = code = code->block->next;
   gcc_assert (code->op == EXEC_DO);
 
+  init = make_tree_vec (collapse);
+  cond = make_tree_vec (collapse);
+  incr = make_tree_vec (collapse);
+
   if (pblock == NULL)
     {
       gfc_start_block (&block);
@@ -914,107 +1149,168 @@ gfc_trans_omp_do (gfc_code *code, stmtblock_t *pblock,
     }
 
   omp_clauses = gfc_trans_omp_clauses (pblock, do_clauses, code->loc);
-  if (clauses)
-    {
-      gfc_namelist *n;
-      for (n = clauses->lists[OMP_LIST_LASTPRIVATE]; n != NULL; n = n->next)
-	if (code->ext.iterator->var->symtree->n.sym == n->sym)
-	  break;
-      if (n == NULL)
-	for (n = clauses->lists[OMP_LIST_PRIVATE]; n != NULL; n = n->next)
-	  if (code->ext.iterator->var->symtree->n.sym == n->sym)
-	    break;
-      if (n != NULL)
-	dovar_found = true;
-    }
 
-  /* Evaluate all the expressions in the iterator.  */
-  gfc_init_se (&se, NULL);
-  gfc_conv_expr_lhs (&se, code->ext.iterator->var);
-  gfc_add_block_to_block (pblock, &se.pre);
-  dovar = se.expr;
-  type = TREE_TYPE (dovar);
-  gcc_assert (TREE_CODE (type) == INTEGER_TYPE);
-
-  gfc_init_se (&se, NULL);
-  gfc_conv_expr_val (&se, code->ext.iterator->start);
-  gfc_add_block_to_block (pblock, &se.pre);
-  from = gfc_evaluate_now (se.expr, pblock);
-
-  gfc_init_se (&se, NULL);
-  gfc_conv_expr_val (&se, code->ext.iterator->end);
-  gfc_add_block_to_block (pblock, &se.pre);
-  to = gfc_evaluate_now (se.expr, pblock);
-
-  gfc_init_se (&se, NULL);
-  gfc_conv_expr_val (&se, code->ext.iterator->step);
-  gfc_add_block_to_block (pblock, &se.pre);
-  step = gfc_evaluate_now (se.expr, pblock);
-
-  /* Special case simple loops.  */
-  if (integer_onep (step))
-    simple = 1;
-  else if (tree_int_cst_equal (step, integer_minus_one_node))
-    simple = -1;
-
-  /* Loop body.  */
-  if (simple)
+  for (i = 0; i < collapse; i++)
     {
-      init = build2_v (GIMPLE_MODIFY_STMT, dovar, from);
-      cond = fold_build2 (simple > 0 ? LE_EXPR : GE_EXPR, boolean_type_node,
-			  dovar, to);
-      incr = fold_build2 (PLUS_EXPR, type, dovar, step);
-      incr = fold_build2 (GIMPLE_MODIFY_STMT, type, dovar, incr);
-      if (pblock != &block)
+      int simple = 0;
+      int dovar_found = 0;
+
+      if (clauses)
 	{
-	  pushlevel (0);
-	  gfc_start_block (&block);
+	  gfc_namelist *n;
+	  for (n = clauses->lists[OMP_LIST_LASTPRIVATE]; n != NULL;
+	       n = n->next)
+	    if (code->ext.iterator->var->symtree->n.sym == n->sym)
+	      break;
+	  if (n != NULL)
+	    dovar_found = 1;
+	  else if (n == NULL)
+	    for (n = clauses->lists[OMP_LIST_PRIVATE]; n != NULL; n = n->next)
+	      if (code->ext.iterator->var->symtree->n.sym == n->sym)
+		break;
+	  if (n != NULL)
+	    dovar_found++;
 	}
-      gfc_start_block (&body);
-    }
-  else
-    {
-      /* STEP is not 1 or -1.  Use:
-	 for (count = 0; count < (to + step - from) / step; count++)
-	   {
-	     dovar = from + count * step;
-	     body;
-	   cycle_label:;
-	   }  */
-      tmp = fold_build2 (MINUS_EXPR, type, step, from);
-      tmp = fold_build2 (PLUS_EXPR, type, to, tmp);
