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

25 files changed, 1901 insertions, 6 deletions

diff --git a/libgomp/testsuite/libgomp.c/collapse-1.c b/libgomp/testsuite/libgomp.c/collapse-1.c
new file mode 100644
index 0000000..82becfa
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/collapse-1.c
@@ -0,0 +1,30 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+
+int
+main (void)
+{
+  int i, j, k, l = 0;
+  int a[3][3][3];
+
+  memset (a, '\0', sizeof (a));
+  #pragma omp parallel for collapse(4 - 1) schedule(static, 4)
+    for (i = 0; i < 2; i++)
+      for (j = 0; j < 2; j++)
+	for (k = 0; k < 2; k++)
+	  a[i][j][k] = i + j * 4 + k * 16;
+  #pragma omp parallel
+    {
+      #pragma omp for collapse(2) reduction(|:l)
+	for (i = 0; i < 2; i++)
+	  for (j = 0; j < 2; j++)
+	    for (k = 0; k < 2; k++)
+	      if (a[i][j][k] != i + j * 4 + k * 16)
+		l = 1;
+    }
+  if (l)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/collapse-2.c b/libgomp/testsuite/libgomp.c/collapse-2.c
new file mode 100644
index 0000000..b5c77d4
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/collapse-2.c
@@ -0,0 +1,30 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <omp.h>
+
+int
+main (void)
+{
+  int i, j, k, l = 0, f = 0;
+  int m1 = 4, m2 = -5, m3 = 17;
+
+  #pragma omp parallel for num_threads (8) collapse(3) \
+		       schedule(static, 9) reduction(+:l) \
+		       firstprivate(f)
+    for (i = -2; i < m1; i++)
+      for (j = m2; j < -2; j++)
+	{
+	  for (k = 13; k < m3; k++)
+	    {
+	      if (omp_get_num_threads () == 8
+		  && ((i + 2) * 12 + (j + 5) * 4 + (k - 13)
+		      != (omp_get_thread_num () * 9
+			  + f++)))
+		l++;
+	    }
+	}
+  if (l)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/collapse-3.c b/libgomp/testsuite/libgomp.c/collapse-3.c
new file mode 100644
index 0000000..4674f83
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/collapse-3.c
@@ -0,0 +1,31 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -std=gnu99" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+int
+main (void)
+{
+  int i2, l = 0;
+  int a[3][3][3];
+
+  memset (a, '\0', sizeof (a));
+  #pragma omp parallel for collapse(4 - 1) schedule(static, 4)
+    for (int i = 0; i < 2; i++)
+      for (int j = 0; j < 2; j++)
+	for (int k = 0; k < 2; k++)
+	  a[i][j][k] = i + j * 4 + k * 16;
+  #pragma omp parallel
+    {
+      #pragma omp for collapse(2) reduction(|:l)
+	for (i2 = 0; i2 < 2; i2++)
+	  for (int j = 0; j < 2; j++)
+	    for (int k = 0; k < 2; k++)
+	      if (a[i2][j][k] != i2 + j * 4 + k * 16)
+		l = 1;
+    }
+  if (l)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/icv-1.c b/libgomp/testsuite/libgomp.c/icv-1.c
new file mode 100644
index 0000000..99708f8
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/icv-1.c
@@ -0,0 +1,33 @@
+#include <omp.h>
+#include <stdlib.h>
+
+int
+main (void)
+{
+  int err = 0;
+
+  omp_set_num_threads (4);
+  if (omp_get_max_threads () != 4)
+    abort ();
+  #pragma omp parallel reduction(|: err) num_threads(1)
+  {
+    if (omp_get_max_threads () != 4)
+      err |= 1;
+    omp_set_num_threads (6);
+    #pragma omp task if(0) shared(err)
+    {
+      if (omp_get_max_threads () != 6)
+	err |= 2;
+      omp_set_num_threads (5);
+      if (omp_get_max_threads () != 5)
+	err |= 4;
+    }
+    if (omp_get_max_threads () != 6)
+      err |= 8;
+  }
+  if (err)
+    abort ();
+  if (omp_get_max_threads () != 4)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/icv-2.c b/libgomp/testsuite/libgomp.c/icv-2.c
new file mode 100644
index 0000000..326f8eb
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/icv-2.c
@@ -0,0 +1,46 @@
+/* { dg-do run { target *-*-linux* } } */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE 1
+#endif
+#include <pthread.h>
+#include <omp.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+pthread_barrier_t bar;
+
+void *tf (void *p)
+{
+  int l;
+  if (p)
+    omp_set_num_threads (3);
+  pthread_barrier_wait (&bar);
+  if (!p)
+    omp_set_num_threads (6);
+  pthread_barrier_wait (&bar);
+  omp_set_dynamic (0);
+  if (omp_get_max_threads () != (p ? 3 : 6))
+    abort ();
+  l = 0;
+  #pragma omp parallel num_threads (6) reduction (|:l)
+    {
+      l |= omp_get_max_threads () != (p ? 3 : 6);
+      omp_set_num_threads ((p ? 3 : 6) + omp_get_thread_num ());
+      l |= omp_get_max_threads () != ((p ? 3 : 6) + omp_get_thread_num ());
+    }
+  if (l)
+    abort ();
+  return NULL;
+}
+
+int
+main (void)
+{
+  pthread_t th;
+  pthread_barrier_init (&bar, NULL, 2);
+  pthread_create (&th, NULL, tf, NULL);
+  tf ("");
+  pthread_join (th, NULL);
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/lib-2.c b/libgomp/testsuite/libgomp.c/lib-2.c
new file mode 100644
index 0000000..3a3b3f6
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/lib-2.c
@@ -0,0 +1,25 @@
+#include <stdlib.h>
+#include <omp.h>
+
+int
+main (void)
+{
+  omp_sched_t kind;
+  int modifier;
+
+  omp_set_schedule (omp_sched_static, 32);
+  omp_get_schedule (&kind, &modifier);
+  if (kind != omp_sched_static || modifier != 32)
+    abort ();
+  omp_set_schedule (omp_sched_guided, 4);
+  omp_get_schedule (&kind, &modifier);
+  if (kind != omp_sched_guided || modifier != 4)
+    abort ();
+  if (omp_get_thread_limit () < 0)
+    abort ();
+  omp_set_max_active_levels (6);
+  if (omp_get_max_active_levels () != 6)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/lock-1.c b/libgomp/testsuite/libgomp.c/lock-1.c
new file mode 100644
index 0000000..e09645d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/lock-1.c
@@ -0,0 +1,31 @@
+#include <omp.h>
+#include <stdlib.h>
+
+int
+main (void)
+{
+  int l = 0;
+  omp_nest_lock_t lock;
+  omp_init_nest_lock (&lock);
+  if (omp_test_nest_lock (&lock) != 1)
+    abort ();
+  if (omp_test_nest_lock (&lock) != 2)
+    abort ();
+#pragma omp parallel if (0) reduction (+:l)
+  {
+    /* In OpenMP 2.5 this was supposed to return 3,
+       but in OpenMP 3.0 the parallel region has a different
+       task and omp_*_lock_t are owned by tasks, not by threads.  */
+    if (omp_test_nest_lock (&lock) != 0)
+      l++;
+  }
+  if (l)
+    abort ();
+  if (omp_test_nest_lock (&lock) != 3)
+    abort ();
+  omp_unset_nest_lock (&lock);
+  omp_unset_nest_lock (&lock);
+  omp_unset_nest_lock (&lock);