-      tmp = fold_build2 (TRUNC_DIV_EXPR, type, tmp, step);
-      tmp = gfc_evaluate_now (tmp, pblock);
-      count = gfc_create_var (type, "count");
-      init = build2_v (GIMPLE_MODIFY_STMT, count, build_int_cst (type, 0));
-      cond = fold_build2 (LT_EXPR, boolean_type_node, count, tmp);
-      incr = fold_build2 (PLUS_EXPR, type, count, build_int_cst (type, 1));
-      incr = fold_build2 (GIMPLE_MODIFY_STMT, type, count, incr);
-
-      if (pblock != &block)
+
+      /* Evaluate all the expressions in the iterator.  */
+      gfc_init_se (&se, NULL);
+      gfc_conv_expr_lhs (&se, code->ext.iterator->var);
+      gfc_add_block_to_block (pblock, &se.pre);
+      dovar = se.expr;
+      type = TREE_TYPE (dovar);
+      gcc_assert (TREE_CODE (type) == INTEGER_TYPE);
+
+      gfc_init_se (&se, NULL);
+      gfc_conv_expr_val (&se, code->ext.iterator->start);
+      gfc_add_block_to_block (pblock, &se.pre);
+      from = gfc_evaluate_now (se.expr, pblock);
+
+      gfc_init_se (&se, NULL);
+      gfc_conv_expr_val (&se, code->ext.iterator->end);
+      gfc_add_block_to_block (pblock, &se.pre);
+      to = gfc_evaluate_now (se.expr, pblock);
+
+      gfc_init_se (&se, NULL);
+      gfc_conv_expr_val (&se, code->ext.iterator->step);
+      gfc_add_block_to_block (pblock, &se.pre);
+      step = gfc_evaluate_now (se.expr, pblock);
+
+      /* Special case simple loops.  */
+      if (integer_onep (step))
+	simple = 1;
+      else if (tree_int_cst_equal (step, integer_minus_one_node))
+	simple = -1;
+
+      /* Loop body.  */
+      if (simple)
 	{
-	  pushlevel (0);
-	  gfc_start_block (&block);
+	  TREE_VEC_ELT (init, i) = build2_v (GIMPLE_MODIFY_STMT, dovar, from);
+	  TREE_VEC_ELT (cond, i) = fold_build2 (simple > 0 ? LE_EXPR : GE_EXPR,
+						boolean_type_node, dovar, to);
+	  TREE_VEC_ELT (incr, i) = fold_build2 (PLUS_EXPR, type, dovar, step);
+	  TREE_VEC_ELT (incr, i) = fold_build2 (GIMPLE_MODIFY_STMT, type, dovar,
+						TREE_VEC_ELT (incr, i));
+	}
+      else
+	{
+	  /* STEP is not 1 or -1.  Use:
+	     for (count = 0; count < (to + step - from) / step; count++)
+	       {
+		 dovar = from + count * step;
+		 body;
+	       cycle_label:;
+	       }  */
+	  tmp = fold_build2 (MINUS_EXPR, type, step, from);
+	  tmp = fold_build2 (PLUS_EXPR, type, to, tmp);
+	  tmp = fold_build2 (TRUNC_DIV_EXPR, type, tmp, step);
+	  tmp = gfc_evaluate_now (tmp, pblock);
+	  count = gfc_create_var (type, "count");
+	  TREE_VEC_ELT (init, i) = build2_v (GIMPLE_MODIFY_STMT, count,
+					     build_int_cst (type, 0));
+	  TREE_VEC_ELT (cond, i) = fold_build2 (LT_EXPR, boolean_type_node,
+						count, tmp);
+	  TREE_VEC_ELT (incr, i) = fold_build2 (PLUS_EXPR, type, count,
+						build_int_cst (type, 1));
+	  TREE_VEC_ELT (incr, i) = fold_build2 (GIMPLE_MODIFY_STMT, type,
+						count, TREE_VEC_ELT (incr, i));
+
+	  /* Initialize DOVAR.  */
+	  tmp = fold_build2 (MULT_EXPR, type, count, step);
+	  tmp = fold_build2 (PLUS_EXPR, type, from, tmp);
+	  dovar_init = tree_cons (dovar, tmp, dovar_init);
 	}
-      gfc_start_block (&body);
 
-      /* Initialize DOVAR.  */
-      tmp = fold_build2 (MULT_EXPR, type, count, step);
-      tmp = fold_build2 (PLUS_EXPR, type, from, tmp);
-      gfc_add_modify_stmt (&body, dovar, tmp);
+      if (!dovar_found)
+	{
+	  tmp = build_omp_clause (OMP_CLAUSE_PRIVATE);
+	  OMP_CLAUSE_DECL (tmp) = dovar;
+	  omp_clauses = gfc_trans_add_clause (tmp, omp_clauses);
+	}
+      else if (dovar_found == 2)
+	{
+	  tree c = NULL;
+
+	  tmp = NULL;
+	  if (!simple)
+	    {
+	      /* If dovar is lastprivate, but different counter is used,
+		 dovar += step needs to be added to
+		 OMP_CLAUSE_LASTPRIVATE_STMT, otherwise the copied dovar
+		 will have the value on entry of the last loop, rather
+		 than value after iterator increment.  */
+	      tmp = gfc_evaluate_now (step, pblock);
+	      tmp = fold_build2 (PLUS_EXPR, type, dovar, tmp);
+	      tmp = fold_build2 (GIMPLE_MODIFY_STMT, type, dovar, tmp);
+	      for (c = omp_clauses; c ; c = OMP_CLAUSE_CHAIN (c))
+		if (OMP_CLAUSE_CODE (c) == OMP_CLAUSE_LASTPRIVATE
+		    && OMP_CLAUSE_DECL (c) == dovar)
+		  {
+		    OMP_CLAUSE_LASTPRIVATE_STMT (c) = tmp;
+		    break;
+		  }
+	    }
+	  if (c == NULL && par_clauses != NULL)
+	    {
+	      for (c = par_clauses; c ; c = OMP_CLAUSE_CHAIN (c))
+		if (OMP_CLAUSE_CODE (c) == OMP_CLAUSE_LASTPRIVATE
+		    && OMP_CLAUSE_DECL (c) == dovar)
+		  {
+		    tree l = build_omp_clause (OMP_CLAUSE_LASTPRIVATE);
+		    OMP_CLAUSE_DECL (l) = dovar;
+		    OMP_CLAUSE_CHAIN (l) = omp_clauses;
+		    OMP_CLAUSE_LASTPRIVATE_STMT (l) = tmp;
+		    omp_clauses = l;
+		    OMP_CLAUSE_SET_CODE (c, OMP_CLAUSE_SHARED);
+		    break;
+		  }
+	    }
+	  gcc_assert (simple || c != NULL);
+	}
+      if (!simple)
+	{
+	  tmp = build_omp_clause (OMP_CLAUSE_PRIVATE);
+	  OMP_CLAUSE_DECL (tmp) = count;
+	  omp_clauses = gfc_trans_add_clause (tmp, omp_clauses);
+	}
+
+      if (i + 1 < collapse)
+	code = code->block->next;
     }
 
-  if (!dovar_found)
+  if (pblock != &block)
     {
-      tmp = build_omp_clause (OMP_CLAUSE_PRIVATE);
-      OMP_CLAUSE_DECL (tmp) = dovar;
-      omp_clauses = gfc_trans_add_clause (tmp, omp_clauses);
+      pushlevel (0);
+      gfc_start_block (&block);
     }
-  if (!simple)
+
+  gfc_start_block (&body);
+
+  dovar_init = nreverse (dovar_init);
+  while (dovar_init)
     {
-      tmp = build_omp_clause (OMP_CLAUSE_PRIVATE);
-      OMP_CLAUSE_DECL (tmp) = count;
-      omp_clauses = gfc_trans_add_clause (tmp, omp_clauses);
+      gfc_add_modify_stmt (&body, TREE_PURPOSE (dovar_init),
+			   TREE_VALUE (dovar_init));
+      dovar_init = TREE_CHAIN (dovar_init);
     }
 