+  omp_destroy_nest_lock (&lock);
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/lock-2.c b/libgomp/testsuite/libgomp.c/lock-2.c
new file mode 100644
index 0000000..9009b12
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/lock-2.c
@@ -0,0 +1,32 @@
+#include <omp.h>
+#include <stdlib.h>
+
+int
+main (void)
+{
+  int l = 0;
+  omp_nest_lock_t lock;
+  omp_init_nest_lock (&lock);
+#pragma omp parallel reduction (+:l) num_threads (1)
+  {
+    if (omp_test_nest_lock (&lock) != 1)
+      l++;
+    if (omp_test_nest_lock (&lock) != 2)
+      l++;
+  #pragma omp task if (0) shared (lock, l)
+    {
+      if (omp_test_nest_lock (&lock) != 0)
+	l++;
+    }
+  #pragma omp taskwait
+    if (omp_test_nest_lock (&lock) != 3)
+      l++;
+    omp_unset_nest_lock (&lock);
+    omp_unset_nest_lock (&lock);
+    omp_unset_nest_lock (&lock);
+  }
+  if (l)
+    abort ();
+  omp_destroy_nest_lock (&lock);
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/lock-3.c b/libgomp/testsuite/libgomp.c/lock-3.c
new file mode 100644
index 0000000..1fc8372
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/lock-3.c
@@ -0,0 +1,60 @@
+/* { dg-do run { target *-*-linux* } } */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE 1
+#endif
+#include <pthread.h>
+#include <omp.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+pthread_barrier_t bar;
+omp_nest_lock_t lock;
+
+void *tf (void *p)
+{
+  int l;
+  if (p)
+    {
+      if (omp_test_nest_lock (&lock) != 1)
+	abort ();
+      if (omp_test_nest_lock (&lock) != 2)
+	abort ();
+    }
+  pthread_barrier_wait (&bar);
+  if (!p && omp_test_nest_lock (&lock) != 0)
+    abort ();
+  pthread_barrier_wait (&bar);
+  if (p)
+    {
+      if (omp_test_nest_lock (&lock) != 3)
+	abort ();
+      omp_unset_nest_lock (&lock);
+      omp_unset_nest_lock (&lock);
+      omp_unset_nest_lock (&lock);
+    }
+  pthread_barrier_wait (&bar);
+  if (!p)
+    {
+      if (omp_test_nest_lock (&lock) != 1)
+	abort ();
+      if (omp_test_nest_lock (&lock) != 2)
+	abort ();
+      omp_unset_nest_lock (&lock);
+      omp_unset_nest_lock (&lock);
+    }
+  return NULL;
+}
+
+int
+main (void)
+{
+  pthread_t th;
+  omp_init_nest_lock (&lock);
+  pthread_barrier_init (&bar, NULL, 2);
+  pthread_create (&th, NULL, tf, NULL);
+  tf ("");
+  pthread_join (th, NULL);
+  omp_destroy_nest_lock (&lock);
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/loop-4.c b/libgomp/testsuite/libgomp.c/loop-4.c
new file mode 100644
index 0000000..bc57c04
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/loop-4.c
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+extern void abort (void);
+
+int
+main (void)
+{
+  int e = 0;
+#pragma omp parallel num_threads (4) reduction(+:e)
+  {
+    long i;
+    #pragma omp for schedule(dynamic,1)
+    for (i = __LONG_MAX__ - 30001; i <= __LONG_MAX__ - 10001; i += 10000)
+      if (i != __LONG_MAX__ - 30001
+	  && i != __LONG_MAX__ - 20001
+	  && i != __LONG_MAX__ - 10001)
+	e = 1;
+    #pragma omp for schedule(dynamic,1)
+    for (i = -__LONG_MAX__ + 30000; i >= -__LONG_MAX__ + 10000; i -= 10000)
+      if (i != -__LONG_MAX__ + 30000
+	  && i != -__LONG_MAX__ + 20000
+	  && i != -__LONG_MAX__ + 10000)
+	e = 1;
+  }
+  if (e)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/loop-5.c b/libgomp/testsuite/libgomp.c/loop-5.c
new file mode 100644
index 0000000..3a5c7cf
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/loop-5.c
@@ -0,0 +1,276 @@
+#include <omp.h>
+#include <stdlib.h>
+#include <string.h>
+
+int
+test1 (void)
+{
+  short int buf[64], *p;
+  int i;
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for
+  for (p = &buf[10]; p < &buf[54]; p++)
+    *p = 5;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 5 * (i >= 10 && i < 54))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for
+  for (p = &buf[3]; p <= &buf[63]; p += 2)
+    p[-2] = 6;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 6 * ((i & 1) && i <= 61))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for
+  for (p = &buf[16]; p < &buf[51]; p = 4 + p)
+    p[2] = 7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 7 * ((i & 3) == 2 && i >= 18 && i < 53))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for
+  for (p = &buf[16]; p <= &buf[40]; p = p + 4ULL)
+    p[2] = -7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != -7 * ((i & 3) == 2 && i >= 18 && i <= 42))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for
+  for (p = &buf[53]; p > &buf[9]; --p)
+    *p = 5;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 5 * (i >= 10 && i < 54))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for
+  for (p = &buf[63]; p >= &buf[3]; p -= 2)
+    p[-2] = 6;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 6 * ((i & 1) && i <= 61))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for
+  for (p = &buf[48]; p > &buf[15]; p = -4 + p)
+    p[2] = 7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 7 * ((i & 3) == 2 && i >= 18 && i < 53))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for
+  for (p = &buf[40]; p >= &buf[16]; p = p - 4ULL)
+    p[2] = -7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != -7 * ((i & 3) == 2 && i >= 18 && i <= 42))
+      abort ();
+  return 0;
+}
+
+int
+test2 (void)
+{
+  int buf[64], *p;
+  int i;
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (static, 3)
+  for (p = &buf[10]; p < &buf[54]; p++)
+    *p = 5;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 5 * (i >= 10 && i < 54))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (static, 3)
+  for (p = &buf[3]; p <= &buf[63]; p += 2)
+    p[-2] = 6;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 6 * ((i & 1) && i <= 61))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (static, 3)
+  for (p = &buf[16]; p < &buf[51]; p = 4 + p)
+    p[2] = 7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 7 * ((i & 3) == 2 && i >= 18 && i < 53))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (static, 3)
+  for (p = &buf[16]; p <= &buf[40]; p = p + 4ULL)
+    p[2] = -7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != -7 * ((i & 3) == 2 && i >= 18 && i <= 42))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (static, 3)
+  for (p = &buf[53]; p > &buf[9]; --p)
+    *p = 5;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 5 * (i >= 10 && i < 54))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (static, 3)
+  for (p = &buf[63]; p >= &buf[3]; p -= 2)
+    p[-2] = 6;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 6 * ((i & 1) && i <= 61))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (static, 3)
+  for (p = &buf[48]; p > &buf[15]; p = -4 + p)
+    p[2] = 7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 7 * ((i & 3) == 2 && i >= 18 && i < 53))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (static, 3)
+  for (p = &buf[40]; p >= &buf[16]; p = p - 4ULL)
+    p[2] = -7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != -7 * ((i & 3) == 2 && i >= 18 && i <= 42))
+      abort ();
+  return 0;
+}
+
+int
+test3 (void)
+{
+  int buf[64], *p;
+  int i;
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (dynamic, 3)
+  for (p = &buf[10]; p < &buf[54]; p++)
+    *p = 5;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 5 * (i >= 10 && i < 54))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (dynamic, 3)
+  for (p = &buf[3]; p <= &buf[63]; p += 2)
+    p[-2] = 6;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 6 * ((i & 1) && i <= 61))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (dynamic, 3)
+  for (p = &buf[16]; p < &buf[51]; p = 4 + p)
+    p[2] = 7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 7 * ((i & 3) == 2 && i >= 18 && i < 53))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (dynamic, 3)
+  for (p = &buf[16]; p <= &buf[40]; p = p + 4ULL)
+    p[2] = -7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != -7 * ((i & 3) == 2 && i >= 18 && i <= 42))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (dynamic, 3)
+  for (p = &buf[53]; p > &buf[9]; --p)
+    *p = 5;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 5 * (i >= 10 && i < 54))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (dynamic, 3)
+  for (p = &buf[63]; p >= &buf[3]; p -= 2)
+    p[-2] = 6;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 6 * ((i & 1) && i <= 61))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (dynamic, 3)
+  for (p = &buf[48]; p > &buf[15]; p = -4 + p)
+    p[2] = 7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 7 * ((i & 3) == 2 && i >= 18 && i < 53))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (dynamic, 3)
+  for (p = &buf[40]; p >= &buf[16]; p = p - 4ULL)
+    p[2] = -7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != -7 * ((i & 3) == 2 && i >= 18 && i <= 42))
+      abort ();
+  return 0;
+}
+
+int
+test4 (void)
+{
+  int buf[64], *p;
+  int i;
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (runtime)
+  for (p = &buf[10]; p < &buf[54]; p++)
+    *p = 5;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 5 * (i >= 10 && i < 54))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (runtime)
+  for (p = &buf[3]; p <= &buf[63]; p += 2)
+    p[-2] = 6;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 6 * ((i & 1) && i <= 61))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (runtime)
+  for (p = &buf[16]; p < &buf[51]; p = 4 + p)
+    p[2] = 7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 7 * ((i & 3) == 2 && i >= 18 && i < 53))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (runtime)
+  for (p = &buf[16]; p <= &buf[40]; p = p + 4ULL)
+    p[2] = -7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != -7 * ((i & 3) == 2 && i >= 18 && i <= 42))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (runtime)
+  for (p = &buf[53]; p > &buf[9]; --p)
+    *p = 5;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 5 * (i >= 10 && i < 54))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (runtime)
+  for (p = &buf[63]; p >= &buf[3]; p -= 2)
+    p[-2] = 6;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 6 * ((i & 1) && i <= 61))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (runtime)
+  for (p = &buf[48]; p > &buf[15]; p = -4 + p)
+    p[2] = 7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != 7 * ((i & 3) == 2 && i >= 18 && i < 53))
+      abort ();
+  memset (buf, '\0', sizeof (buf));
+#pragma omp parallel for schedule (runtime)
+  for (p = &buf[40]; p >= &buf[16]; p = p - 4ULL)
+    p[2] = -7;
+  for (i = 0; i < 64; i++)
+    if (buf[i] != -7 * ((i & 3) == 2 && i >= 18 && i <= 42))
+      abort ();
+  return 0;
+}
+
+int
+main (void)
+{
+  test1 ();
+  test2 ();
+  test3 ();
+  omp_set_schedule (omp_sched_static, 0);
+  test4 ();
+  omp_set_schedule (omp_sched_static, 3);
+  test4 ();
+  omp_set_schedule (omp_sched_dynamic, 5);
+  test4 ();
+  omp_set_schedule (omp_sched_guided, 2);
+  test4 ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/loop-6.c b/libgomp/testsuite/libgomp.c/loop-6.c
new file mode 100644
index 0000000..9029e18
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/loop-6.c
@@ -0,0 +1,387 @@
+/* { dg-do run } */
+
+#include <omp.h>
+
+extern void abort (void);
+
+#define LLONG_MAX __LONG_LONG_MAX__
+#define ULLONG_MAX (LLONG_MAX * 2ULL + 1)
+#define INT_MAX __INT_MAX__
+
+int arr[6 * 5];
+
+void
+set (int loopidx, int idx)
+{
+#pragma omp atomic
+  arr[loopidx * 5 + idx]++;
+}
+
+#define check(var, val, loopidx, idx) \
+  if (var == (val)) set (loopidx, idx); else
+#define test(loopidx, count) \
+  for (idx = 0; idx < 5; idx++) \
+    if (arr[loopidx * 5 + idx] != idx < count) \
+      abort (); \
+    else \
+      arr[loopidx * 5 + idx] = 0
+
+int
+test1 (void)
+{
+  int e = 0, idx;
+
+#pragma omp parallel reduction(+:e)
+  {
+    long long i;
+    unsigned long long j;
+    #pragma omp for schedule(dynamic,1) nowait
+    for (i = LLONG_MAX - 30001; i <= LLONG_MAX - 10001; i += 10000)
+      {
+	check (i, LLONG_MAX - 30001, 0, 0)
+	check (i, LLONG_MAX - 20001, 0, 1)
+	check (i, LLONG_MAX - 10001, 0, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(dynamic,1) nowait
+    for (i = -LLONG_MAX + 30000; i >= -LLONG_MAX + 10000; i -= 10000)
+      {
+	check (i, -LLONG_MAX + 30000, 1, 0)
+	check (i, -LLONG_MAX + 20000, 1, 1)
+	check (i, -LLONG_MAX + 10000, 1, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(dynamic,1) nowait
+    for (j = 20; j <= LLONG_MAX - 70; j += LLONG_MAX + 50ULL)
+      {
+	check (j, 20, 2, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(dynamic,1) nowait
+    for (j = ULLONG_MAX - 3; j >= LLONG_MAX + 70ULL; j -= LLONG_MAX + 50ULL)
+      {
+	check (j, ULLONG_MAX - 3, 3, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(dynamic,1) nowait
+    for (j = LLONG_MAX - 20000ULL; j <= LLONG_MAX + 10000ULL; j += 10000ULL)
+      {
+	check (j, LLONG_MAX - 20000ULL, 4, 0)
+	check (j, LLONG_MAX - 10000ULL, 4, 1)
+	check (j, LLONG_MAX, 4, 2)
+	check (j, LLONG_MAX + 10000ULL, 4, 3)
+	e = 1;
+      }
+    #pragma omp for schedule(dynamic,1) nowait
+    for (i = -3LL * INT_MAX - 20000LL; i <= INT_MAX + 10000LL; i += INT_MAX + 200LL)
+      {
+	check (i, -3LL * INT_MAX - 20000LL, 5, 0)
+	check (i, -2LL * INT_MAX - 20000LL + 200LL, 5, 1)
+	check (i, -INT_MAX - 20000LL + 400LL, 5, 2)
+	check (i, -20000LL + 600LL, 5, 3)
+	check (i, INT_MAX - 20000LL + 800LL, 5, 4)
+	e = 1;
+      }
+  }
+  if (e)
+    abort ();
+  test (0, 3);
+  test (1, 3);
+  test (2, 1);
+  test (3, 1);
+  test (4, 4);
+  test (5, 5);
+  return 0;
+}
+
+int
+test2 (void)
+{
+  int e = 0, idx;
+
+#pragma omp parallel reduction(+:e)
+  {
+    long long i;
+    unsigned long long j;
+    #pragma omp for schedule(guided,1) nowait
+    for (i = LLONG_MAX - 30001; i <= LLONG_MAX - 10001; i += 10000)
+      {
+	check (i, LLONG_MAX - 30001, 0, 0)
+	check (i, LLONG_MAX - 20001, 0, 1)
+	check (i, LLONG_MAX - 10001, 0, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(guided,1) nowait
+    for (i = -LLONG_MAX + 30000; i >= -LLONG_MAX + 10000; i -= 10000)
+      {
+	check (i, -LLONG_MAX + 30000, 1, 0)
+	check (i, -LLONG_MAX + 20000, 1, 1)
+	check (i, -LLONG_MAX + 10000, 1, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(guided,1) nowait
+    for (j = 20; j <= LLONG_MAX - 70; j += LLONG_MAX + 50ULL)
+      {
+	check (j, 20, 2, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(guided,1) nowait
+    for (j = ULLONG_MAX - 3; j >= LLONG_MAX + 70ULL; j -= LLONG_MAX + 50ULL)
+      {
+	check (j, ULLONG_MAX - 3, 3, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(guided,1) nowait
+    for (j = LLONG_MAX - 20000ULL; j <= LLONG_MAX + 10000ULL; j += 10000ULL)
+      {
+	check (j, LLONG_MAX - 20000ULL, 4, 0)
+	check (j, LLONG_MAX - 10000ULL, 4, 1)
+	check (j, LLONG_MAX, 4, 2)
+	check (j, LLONG_MAX + 10000ULL, 4, 3)
+	e = 1;
+      }
+    #pragma omp for schedule(guided,1) nowait
+    for (i = -3LL * INT_MAX - 20000LL; i <= INT_MAX + 10000LL; i += INT_MAX + 200LL)
+      {
+	check (i, -3LL * INT_MAX - 20000LL, 5, 0)
+	check (i, -2LL * INT_MAX - 20000LL + 200LL, 5, 1)
+	check (i, -INT_MAX - 20000LL + 400LL, 5, 2)
+	check (i, -20000LL + 600LL, 5, 3)
+	check (i, INT_MAX - 20000LL + 800LL, 5, 4)
+	e = 1;
+      }
+  }
+  if (e)
+    abort ();
+  test (0, 3);
+  test (1, 3);
+  test (2, 1);
+  test (3, 1);
+  test (4, 4);
+  test (5, 5);
+  return 0;
+}
+
+int
+test3 (void)
+{
+  int e = 0, idx;
+
+#pragma omp parallel reduction(+:e)
+  {
+    long long i;
+    unsigned long long j;
+    #pragma omp for schedule(static) nowait
+    for (i = LLONG_MAX - 30001; i <= LLONG_MAX - 10001; i += 10000)
+      {
+	check (i, LLONG_MAX - 30001, 0, 0)
+	check (i, LLONG_MAX - 20001, 0, 1)
+	check (i, LLONG_MAX - 10001, 0, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(static) nowait
+    for (i = -LLONG_MAX + 30000; i >= -LLONG_MAX + 10000; i -= 10000)
+      {
+	check (i, -LLONG_MAX + 30000, 1, 0)
+	check (i, -LLONG_MAX + 20000, 1, 1)
+	check (i, -LLONG_MAX + 10000, 1, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(static) nowait
+    for (j = 20; j <= LLONG_MAX - 70; j += LLONG_MAX + 50ULL)
+      {
+	check (j, 20, 2, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(static) nowait
+    for (j = ULLONG_MAX - 3; j >= LLONG_MAX + 70ULL; j -= LLONG_MAX + 50ULL)
+      {
+	check (j, ULLONG_MAX - 3, 3, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(static) nowait
+    for (j = LLONG_MAX - 20000ULL; j <= LLONG_MAX + 10000ULL; j += 10000ULL)
+      {
+	check (j, LLONG_MAX - 20000ULL, 4, 0)
+	check (j, LLONG_MAX - 10000ULL, 4, 1)
+	check (j, LLONG_MAX, 4, 2)
+	check (j, LLONG_MAX + 10000ULL, 4, 3)
+	e = 1;
+      }
+    #pragma omp for schedule(static) nowait
+    for (i = -3LL * INT_MAX - 20000LL; i <= INT_MAX + 10000LL; i += INT_MAX + 200LL)
+      {
+	check (i, -3LL * INT_MAX - 20000LL, 5, 0)
+	check (i, -2LL * INT_MAX - 20000LL + 200LL, 5, 1)
+	check (i, -INT_MAX - 20000LL + 400LL, 5, 2)
+	check (i, -20000LL + 600LL, 5, 3)
+	check (i, INT_MAX - 20000LL + 800LL, 5, 4)
+	e = 1;
+      }
+  }
+  if (e)
+    abort ();
+  test (0, 3);
+  test (1, 3);
+  test (2, 1);
+  test (3, 1);
+  test (4, 4);
+  test (5, 5);
+  return 0;
+}
+
+int
+test4 (void)
+{
+  int e = 0, idx;
+
+#pragma omp parallel reduction(+:e)
+  {
+    long long i;
+    unsigned long long j;
+    #pragma omp for schedule(static,1) nowait
+    for (i = LLONG_MAX - 30001; i <= LLONG_MAX - 10001; i += 10000)
+      {
+	check (i, LLONG_MAX - 30001, 0, 0)
+	check (i, LLONG_MAX - 20001, 0, 1)
+	check (i, LLONG_MAX - 10001, 0, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(static,1) nowait
+    for (i = -LLONG_MAX + 30000; i >= -LLONG_MAX + 10000; i -= 10000)
+      {
+	check (i, -LLONG_MAX + 30000, 1, 0)
+	check (i, -LLONG_MAX + 20000, 1, 1)
+	check (i, -LLONG_MAX + 10000, 1, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(static,1) nowait
+    for (j = 20; j <= LLONG_MAX - 70; j += LLONG_MAX + 50ULL)
+      {
+	check (j, 20, 2, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(static,1) nowait
+    for (j = ULLONG_MAX - 3; j >= LLONG_MAX + 70ULL; j -= LLONG_MAX + 50ULL)
+      {
+	check (j, ULLONG_MAX - 3, 3, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(static,1) nowait
+    for (j = LLONG_MAX - 20000ULL; j <= LLONG_MAX + 10000ULL; j += 10000ULL)
+      {
+	check (j, LLONG_MAX - 20000ULL, 4, 0)
+	check (j, LLONG_MAX - 10000ULL, 4, 1)
+	check (j, LLONG_MAX, 4, 2)
+	check (j, LLONG_MAX + 10000ULL, 4, 3)
+	e = 1;
+      }
+    #pragma omp for schedule(static,1) nowait
+    for (i = -3LL * INT_MAX - 20000LL; i <= INT_MAX + 10000LL; i += INT_MAX + 200LL)
+      {
+	check (i, -3LL * INT_MAX - 20000LL, 5, 0)
+	check (i, -2LL * INT_MAX - 20000LL + 200LL, 5, 1)
+	check (i, -INT_MAX - 20000LL + 400LL, 5, 2)
+	check (i, -20000LL + 600LL, 5, 3)
+	check (i, INT_MAX - 20000LL + 800LL, 5, 4)
+	e = 1;
+      }
+  }
+  if (e)
+    abort ();
+  test (0, 3);
+  test (1, 3);
+  test (2, 1);
+  test (3, 1);
+  test (4, 4);
+  test (5, 5);
+  return 0;
+}
+
+int
+test5 (void)
+{
+  int e = 0, idx;
+
+#pragma omp parallel reduction(+:e)
+  {
+    long long i;
+    unsigned long long j;
+    #pragma omp for schedule(runtime) nowait
+    for (i = LLONG_MAX - 30001; i <= LLONG_MAX - 10001; i += 10000)
+      {
+	check (i, LLONG_MAX - 30001, 0, 0)
+	check (i, LLONG_MAX - 20001, 0, 1)
+	check (i, LLONG_MAX - 10001, 0, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(runtime) nowait
+    for (i = -LLONG_MAX + 30000; i >= -LLONG_MAX + 10000; i -= 10000)
+      {
+	check (i, -LLONG_MAX + 30000, 1, 0)
+	check (i, -LLONG_MAX + 20000, 1, 1)
+	check (i, -LLONG_MAX + 10000, 1, 2)
+	e = 1;
+      }
+    #pragma omp for schedule(runtime) nowait
+    for (j = 20; j <= LLONG_MAX - 70; j += LLONG_MAX + 50ULL)
+      {
+	check (j, 20, 2, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(runtime) nowait
+    for (j = ULLONG_MAX - 3; j >= LLONG_MAX + 70ULL; j -= LLONG_MAX + 50ULL)
+      {
+	check (j, ULLONG_MAX - 3, 3, 0)
+	e = 1;
+      }
+    #pragma omp for schedule(runtime) nowait
+    for (j = LLONG_MAX - 20000ULL; j <= LLONG_MAX + 10000ULL; j += 10000ULL)
+      {
+	check (j, LLONG_MAX - 20000ULL, 4, 0)
+	check (j, LLONG_MAX - 10000ULL, 4, 1)
+	check (j, LLONG_MAX, 4, 2)
+	check (j, LLONG_MAX + 10000ULL, 4, 3)
+	e = 1;
+      }
+    #pragma omp for schedule(runtime) nowait
+    for (i = -3LL * INT_MAX - 20000LL; i <= INT_MAX + 10000LL; i += INT_MAX + 200LL)
+      {
+	check (i, -3LL * INT_MAX - 20000LL, 5, 0)
+	check (i, -2LL * INT_MAX - 20000LL + 200LL, 5, 1)
+	check (i, -INT_MAX - 20000LL + 400LL, 5, 2)
+	check (i, -20000LL + 600LL, 5, 3)
+	check (i, INT_MAX - 20000LL + 800LL, 5, 4)
+	e = 1;
+      }
+  }
+  if (e)
+    abort ();
+  test (0, 3);
+  test (1, 3);
+  test (2, 1);
+  test (3, 1);
+  test (4, 4);
+  test (5, 5);
+  return 0;
+}
+
+int
+main (void)
+{
+  if (2 * sizeof (int) != sizeof (long long))
+    return 0;
+  test1 ();
+  test2 ();
+  test3 ();
+  test4 ();
+  omp_set_schedule (omp_sched_static, 0);
+  test5 ();
+  omp_set_schedule (omp_sched_static, 3);
+  test5 ();
+  omp_set_schedule (omp_sched_dynamic, 5);
+  test5 ();
+  omp_set_schedule (omp_sched_guided, 2);
+  test5 ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/loop-7.c b/libgomp/testsuite/libgomp.c/loop-7.c
new file mode 100644
index 0000000..fc97f4a
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/loop-7.c
@@ -0,0 +1,105 @@
+/* { dg-do run } */
+
+#include <omp.h>
+
+extern void abort (void);
+
+#define LLONG_MAX __LONG_LONG_MAX__
+#define ULLONG_MAX (LLONG_MAX * 2ULL + 1)
+#define INT_MAX __INT_MAX__
+
+int v;
+
+int
+test1 (void)
+{
+  int e = 0, cnt = 0;
+  long long i;
+  unsigned long long j;
+  char buf[6], *p;
+
+  #pragma omp for schedule(dynamic,1) collapse(2) nowait
+  for (i = LLONG_MAX - 30001; i <= LLONG_MAX - 10001; i += 10000)
+    for (j = 20; j <= LLONG_MAX - 70; j += LLONG_MAX + 50ULL)
+      if ((i != LLONG_MAX - 30001
+	   && i != LLONG_MAX - 20001
+	   && i != LLONG_MAX - 10001)
+	  || j != 20)
+	e = 1;
+      else
+	cnt++;
+  if (e || cnt != 3)
+    abort ();
+  else
+    cnt = 0;
+
+  #pragma omp for schedule(guided,1) collapse(2) nowait
+  for (i = -LLONG_MAX + 30000; i >= -LLONG_MAX + 10000; i -= 10000)
+    for (j = ULLONG_MAX - 3; j >= LLONG_MAX + 70ULL; j -= LLONG_MAX + 50ULL)
+      if ((i != -LLONG_MAX + 30000
+	   && i != -LLONG_MAX + 20000
+	   && i != -LLONG_MAX + 10000)
+	  || j != ULLONG_MAX - 3)
+	e = 1;
+      else
+	cnt++;
+  if (e || cnt != 3)
+    abort ();
+  else
+    cnt = 0;
+
+  #pragma omp for schedule(static,1) collapse(2) nowait
+  for (i = LLONG_MAX - 30001; i <= LLONG_MAX - 10001; i += 10000)
+    for (j = 20; j <= LLONG_MAX - 70 + v; j += LLONG_MAX + 50ULL)
+      if ((i != LLONG_MAX - 30001
+	   && i != LLONG_MAX - 20001
+	   && i != LLONG_MAX - 10001)
+	  || j != 20)
+	e = 1;
+      else
+	cnt++;
+  if (e || cnt != 3)
+    abort ();
+  else
+    cnt = 0;
+
+  #pragma omp for schedule(static) collapse(2) nowait
+  for (i = -LLONG_MAX + 30000 + v; i >= -LLONG_MAX + 10000; i -= 10000)
+    for (j = ULLONG_MAX - 3; j >= LLONG_MAX + 70ULL; j -= LLONG_MAX + 50ULL)
+      if ((i != -LLONG_MAX + 30000
+	   && i != -LLONG_MAX + 20000
+	   && i != -LLONG_MAX + 10000)
+	  || j != ULLONG_MAX - 3)
+	e = 1;
+      else
+	cnt++;
+  if (e || cnt != 3)
+    abort ();
+  else
+    cnt = 0;
+
+  #pragma omp for schedule(runtime) collapse(2) nowait
+  for (i = 10; i < 30; i++)
+    for (p = buf; p <= buf + 4; p += 2)
+      if (i < 10 || i >= 30 || (p != buf && p != buf + 2 && p != buf + 4))
+	e = 1;
+      else
+	cnt++;
+  if (e || cnt != 60)
+    abort ();
+  else
+    cnt = 0;
+
+  return 0;
+}
+
+int
+main (void)
+{
+  if (2 * sizeof (int) != sizeof (long long))
+    return 0;
+  asm volatile ("" : "+r" (v));
+  omp_set_schedule (omp_sched_dynamic, 1);
+  test1 ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/loop-8.c b/libgomp/testsuite/libgomp.c/loop-8.c
new file mode 100644
index 0000000..25db25c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/loop-8.c
@@ -0,0 +1,27 @@
+extern void abort (void);
+
+int buf[256];
+
+void __attribute__((noinline))
+foo (void)
+{
+  int i;
+  #pragma omp for schedule (auto)
+    for (i = 0; i < 256; i++)
+      buf[i] += i;
+}
+
+int
+main (void)
+{
+  int i;
+  #pragma omp parallel for schedule (auto)
+    for (i = 0; i < 256; i++)
+      buf[i] = i;
+  #pragma omp parallel num_threads (4)
+    foo ();
+  for (i = 0; i < 256; i++)
+    if (buf[i] != 2 * i)
+      abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/loop-9.c b/libgomp/testsuite/libgomp.c/loop-9.c
new file mode 100644
index 0000000..1f789e1
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/loop-9.c
@@ -0,0 +1,18 @@
+extern void abort (void);
+
+char buf[8] = "01234567";
+char buf2[8] = "23456789";
+
+int
+main (void)
+{
+  char *p, *q;
+  int sum = 0;
+  #pragma omp parallel for collapse (2) reduction (+:sum) lastprivate (p, q)
+  for (p = buf; p < &buf[8]; p++)
+    for (q = &buf2[0]; q <= buf2 + 7; q++)
+      sum += (*p - '0') + (*q - '0');
+  if (p != &buf[8] || q != buf2 + 8 || sum != 576)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/nested-3.c b/libgomp/testsuite/libgomp.c/nested-3.c
new file mode 100644
index 0000000..6186006
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/nested-3.c
@@ -0,0 +1,89 @@
+#include <omp.h>
+#include <stdlib.h>
+#include <string.h>
+
+int
+main (void)
+{
+  int e[3];
+
+  memset (e, '\0', sizeof (e));
+  omp_set_nested (1);
+  omp_set_dynamic (0);
+  if (omp_in_parallel ()
+      || omp_get_level () != 0
+      || omp_get_ancestor_thread_num (0) != 0
+      || omp_get_ancestor_thread_num (-1) != -1
+      || omp_get_ancestor_thread_num (1) != -1
+      || omp_get_team_size (0) != 1
+      || omp_get_team_size (-1) != -1
+      || omp_get_team_size (1) != -1
+      || omp_get_active_level () != 0)
+    abort ();
+#pragma omp parallel num_threads (4)
+  {
+    int tn1 = omp_get_thread_num ();
+    if (omp_in_parallel () != 1
+	|| omp_get_num_threads () != 4
+	|| tn1 >= 4 || tn1 < 0
+	|| omp_get_level () != 1
+	|| omp_get_ancestor_thread_num (0) != 0
+	|| omp_get_ancestor_thread_num (1) != tn1
+	|| omp_get_ancestor_thread_num (-1) != -1
+	|| omp_get_ancestor_thread_num (2) != -1
+	|| omp_get_team_size (0) != 1
+	|| omp_get_team_size (1) != omp_get_num_threads ()
+	|| omp_get_team_size (-1) != -1
+	|| omp_get_team_size (2) != -1
+	|| omp_get_active_level () != 1)
+      #pragma omp atomic
+	e[0] += 1;
+    #pragma omp parallel if (0) num_threads(5) firstprivate(tn1)
+    {
+      int tn2 = omp_get_thread_num ();
+      if (omp_in_parallel () != 1
+	  || omp_get_num_threads () != 1
+	  || tn2 != 0
+	  || omp_get_level () != 2
+	  || omp_get_ancestor_thread_num (0) != 0
+	  || omp_get_ancestor_thread_num (1) != tn1
+	  || omp_get_ancestor_thread_num (2) != tn2
+	  || omp_get_ancestor_thread_num (-1) != -1
+	  || omp_get_ancestor_thread_num (3) != -1
+	  || omp_get_team_size (0) != 1
+	  || omp_get_team_size (1) != 4
+	  || omp_get_team_size (2) != 1
+	  || omp_get_team_size (-1) != -1
+	  || omp_get_team_size (3) != -1
+	  || omp_get_active_level () != 1)
+	#pragma omp atomic
+	  e[1] += 1;
+      #pragma omp parallel num_threads(2) firstprivate(tn1, tn2)
+      {
+	int tn3 = omp_get_thread_num ();
+	if (omp_in_parallel () != 1
+	    || omp_get_num_threads () != 2
+	    || tn3 > 1 || tn3 < 0
+	    || omp_get_level () != 3
+	    || omp_get_ancestor_thread_num (0) != 0
+	    || omp_get_ancestor_thread_num (1) != tn1
+	    || omp_get_ancestor_thread_num (2) != tn2
+	    || omp_get_ancestor_thread_num (3) != tn3
+	    || omp_get_ancestor_thread_num (-1) != -1
+	    || omp_get_ancestor_thread_num (4) != -1
+	    || omp_get_team_size (0) != 1
+	    || omp_get_team_size (1) != 4
+	    || omp_get_team_size (2) != 1
+	    || omp_get_team_size (3) != 2
+	    || omp_get_team_size (-1) != -1
+	    || omp_get_team_size (4) != -1
+	    || omp_get_active_level () != 2)
+	  #pragma omp atomic
+	    e[2] += 1;
+      }
+    }
+  }
+  if (e[0] || e[1] || e[2])
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/nestedfn-6.c b/libgomp/testsuite/libgomp.c/nestedfn-6.c
new file mode 100644
index 0000000..c0ace6b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/nestedfn-6.c
@@ -0,0 +1,21 @@
+extern void abort (void);
+
+int j;
+
+int
+main (void)
+{
+  int i;
+  void nested (void) { i = 0; }
+#pragma omp parallel for lastprivate (i)
+  for (i = 0; i < 50; i += 3)
+    ;
+  if (i != 51)
+    abort ();
+#pragma omp parallel for lastprivate (j)
+  for (j = -50; j < 70; j += 7)
+    ;
+  if (j != 76)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/pr26943-2.c b/libgomp/testsuite/libgomp.c/pr26943-2.c
index 7780484..c052e81 100644
--- a/libgomp/testsuite/libgomp.c/pr26943-2.c
+++ b/libgomp/testsuite/libgomp.c/pr26943-2.c
@@ -20,7 +20,7 @@ main (void)
     {
       if (a != 8 || b != 12 || e[0] != 'a' || f[0] != 'b')
 	j++;
-#pragma omp barrier
+#pragma omp barrier	/* { dg-warning "may not be closely nested" } */
 #pragma omp atomic
       a += i;
       b += i;
@@ -31,7 +31,7 @@ main (void)
       f[0] += i;
       g[0] = 'g' + i;
       h[0] = 'h' + i;
-#pragma omp barrier
+#pragma omp barrier	/* { dg-warning "may not be closely nested" } */
       if (a != 8 + 6 || b != 12 + i || c != i || d != i)
 	j += 8;
       if (e[0] != 'a' + 6 || f[0] != 'b' + i || g[0] != 'g' + i)
diff --git a/libgomp/testsuite/libgomp.c/pr26943-3.c b/libgomp/testsuite/libgomp.c/pr26943-3.c
index be93cb4..dc3d501 100644
--- a/libgomp/testsuite/libgomp.c/pr26943-3.c
+++ b/libgomp/testsuite/libgomp.c/pr26943-3.c
@@ -26,7 +26,7 @@ main (void)
 	{
 	  if (a != 8 || b != 12 || e[0] != 'a' || f[0] != 'b')
 	    j++;
-#pragma omp barrier
+#pragma omp barrier	/* { dg-warning "may not be closely nested" } */
 #pragma omp atomic
 	  a += i;
 	  b += i;
@@ -37,7 +37,7 @@ main (void)
 	  f[0] += i;
 	  g[0] = 'g' + i;
 	  h[0] = 'h' + i;
-#pragma omp barrier
+#pragma omp barrier	/* { dg-warning "may not be closely nested" } */
 	  if (a != 8 + 6 || b != 12 + i || c != i || d != i)
 	    j += 8;
 	  if (e[0] != 'a' + 6 || f[0] != 'b' + i || g[0] != 'g' + i)
diff --git a/libgomp/testsuite/libgomp.c/pr26943-4.c b/libgomp/testsuite/libgomp.c/pr26943-4.c
index 33d3685..0f1d419 100644
--- a/libgomp/testsuite/libgomp.c/pr26943-4.c
+++ b/libgomp/testsuite/libgomp.c/pr26943-4.c
@@ -27,7 +27,7 @@ main (void)
 	{
 	  if (a != 8 || b != 12 || e[0] != 'a' || f[0] != 'b')
 	    j++;
-#pragma omp barrier
+#pragma omp barrier	/* { dg-warning "may not be closely nested" } */
 #pragma omp atomic
 	  a += i;
 	  b += i;
@@ -38,7 +38,7 @@ main (void)
 	  f[0] += i;
 	  g[0] = 'g' + i;
 	  h[0] = 'h' + i;
-#pragma omp barrier
+#pragma omp barrier	/* { dg-warning "may not be closely nested" } */
 	  if (a != 8 + 6 || b != 12 + i || c != i || d != i)
 	    j += 8;
 	  if (e[0] != 'a' + 6 || f[0] != 'b' + i || g[0] != 'g' + i)
diff --git a/libgomp/testsuite/libgomp.c/sort-1.c b/libgomp/testsuite/libgomp.c/sort-1.c
new file mode 100644
index 0000000..269d69d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/sort-1.c
@@ -0,0 +1,379 @@
+/* Test and benchmark of a couple of parallel sorting algorithms.
+   Copyright (C) 2008 Free Software Foundation, Inc.
+
+   GCC is free software; you can redistribute it and/or modify it under
+   the terms of the GNU General Public License as published by the Free
+   Software Foundation; either version 3, or (at your option) any later
+   version.
+
+   GCC is distributed in the hope that it will be useful, but WITHOUT ANY
+   WARRANTY; without even the implied warranty of MERCHANTABILITY or
+   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+   for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with GCC; see the file COPYING3.  If not see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <limits.h>
+#include <omp.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+int failures;
+
+#define THRESHOLD 100
+
+static void
+verify (const char *name, double stime, int *array, int count)
+{
+  int i;
+  double etime = omp_get_wtime ();
+
+  printf ("%s: %g\n", name, etime - stime);
+  for (i = 1; i < count; i++)
+    if (array[i] < array[i - 1])
+      {
+	printf ("%s: incorrectly sorted\n", name);
+	failures = 1;
+      }
+}
+
+static void
+insertsort (int *array, int s, int e)
+{
+  int i, j, val;
+  for (i = s + 1; i <= e; i++)
+    {
+      val = array[i];
+      j = i;
+      while (j-- > s && val < array[j])
+	array[j + 1] = array[j];
+      array[j + 1] = val;
+    }
+}
+
+struct int_pair
+{
+  int lo;
+  int hi;
+};
+
+struct int_pair_stack
+{
+  struct int_pair *top;
+#define STACK_SIZE 4 * CHAR_BIT * sizeof (int)
+  struct int_pair arr[STACK_SIZE];
+};
+
+static inline void
+init_int_pair_stack (struct int_pair_stack *stack)
+{
+  stack->top = &stack->arr[0];
+}
+
+static inline void
+push_int_pair_stack (struct int_pair_stack *stack, int lo, int hi)
+{
+  stack->top->lo = lo;
+  stack->top->hi = hi;
+  stack->top++;
+}
+
+static inline void
+pop_int_pair_stack (struct int_pair_stack *stack, int *lo, int *hi)
+{
+  stack->top--;
+  *lo = stack->top->lo;
+  *hi = stack->top->hi;
+}
+
+static inline int
+size_int_pair_stack (struct int_pair_stack *stack)
+{
+  return stack->top - &stack->arr[0];
+}
+
+static inline void
+busy_wait (void)
+{
+#if defined __i386__ || defined __x86_64__
+  __asm volatile ("rep; nop" : : : "memory");
+#elif defined __ia64__
+  __asm volatile ("hint @pause" : : : "memory");
+#elif defined __sparc__ && (defined __arch64__ || defined __sparc_v9__)
+  __asm volatile ("membar #LoadLoad" : : : "memory");
+#else
+  __asm volatile ("" : : : "memory");
+#endif
+}
+
+static inline void
+swap (int *array, int a, int b)
+{
+  int val = array[a];
+  array[a] = array[b];
+  array[b] = val;
+}
+
+static inline int
+choose_pivot (int *array, int lo, int hi)
+{
+  int mid = (lo + hi) / 2;
+
+  if (array[mid] < array[lo])
+    swap (array, lo, mid);
+  if (array[hi] < array[mid])
+    {
+      swap (array, mid, hi);
+      if (array[mid] < array[lo])
+	swap (array, lo, mid);
+    }
+  return array[mid];
+}
+
+static inline int
+partition (int *array, int lo, int hi)
+{
+  int pivot = choose_pivot (array, lo, hi);
+  int left = lo;
+  int right = hi;
+
+  for (;;)
+    {
+      while (array[++left] < pivot);
+      while (array[--right] > pivot);
+      if (left >= right)
+	break;
+      swap (array, left, right);
+    }
+  return left;
+}
+
+static void
+sort1 (int *array, int count)
+{
+  omp_lock_t lock;
+  struct int_pair_stack global_stack;
+  int busy = 1;
+  int num_threads;
+
+  omp_init_lock (&lock);
+  init_int_pair_stack (&global_stack);
+  #pragma omp parallel firstprivate (array, count)
+  {
+    int lo = 0, hi = 0, mid, next_lo, next_hi;
+    bool idle = true;
+    struct int_pair_stack local_stack;
+
+    init_int_pair_stack (&local_stack);
+    if (omp_get_thread_num () == 0)
+      {
+	num_threads = omp_get_num_threads ();
+	hi = count - 1;
+	idle = false;
+      }
+
+    for (;;)
+      {
+	if (hi - lo < THRESHOLD)
+	  {
+	    insertsort (array, lo, hi);
+	    lo = hi;
+	  }
+	if (lo >= hi)
+	  {
+	    if (size_int_pair_stack (&local_stack) == 0)
+	      {
+	      again:
+		omp_set_lock (&lock);
+		if (size_int_pair_stack (&global_stack) == 0)
+		  {
+		    if (!idle)
+		      busy--;
+		    if (busy == 0)
+		      {
+			omp_unset_lock (&lock);
+			break;
+		      }
+		    omp_unset_lock (&lock);
+		    idle = true;
+		    while (size_int_pair_stack (&global_stack) == 0
+			   && busy)
+		      busy_wait ();
+		    goto again;
+		  }
+		if (idle)
+		  busy++;
+		pop_int_pair_stack (&global_stack, &lo, &hi);
+		omp_unset_lock (&lock);
+		idle = false;
+	      }
+	    else
+	      pop_int_pair_stack (&local_stack, &lo, &hi);
+	  }
+
+	mid = partition (array, lo, hi);
+	if (mid - lo < hi - mid)
+	  {
+	    next_lo = mid;
+	    next_hi = hi;
+	    hi = mid - 1;
+	  }
+	else
+	  {
+	    next_lo = lo;
+	    next_hi = mid - 1;
+	    lo = mid;
+	  }
+
+	if (next_hi - next_lo < THRESHOLD)
+	  insertsort (array, next_lo, next_hi);
+	else
+	  {
+	    if (size_int_pair_stack (&global_stack) < num_threads - 1)
+	      {
+		int size;
+
+		omp_set_lock (&lock);
+		size = size_int_pair_stack (&global_stack);
+		if (size < num_threads - 1 && size < STACK_SIZE)
+		  push_int_pair_stack (&global_stack, next_lo, next_hi);
+		else
+		  push_int_pair_stack (&local_stack, next_lo, next_hi);
+		omp_unset_lock (&lock);
+	      }
+	    else
+	      push_int_pair_stack (&local_stack, next_lo, next_hi);
+	  }
+      }
+    }
+  omp_destroy_lock (&lock);
+}
+
+static void
+sort2_1 (int *array, int lo, int hi, int num_threads, int *busy)
+{
+  int mid;
+
+  if (hi - lo < THRESHOLD)
+    {
+      insertsort (array, lo, hi);
+      return;
+    }
+
+  mid = partition (array, lo, hi);
+
+  if (*busy >= num_threads)
+    {
+      sort2_1 (array, lo, mid - 1, num_threads, busy);
+      sort2_1 (array, mid, hi, num_threads, busy);
+      return;
+    }
+
+  #pragma omp atomic
+    *busy += 1;
+
+  #pragma omp parallel num_threads (2) \
+		       firstprivate (array, lo, hi, mid, num_threads, busy)
+  {
+    if (omp_get_thread_num () == 0)
+      sort2_1 (array, lo, mid - 1, num_threads, busy);
+    else
+      {
+	sort2_1 (array, mid, hi, num_threads, busy);
+	#pragma omp atomic
+	  *busy -= 1;
+      }
+  }
+}
+
+static void
+sort2 (int *array, int count)
+{
+  int num_threads;
+  int busy = 1;
+
+  #pragma omp parallel
+    #pragma omp single nowait
+      num_threads = omp_get_num_threads ();
+
+  sort2_1 (array, 0, count - 1, num_threads, &busy);
+}
+
+#if _OPENMP >= 200805
+static void
+sort3_1 (int *array, int lo, int hi)
+{
+  int mid;
+
+  if (hi - lo < THRESHOLD)
+    {
+      insertsort (array, lo, hi);
+      return;
+    }
+
+  mid = partition (array, lo, hi);
+  #pragma omp task
+    sort3_1 (array, lo, mid - 1);
+  sort3_1 (array, mid, hi);
+}
+
+static void
+sort3 (int *array, int count)
+{
+  #pragma omp parallel
+    #pragma omp single
+      sort3_1 (array, 0, count - 1);
+}
+#endif
+
+int
+main (int argc, char **argv)
+{
+  int i, count = 1000000;
+  double stime;
+  int *unsorted, *sorted, num_threads;
+  if (argc >= 2)
+    count = strtoul (argv[1], NULL, 0);
+
+  unsorted = malloc (count * sizeof (int));
+  sorted = malloc (count * sizeof (int));
+  if (unsorted == NULL || sorted == NULL)
+    {
+      puts ("allocation failure");
+      exit (1);
+    }
+
+  srand (0xdeadbeef);
+  for (i = 0; i < count; i++)
+    unsorted[i] = rand ();
+
+  omp_set_nested (1);
+  omp_set_dynamic (0);
+  #pragma omp parallel
+    #pragma omp single nowait
+      num_threads = omp_get_num_threads ();
+  printf ("Threads: %d\n", num_threads);
+
+  memcpy (sorted, unsorted, count * sizeof (int));
+  stime = omp_get_wtime ();
+  sort1 (sorted, count);
+  verify ("sort1", stime, sorted, count);
+
+  memcpy (sorted, unsorted, count * sizeof (int));
+  stime = omp_get_wtime ();
+  sort2 (sorted, count);
+  verify ("sort2", stime, sorted, count);
+
+#if _OPENMP >= 200805
+  memcpy (sorted, unsorted, count * sizeof (int));
+  stime = omp_get_wtime ();
+  sort3 (sorted, count);
+  verify ("sort3", stime, sorted, count);
+#endif
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/task-1.c b/libgomp/testsuite/libgomp.c/task-1.c
new file mode 100644
index 0000000..66f58a2
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/task-1.c
@@ -0,0 +1,84 @@
+extern void abort (void);
+
+int a = 18;
+
+void
+f1 (int i, int j, int k)
+{
+  int l = 6, m = 7, n = 8;
+#pragma omp task private(j, m) shared(k, n)
+  {
+    j = 6;
+    m = 5;
+    if (++a != 19 || ++i != 9 || j != 6 || ++l != 7 || m != 5 || ++n != 9)
+      #pragma omp atomic
+	k++;
+  }
+#pragma omp taskwait
+  if (a != 19 || i != 8 || j != 26 || k != 0 || l != 6 || m != 7 || n != 9)
+    abort ();
+}
+
+int v1 = 1, v2 = 2, v5 = 5;
+int err;
+
+void
+f2 (void)
+{
+  int v3 = 3;
+#pragma omp sections private (v1) firstprivate (v2)
+  {
+  #pragma omp section
+    {
+      int v4 = 4;
+      v1 = 7;
+      #pragma omp task
+	{
+	  if (++v1 != 8 || ++v2 != 3 || ++v3 != 4 || ++v4 != 5 || ++v5 != 6)
+	    err = 1;
+	}
+      #pragma omp taskwait
+      if (v1 != 7 || v2 != 2 || v3 != 3 || v4 != 4 || v5 != 6)
+	abort ();
+      if (err)
+	abort ();
+    }
+  }
+}
+
+void
+f3 (int i, int j, int k)
+{
+  int l = 6, m = 7, n = 8;
+#pragma omp task private(j, m) shared(k, n) untied
+  {
+    j = 6;
+    m = 5;
+    if (++a != 19 || ++i != 9 || j != 6 || ++l != 7 || m != 5 || ++n != 9)
+      #pragma omp atomic
+	k++;
+  }
+#pragma omp taskwait
+  if (a != 19 || i != 8 || j != 26 || k != 0 || l != 6 || m != 7 || n != 9)
+    abort ();
+}
+
+int
+main (void)
+{
+  f1 (8, 26, 0);
+  f2 ();
+  a = 18;
+  f3 (8, 26, 0);
+  a = 18;
+#pragma omp parallel num_threads(4)
+  {
+    #pragma omp master
+      {
+	f1 (8, 26, 0);
+	a = 18;
+	f3 (8, 26, 0);
+      }
+  }
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/task-2.c b/libgomp/testsuite/libgomp.c/task-2.c
new file mode 100644
index 0000000..ed6a09c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/task-2.c
@@ -0,0 +1,53 @@
+extern void abort (void);
+
+int
+f1 (void)
+{
+  int a = 6, e = 0;
+  int nested (int x)
+  {
+    return x + a;
+  }
+  #pragma omp task
+  {
+    int n = nested (5);
+    if (n != 11)
+      #pragma omp atomic
+	e += 1;
+  }
+  #pragma omp taskwait
+  return e;
+}
+
+int
+f2 (void)
+{
+  int a = 6, e = 0;
+  int nested (int x)
+  {
+    return x + a;
+  }
+  a = nested (4);
+  #pragma omp task
+  {
+    if (a != 10)
+      #pragma omp atomic
+	e += 1;
+  }
+  #pragma omp taskwait
+  return e;
+}
+
+int
+main (void)
+{
+  int e = 0;
+  #pragma omp parallel num_threads(4) reduction(+:e)
+  {
+    e += f1 ();
+    e += f2 ();
+  }
+  if (e)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/task-3.c b/libgomp/testsuite/libgomp.c/task-3.c
new file mode 100644
index 0000000..5657346
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/task-3.c
@@ -0,0 +1,70 @@
+/* { dg-do run } */
+
+#include <omp.h>
+extern void abort ();
+
+int l = 5;
+
+int
+foo (int i)
+{
+  int j = 7;
+  const int k = 8;
+  #pragma omp task firstprivate (i) shared (j, l)
+  {
+    #pragma omp critical
+      {
+	j += i;
+	l += k;
+      }
+  }
+  i++;
+  #pragma omp task firstprivate (i) shared (j, l)
+  {
+    #pragma omp critical
+      {
+	j += i;
+	l += k;
+      }
+  }
+  i++;
+  #pragma omp task firstprivate (i) shared (j, l)
+  {
+    #pragma omp critical
+      {
+	j += i;
+	l += k;
+      }
+  }
+  i++;
+  #pragma omp task firstprivate (i) shared (j, l)
+  {
+    #pragma omp critical
+      {
+	j += i;
+	l += k;
+      }
+  }
+  i++;
+  #pragma omp taskwait
+  return (i != 8 * omp_get_thread_num () + 4
+	  || j != 4 * i - 3
+	  || k != 8);
+}
+
+int
+main (void)
+{
+  int r = 0;
+  #pragma omp parallel num_threads (4) reduction(+:r)
+    if (omp_get_num_threads () != 4)
+      {
+	#pragma omp master
+	  l = 133;
+      }
+    else if (foo (8 * omp_get_thread_num ()))
+      r++;
+  if (r || l != 133)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.c/task-4.c b/libgomp/testsuite/libgomp.c/task-4.c
new file mode 100644
index 0000000..1843593
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/task-4.c
@@ -0,0 +1,40 @@
+/* { dg-do run } */
+
+#include <omp.h>
+#include <stdlib.h>
+#include <string.h>
+
+int e;
+
+void __attribute__((noinline))
+baz (int i, int *p, int j, int *q)
+{
+  if (p[0] != 1 || p[i] != 3 || q[0] != 2 || q[j] != 4)
+    #pragma omp atomic
+      e++;
+}
+
+void __attribute__((noinline))
+foo (int i, int j)
+{
+  int p[i + 1];
+  int q[j + 1];
+  memset (p, 0, sizeof (p));
+  memset (q, 0, sizeof (q));
+  p[0] = 1;
+  p[i] = 3;
+  q[0] = 2;
+  q[j] = 4;
+  #pragma omp task firstprivate (p, q)
+    baz (i, p, j, q);
+}
+
+int
+main (void)
+{
+  #pragma omp parallel num_threads (4)
+    foo (5 + omp_get_thread_num (), 7 + omp_get_thread_num ());
+  if (e)
+    abort ();
+  return 0;
+}