   /* Cycle statement is implemented with a goto.  Exit statement must not be
@@ -1107,9 +1403,11 @@ gfc_trans_omp_parallel_do (gfc_code *code)
       do_clauses.sched_kind = parallel_clauses.sched_kind;
       do_clauses.chunk_size = parallel_clauses.chunk_size;
       do_clauses.ordered = parallel_clauses.ordered;
+      do_clauses.collapse = parallel_clauses.collapse;
       parallel_clauses.sched_kind = OMP_SCHED_NONE;
       parallel_clauses.chunk_size = NULL;
       parallel_clauses.ordered = false;
+      parallel_clauses.collapse = 0;
       omp_clauses = gfc_trans_omp_clauses (&block, &parallel_clauses,
 					   code->loc);
     }
@@ -1118,7 +1416,7 @@ gfc_trans_omp_parallel_do (gfc_code *code)
     pblock = &block;
   else
     pushlevel (0);
-  stmt = gfc_trans_omp_do (code, pblock, &do_clauses);
+  stmt = gfc_trans_omp_do (code, pblock, &do_clauses, omp_clauses);
   if (TREE_CODE (stmt) != BIND_EXPR)
     stmt = build3_v (BIND_EXPR, NULL, stmt, poplevel (1, 0, 0));
   else
@@ -1221,6 +1519,31 @@ gfc_trans_omp_single (gfc_code *code, gfc_omp_clauses *clauses)
 }
 
 static tree
+gfc_trans_omp_task (gfc_code *code)
+{
+  stmtblock_t block;
+  tree stmt, body_stmt, omp_clauses;
+
+  gfc_start_block (&block);
+  omp_clauses = gfc_trans_omp_clauses (&block, code->ext.omp_clauses,
+				       code->loc);
+  body_stmt = gfc_trans_omp_code (code->block->next, true);
+  stmt = make_node (OMP_TASK);
+  TREE_TYPE (stmt) = void_type_node;
+  OMP_TASK_CLAUSES (stmt) = omp_clauses;
+  OMP_TASK_BODY (stmt) = body_stmt;
+  gfc_add_expr_to_block (&block, stmt);
+  return gfc_finish_block (&block);
+}
+
+static tree
+gfc_trans_omp_taskwait (void)
+{
+  tree decl = built_in_decls [BUILT_IN_GOMP_TASKWAIT];
+  return build_call_expr (decl, 0);
+}
+
+static tree
 gfc_trans_omp_workshare (gfc_code *code, gfc_omp_clauses *clauses)
 {
   /* XXX */
@@ -1239,7 +1562,7 @@ gfc_trans_omp_directive (gfc_code *code)
     case EXEC_OMP_CRITICAL:
       return gfc_trans_omp_critical (code);
     case EXEC_OMP_DO:
-      return gfc_trans_omp_do (code, NULL, code->ext.omp_clauses);
+      return gfc_trans_omp_do (code, NULL, code->ext.omp_clauses, NULL);
     case EXEC_OMP_FLUSH:
       return gfc_trans_omp_flush ();
     case EXEC_OMP_MASTER:
@@ -1258,6 +1581,10 @@ gfc_trans_omp_directive (gfc_code *code)
       return gfc_trans_omp_sections (code, code->ext.omp_clauses);
     case EXEC_OMP_SINGLE:
       return gfc_trans_omp_single (code, code->ext.omp_clauses);
+    case EXEC_OMP_TASK:
+      return gfc_trans_omp_task (code);
+    case EXEC_OMP_TASKWAIT:
+      return gfc_trans_omp_taskwait ();
     case EXEC_OMP_WORKSHARE:
       return gfc_trans_omp_workshare (code, code->ext.omp_clauses);
     default: