Merge current set of OpenACC changes from gomp-4_0-branch.

	contrib/
	* gcc_update (files_and_dependencies): Update rules for new
	libgomp/plugin/Makefrag.am and libgomp/plugin/configfrag.ac files.
	gcc/
	* builtin-types.def (BT_FN_VOID_INT_INT_VAR)
	(BT_FN_VOID_INT_PTR_SIZE_PTR_PTR_PTR_INT_INT_VAR)
	(BT_FN_VOID_INT_OMPFN_PTR_SIZE_PTR_PTR_PTR_INT_INT_INT_INT_INT_VAR):
	New function types.
	* builtins.c: Include "gomp-constants.h".
	(expand_builtin_acc_on_device): New function.
	(expand_builtin, is_inexpensive_builtin): Handle
	BUILT_IN_ACC_ON_DEVICE.
	* builtins.def (DEF_GOACC_BUILTIN, DEF_GOACC_BUILTIN_COMPILER):
	New macros.
	* cgraph.c (cgraph_node::create): Consider flag_openacc next to
	flag_openmp.
	* config.gcc <nvptx-*> (tm_file): Add nvptx/offload.h.
	<*-intelmic-* | *-intelmicemul-*> (tm_file): Add
	i386/intelmic-offload.h.
	* gcc.c (LINK_COMMAND_SPEC, GOMP_SELF_SPECS): For -fopenacc, link
	to libgomp and its dependencies.
	* config/arc/arc.h (LINK_COMMAND_SPEC): Likewise.
	* config/darwin.h (LINK_COMMAND_SPEC_A): Likewise.
	* config/i386/mingw32.h (GOMP_SELF_SPECS): Likewise.
	* config/ia64/hpux.h (LIB_SPEC): Likewise.
	* config/pa/pa-hpux11.h (LIB_SPEC): Likewise.
	* config/pa/pa64-hpux.h (LIB_SPEC): Likewise.
	* doc/generic.texi: Update for OpenACC changes.
	* doc/gimple.texi: Likewise.
	* doc/invoke.texi: Likewise.
	* doc/sourcebuild.texi: Likewise.
	* gimple-pretty-print.c (dump_gimple_omp_for): Handle
	GF_OMP_FOR_KIND_OACC_LOOP.
	(dump_gimple_omp_target): Handle GF_OMP_TARGET_KIND_OACC_KERNELS,
	GF_OMP_TARGET_KIND_OACC_PARALLEL, GF_OMP_TARGET_KIND_OACC_DATA,
	GF_OMP_TARGET_KIND_OACC_UPDATE,
	GF_OMP_TARGET_KIND_OACC_ENTER_EXIT_DATA.
	Dump more data.
	* gimple.c: Update comments for OpenACC changes.
	* gimple.def: Likewise.
	* gimple.h: Likewise.
	(enum gf_mask): Add GF_OMP_FOR_KIND_OACC_LOOP,
	GF_OMP_TARGET_KIND_OACC_PARALLEL, GF_OMP_TARGET_KIND_OACC_KERNELS,
	GF_OMP_TARGET_KIND_OACC_DATA, GF_OMP_TARGET_KIND_OACC_UPDATE,
	GF_OMP_TARGET_KIND_OACC_ENTER_EXIT_DATA.
	(gimple_omp_for_cond, gimple_omp_for_set_cond): Sort in the
	appropriate place.
	(is_gimple_omp_oacc, is_gimple_omp_offloaded): New functions.
	* gimplify.c: Include "gomp-constants.h".
	Update comments for OpenACC changes.
	(is_gimple_stmt): Handle OACC_PARALLEL, OACC_KERNELS, OACC_DATA,
	OACC_HOST_DATA, OACC_DECLARE, OACC_UPDATE, OACC_ENTER_DATA,
	OACC_EXIT_DATA, OACC_CACHE, OACC_LOOP.
	(gimplify_scan_omp_clauses, gimplify_adjust_omp_clauses): Handle
	OMP_CLAUSE__CACHE_, OMP_CLAUSE_ASYNC, OMP_CLAUSE_WAIT,
	OMP_CLAUSE_NUM_GANGS, OMP_CLAUSE_NUM_WORKERS,
	OMP_CLAUSE_VECTOR_LENGTH, OMP_CLAUSE_GANG, OMP_CLAUSE_WORKER,
	OMP_CLAUSE_VECTOR, OMP_CLAUSE_DEVICE_RESIDENT,
	OMP_CLAUSE_USE_DEVICE, OMP_CLAUSE_INDEPENDENT, OMP_CLAUSE_AUTO,
	OMP_CLAUSE_SEQ.
	(gimplify_adjust_omp_clauses_1, gimplify_adjust_omp_clauses): Use
	GOMP_MAP_* instead of OMP_CLAUSE_MAP_*.  Use
	OMP_CLAUSE_SET_MAP_KIND.
	(gimplify_oacc_cache): New function.
	(gimplify_omp_for): Handle OACC_LOOP.
	(gimplify_omp_workshare): Handle OACC_KERNELS, OACC_PARALLEL,
	OACC_DATA.
	(gimplify_omp_target_update): Handle OACC_ENTER_DATA,
	OACC_EXIT_DATA, OACC_UPDATE.
	(gimplify_expr): Handle OACC_LOOP, OACC_CACHE, OACC_HOST_DATA,
	OACC_DECLARE, OACC_KERNELS, OACC_PARALLEL, OACC_DATA,
	OACC_ENTER_DATA, OACC_EXIT_DATA, OACC_UPDATE.
	(gimplify_body): Consider flag_openacc next to flag_openmp.
	* lto-streamer-out.c: Include "gomp-constants.h".
	* omp-builtins.def (BUILT_IN_ACC_GET_DEVICE_TYPE)
	(BUILT_IN_GOACC_DATA_START, BUILT_IN_GOACC_DATA_END)
	(BUILT_IN_GOACC_ENTER_EXIT_DATA, BUILT_IN_GOACC_PARALLEL)
	(BUILT_IN_GOACC_UPDATE, BUILT_IN_GOACC_WAIT)
	(BUILT_IN_GOACC_GET_THREAD_NUM, BUILT_IN_GOACC_GET_NUM_THREADS)
	(BUILT_IN_ACC_ON_DEVICE): New builtins.
	* omp-low.c: Include "gomp-constants.h".
	Update comments for OpenACC changes.
	(struct omp_context): Add reduction_map, gwv_below, gwv_this
	members.
	(extract_omp_for_data, use_pointer_for_field, install_var_field)
	(new_omp_context, delete_omp_context, scan_sharing_clauses)
	(create_omp_child_function, scan_omp_for, scan_omp_target)
	(check_omp_nesting_restrictions, lower_reduction_clauses)
	(build_omp_regions_1, diagnose_sb_0, make_gimple_omp_edges):
	Update for OpenACC changes.
	(scan_sharing_clauses): Handle OMP_CLAUSE_NUM_GANGS:
	OMP_CLAUSE_NUM_WORKERS: OMP_CLAUSE_VECTOR_LENGTH,
	OMP_CLAUSE_ASYNC, OMP_CLAUSE_WAIT, OMP_CLAUSE_GANG,
	OMP_CLAUSE_WORKER, OMP_CLAUSE_VECTOR, OMP_CLAUSE_DEVICE_RESIDENT,
	OMP_CLAUSE_USE_DEVICE, OMP_CLAUSE__CACHE_, OMP_CLAUSE_INDEPENDENT,
	OMP_CLAUSE_AUTO, OMP_CLAUSE_SEQ.  Use GOMP_MAP_* instead of
	OMP_CLAUSE_MAP_*.
	(expand_omp_for_static_nochunk, expand_omp_for_static_chunk):
	Handle GF_OMP_FOR_KIND_OACC_LOOP.
	(expand_omp_target, lower_omp_target): Handle
	GF_OMP_TARGET_KIND_OACC_PARALLEL, GF_OMP_TARGET_KIND_OACC_KERNELS,
	GF_OMP_TARGET_KIND_OACC_UPDATE,
	GF_OMP_TARGET_KIND_OACC_ENTER_EXIT_DATA,
	GF_OMP_TARGET_KIND_OACC_DATA.
	(pass_expand_omp::execute, execute_lower_omp)
	(pass_diagnose_omp_blocks::gate): Consider flag_openacc next to
	flag_openmp.
	(offload_symbol_decl): New variable.
	(oacc_get_reduction_array_id, oacc_max_threads)
	(get_offload_symbol_decl, get_base_type, lookup_oacc_reduction)
	(maybe_lookup_oacc_reduction, enclosing_target_ctx)
	(oacc_loop_or_target_p, oacc_lower_reduction_var_helper)
	(oacc_gimple_assign, oacc_initialize_reduction_data)
	(oacc_finalize_reduction_data, oacc_process_reduction_data): New
	functions.
	(is_targetreg_ctx): Remove function.
	* tree-core.h (enum omp_clause_code): Add OMP_CLAUSE__CACHE_,
	OMP_CLAUSE_DEVICE_RESIDENT, OMP_CLAUSE_USE_DEVICE,
	OMP_CLAUSE_GANG, OMP_CLAUSE_ASYNC, OMP_CLAUSE_WAIT,
	OMP_CLAUSE_AUTO, OMP_CLAUSE_SEQ, OMP_CLAUSE_INDEPENDENT,
	OMP_CLAUSE_WORKER, OMP_CLAUSE_VECTOR, OMP_CLAUSE_NUM_GANGS,
	OMP_CLAUSE_NUM_WORKERS, OMP_CLAUSE_VECTOR_LENGTH.
	* tree.c (omp_clause_code_name, walk_tree_1): Update accordingly.
	* tree.h (OMP_CLAUSE_GANG_EXPR, OMP_CLAUSE_GANG_STATIC_EXPR)
	(OMP_CLAUSE_ASYNC_EXPR, OMP_CLAUSE_WAIT_EXPR)
	(OMP_CLAUSE_VECTOR_EXPR, OMP_CLAUSE_WORKER_EXPR)
	(OMP_CLAUSE_NUM_GANGS_EXPR, OMP_CLAUSE_NUM_WORKERS_EXPR)
	(OMP_CLAUSE_VECTOR_LENGTH_EXPR): New macros.
	* tree-core.h: Update comments for OpenACC changes.
	(enum omp_clause_map_kind): Remove.
	(struct tree_omp_clause): Change type of map_kind member from enum
	omp_clause_map_kind to unsigned char.
	* tree-inline.c: Update comments for OpenACC changes.
	* tree-nested.c: Likewise.  Include "gomp-constants.h".
	(convert_nonlocal_reference_stmt, convert_local_reference_stmt)
	(convert_tramp_reference_stmt, convert_gimple_call): Update for
	OpenACC changes.  Use GOMP_MAP_* instead of OMP_CLAUSE_MAP_*.  Use
	OMP_CLAUSE_SET_MAP_KIND.
	* tree-pretty-print.c: Include "gomp-constants.h".
	(dump_omp_clause): Handle OMP_CLAUSE_DEVICE_RESIDENT,
	OMP_CLAUSE_USE_DEVICE, OMP_CLAUSE__CACHE_, OMP_CLAUSE_GANG,
	OMP_CLAUSE_ASYNC, OMP_CLAUSE_AUTO, OMP_CLAUSE_SEQ,
	OMP_CLAUSE_WAIT, OMP_CLAUSE_WORKER, OMP_CLAUSE_VECTOR,
	OMP_CLAUSE_NUM_GANGS, OMP_CLAUSE_NUM_WORKERS,
	OMP_CLAUSE_VECTOR_LENGTH, OMP_CLAUSE_INDEPENDENT.  Use GOMP_MAP_*
	instead of OMP_CLAUSE_MAP_*.
	(dump_generic_node): Handle OACC_PARALLEL, OACC_KERNELS,
	OACC_DATA, OACC_HOST_DATA, OACC_DECLARE, OACC_UPDATE,
	OACC_ENTER_DATA, OACC_EXIT_DATA, OACC_CACHE, OACC_LOOP.
	* tree-streamer-in.c: Include "gomp-constants.h".
	(unpack_ts_omp_clause_value_fields) Use GOMP_MAP_* instead of
	OMP_CLAUSE_MAP_*.  Use OMP_CLAUSE_SET_MAP_KIND.
	* tree-streamer-out.c: Include "gomp-constants.h".
	(pack_ts_omp_clause_value_fields): Use GOMP_MAP_* instead of
	OMP_CLAUSE_MAP_*.
	* tree.def (OACC_PARALLEL, OACC_KERNELS, OACC_DATA)
	(OACC_HOST_DATA, OACC_LOOP, OACC_CACHE, OACC_DECLARE)
	(OACC_ENTER_DATA, OACC_EXIT_DATA, OACC_UPDATE): New tree codes.
	* tree.c (omp_clause_num_ops): Update accordingly.
	* tree.h (OMP_BODY, OMP_CLAUSES, OMP_LOOP_CHECK, OMP_CLAUSE_SIZE):
	Likewise.
	(OACC_PARALLEL_BODY, OACC_PARALLEL_CLAUSES, OACC_KERNELS_BODY)
	(OACC_KERNELS_CLAUSES, OACC_DATA_BODY, OACC_DATA_CLAUSES)
	(OACC_HOST_DATA_BODY, OACC_HOST_DATA_CLAUSES, OACC_CACHE_CLAUSES)
	(OACC_DECLARE_CLAUSES, OACC_ENTER_DATA_CLAUSES)
	(OACC_EXIT_DATA_CLAUSES, OACC_UPDATE_CLAUSES)
	(OACC_KERNELS_COMBINED, OACC_PARALLEL_COMBINED): New macros.
	* tree.h (OMP_CLAUSE_MAP_KIND): Cast it to enum gomp_map_kind.
	(OMP_CLAUSE_SET_MAP_KIND): New macro.
	* varpool.c (varpool_node::get_create): Consider flag_openacc next
	to flag_openmp.
	* config/i386/intelmic-offload.h: New file.
	* config/nvptx/offload.h: Likewise.
	gcc/ada/
	* gcc-interface/utils.c (DEF_FUNCTION_TYPE_VAR_8)
	(DEF_FUNCTION_TYPE_VAR_12): New macros.
	gcc/c-family/
	* c.opt (fopenacc): New option.
	* c-cppbuiltin.c (c_cpp_builtins): Conditionally define _OPENACC.
	* c-common.c (DEF_FUNCTION_TYPE_VAR_8, DEF_FUNCTION_TYPE_VAR_12):
	New macros.
	* c-common.h (c_finish_oacc_wait): New prototype.
	* c-omp.c: Include "omp-low.h" and "gomp-constants.h".
	(c_finish_oacc_wait): New function.
	* c-pragma.c (oacc_pragmas): New variable.
	(c_pp_lookup_pragma, init_pragma): Handle it.
	* c-pragma.h (enum pragma_kind): Add PRAGMA_OACC_CACHE,
	PRAGMA_OACC_DATA, PRAGMA_OACC_ENTER_DATA, PRAGMA_OACC_EXIT_DATA,
	PRAGMA_OACC_KERNELS, PRAGMA_OACC_LOOP, PRAGMA_OACC_PARALLEL,
	PRAGMA_OACC_UPDATE, PRAGMA_OACC_WAIT.
	(enum pragma_omp_clause): Add PRAGMA_OACC_CLAUSE_ASYNC,
	PRAGMA_OACC_CLAUSE_AUTO, PRAGMA_OACC_CLAUSE_COLLAPSE,
	PRAGMA_OACC_CLAUSE_COPY, PRAGMA_OACC_CLAUSE_COPYIN,
	PRAGMA_OACC_CLAUSE_COPYOUT, PRAGMA_OACC_CLAUSE_CREATE,
	PRAGMA_OACC_CLAUSE_DELETE, PRAGMA_OACC_CLAUSE_DEVICE,
	PRAGMA_OACC_CLAUSE_DEVICEPTR, PRAGMA_OACC_CLAUSE_FIRSTPRIVATE,
	PRAGMA_OACC_CLAUSE_GANG, PRAGMA_OACC_CLAUSE_HOST,
	PRAGMA_OACC_CLAUSE_IF, PRAGMA_OACC_CLAUSE_NUM_GANGS,
	PRAGMA_OACC_CLAUSE_NUM_WORKERS, PRAGMA_OACC_CLAUSE_PRESENT,
	PRAGMA_OACC_CLAUSE_PRESENT_OR_COPY,
	PRAGMA_OACC_CLAUSE_PRESENT_OR_COPYIN,
	PRAGMA_OACC_CLAUSE_PRESENT_OR_COPYOUT,
	PRAGMA_OACC_CLAUSE_PRESENT_OR_CREATE, PRAGMA_OACC_CLAUSE_PRIVATE,
	PRAGMA_OACC_CLAUSE_REDUCTION, PRAGMA_OACC_CLAUSE_SELF,
	PRAGMA_OACC_CLAUSE_SEQ, PRAGMA_OACC_CLAUSE_VECTOR,
	PRAGMA_OACC_CLAUSE_VECTOR_LENGTH, PRAGMA_OACC_CLAUSE_WAIT,
	PRAGMA_OACC_CLAUSE_WORKER.
	gcc/c/
	* c-parser.c: Include "gomp-constants.h".
	(c_parser_omp_clause_map): Use enum gomp_map_kind instead of enum
	omp_clause_map_kind.  Use GOMP_MAP_* instead of OMP_CLAUSE_MAP_*.
	Use OMP_CLAUSE_SET_MAP_KIND.
	(c_parser_pragma): Handle PRAGMA_OACC_ENTER_DATA,
	PRAGMA_OACC_EXIT_DATA, PRAGMA_OACC_UPDATE.
	(c_parser_omp_construct): Handle PRAGMA_OACC_CACHE,
	PRAGMA_OACC_DATA, PRAGMA_OACC_KERNELS, PRAGMA_OACC_LOOP,
	PRAGMA_OACC_PARALLEL, PRAGMA_OACC_WAIT.
	(c_parser_omp_clause_name): Handle "auto", "async", "copy",
	"copyout", "create", "delete", "deviceptr", "gang", "host",
	"num_gangs", "num_workers", "present", "present_or_copy", "pcopy",
	"present_or_copyin", "pcopyin", "present_or_copyout", "pcopyout",
	"present_or_create", "pcreate", "seq", "self", "vector",
	"vector_length", "wait", "worker".
	(OACC_DATA_CLAUSE_MASK, OACC_KERNELS_CLAUSE_MASK)
	(OACC_ENTER_DATA_CLAUSE_MASK, OACC_EXIT_DATA_CLAUSE_MASK)
	(OACC_LOOP_CLAUSE_MASK, OACC_PARALLEL_CLAUSE_MASK)
	(OACC_UPDATE_CLAUSE_MASK, OACC_WAIT_CLAUSE_MASK): New macros.
	(c_parser_omp_variable_list): Handle OMP_CLAUSE__CACHE_.
	(c_parser_oacc_wait_list, c_parser_oacc_data_clause)
	(c_parser_oacc_data_clause_deviceptr)
	(c_parser_omp_clause_num_gangs, c_parser_omp_clause_num_workers)
	(c_parser_oacc_clause_async, c_parser_oacc_clause_wait)
	(c_parser_omp_clause_vector_length, c_parser_oacc_all_clauses)
	(c_parser_oacc_cache, c_parser_oacc_data, c_parser_oacc_kernels)
	(c_parser_oacc_enter_exit_data, c_parser_oacc_loop)
	(c_parser_oacc_parallel, c_parser_oacc_update)
	(c_parser_oacc_wait): New functions.
	* c-tree.h (c_finish_oacc_parallel, c_finish_oacc_kernels)
	(c_finish_oacc_data): New prototypes.
	* c-typeck.c: Include "gomp-constants.h".
	(handle_omp_array_sections): Handle GOMP_MAP_FORCE_DEVICEPTR.  Use
	GOMP_MAP_* instead of OMP_CLAUSE_MAP_*.  Use
	OMP_CLAUSE_SET_MAP_KIND.
	(c_finish_oacc_parallel, c_finish_oacc_kernels)
	(c_finish_oacc_data): New functions.
	(c_finish_omp_clauses): Handle OMP_CLAUSE__CACHE_,
	OMP_CLAUSE_NUM_GANGS, OMP_CLAUSE_NUM_WORKERS,
	OMP_CLAUSE_VECTOR_LENGTH, OMP_CLAUSE_ASYNC, OMP_CLAUSE_WAIT,
	OMP_CLAUSE_AUTO, OMP_CLAUSE_SEQ, OMP_CLAUSE_GANG,
	OMP_CLAUSE_WORKER, OMP_CLAUSE_VECTOR, and OMP_CLAUSE_MAP's
	GOMP_MAP_FORCE_DEVICEPTR.
	gcc/cp/
	* parser.c: Include "gomp-constants.h".
	(cp_parser_omp_clause_map): Use enum gomp_map_kind instead of enum
	omp_clause_map_kind.  Use GOMP_MAP_* instead of OMP_CLAUSE_MAP_*.
	Use OMP_CLAUSE_SET_MAP_KIND.
	(cp_parser_omp_construct, cp_parser_pragma): Handle
	PRAGMA_OACC_CACHE, PRAGMA_OACC_DATA, PRAGMA_OACC_ENTER_DATA,
	PRAGMA_OACC_EXIT_DATA, PRAGMA_OACC_KERNELS, PRAGMA_OACC_PARALLEL,
	PRAGMA_OACC_LOOP, PRAGMA_OACC_UPDATE, PRAGMA_OACC_WAIT.
	(cp_parser_omp_clause_name): Handle "async", "copy", "copyout",
	"create", "delete", "deviceptr", "host", "num_gangs",
	"num_workers", "present", "present_or_copy", "pcopy",
	"present_or_copyin", "pcopyin", "present_or_copyout", "pcopyout",
	"present_or_create", "pcreate", "vector_length", "wait".
	(OACC_DATA_CLAUSE_MASK, OACC_ENTER_DATA_CLAUSE_MASK)
	(OACC_EXIT_DATA_CLAUSE_MASK, OACC_KERNELS_CLAUSE_MASK)
	(OACC_LOOP_CLAUSE_MASK, OACC_PARALLEL_CLAUSE_MASK)
	(OACC_UPDATE_CLAUSE_MASK, OACC_WAIT_CLAUSE_MASK): New macros.
	(cp_parser_omp_var_list_no_open): Handle OMP_CLAUSE__CACHE_.
	(cp_parser_oacc_data_clause, cp_parser_oacc_data_clause_deviceptr)
	(cp_parser_oacc_clause_vector_length, cp_parser_oacc_wait_list)
	(cp_parser_oacc_clause_wait, cp_parser_omp_clause_num_gangs)
	(cp_parser_omp_clause_num_workers, cp_parser_oacc_clause_async)
	(cp_parser_oacc_all_clauses, cp_parser_oacc_cache)
	(cp_parser_oacc_data, cp_parser_oacc_enter_exit_data)
	(cp_parser_oacc_kernels, cp_parser_oacc_loop)
	(cp_parser_oacc_parallel, cp_parser_oacc_update)
	(cp_parser_oacc_wait): New functions.
	* cp-tree.h (finish_oacc_data, finish_oacc_kernels)
	(finish_oacc_parallel): New prototypes.
	* semantics.c: Include "gomp-constants.h".
	(handle_omp_array_sections): Handle GOMP_MAP_FORCE_DEVICEPTR.  Use
	GOMP_MAP_* instead of OMP_CLAUSE_MAP_*.  Use
	OMP_CLAUSE_SET_MAP_KIND.
	(finish_omp_clauses): Handle OMP_CLAUSE_ASYNC,
	OMP_CLAUSE_VECTOR_LENGTH, OMP_CLAUSE_WAIT, OMP_CLAUSE__CACHE_.
	Use GOMP_MAP_* instead of OMP_CLAUSE_MAP_*.
	(finish_oacc_data, finish_oacc_kernels, finish_oacc_parallel): New
	functions.
	gcc/fortran/
	* lang.opt (fopenacc): New option.
	* cpp.c (cpp_define_builtins): Conditionally define _OPENACC.
	* dump-parse-tree.c (show_omp_node): Split part of it into...
	(show_omp_clauses): ... this new function.
	(show_omp_node, show_code_node): Handle EXEC_OACC_PARALLEL_LOOP,
	EXEC_OACC_PARALLEL, EXEC_OACC_KERNELS_LOOP, EXEC_OACC_KERNELS,
	EXEC_OACC_DATA, EXEC_OACC_HOST_DATA, EXEC_OACC_LOOP,
	EXEC_OACC_UPDATE, EXEC_OACC_WAIT, EXEC_OACC_CACHE,
	EXEC_OACC_ENTER_DATA, EXEC_OACC_EXIT_DATA.
	(show_namespace): Update for OpenACC.
	* f95-lang.c (DEF_FUNCTION_TYPE_VAR_2, DEF_FUNCTION_TYPE_VAR_8)
	(DEF_FUNCTION_TYPE_VAR_12, DEF_GOACC_BUILTIN)
	(DEF_GOACC_BUILTIN_COMPILER): New macros.
	* types.def (BT_FN_VOID_INT_INT_VAR)
	(BT_FN_VOID_INT_PTR_SIZE_PTR_PTR_PTR_INT_INT_VAR)
	(BT_FN_VOID_INT_OMPFN_PTR_SIZE_PTR_PTR_PTR_INT_INT_INT_INT_INT_VAR):
	New function types.
	* gfortran.h (gfc_statement): Add ST_OACC_PARALLEL_LOOP,
	ST_OACC_END_PARALLEL_LOOP, ST_OACC_PARALLEL, ST_OACC_END_PARALLEL,
	ST_OACC_KERNELS, ST_OACC_END_KERNELS, ST_OACC_DATA,
	ST_OACC_END_DATA, ST_OACC_HOST_DATA, ST_OACC_END_HOST_DATA,
	ST_OACC_LOOP, ST_OACC_END_LOOP, ST_OACC_DECLARE, ST_OACC_UPDATE,
	ST_OACC_WAIT, ST_OACC_CACHE, ST_OACC_KERNELS_LOOP,
	ST_OACC_END_KERNELS_LOOP, ST_OACC_ENTER_DATA, ST_OACC_EXIT_DATA,
	ST_OACC_ROUTINE.
	(struct gfc_expr_list): New data type.
	(gfc_get_expr_list): New macro.
	(gfc_omp_map_op): Add OMP_MAP_FORCE_ALLOC, OMP_MAP_FORCE_DEALLOC,
	OMP_MAP_FORCE_TO, OMP_MAP_FORCE_FROM, OMP_MAP_FORCE_TOFROM,
	OMP_MAP_FORCE_PRESENT, OMP_MAP_FORCE_DEVICEPTR.
	(OMP_LIST_FIRST, OMP_LIST_DEVICE_RESIDENT, OMP_LIST_USE_DEVICE)
	(OMP_LIST_CACHE): New enumerators.
	(struct gfc_omp_clauses): Add async_expr, gang_expr, worker_expr,
	vector_expr, num_gangs_expr, num_workers_expr, vector_length_expr,
	wait_list, tile_list, async, gang, worker, vector, seq,
	independent, wait, par_auto, gang_static, and loc members.
	(struct gfc_namespace): Add oacc_declare_clauses member.
	(gfc_exec_op): Add EXEC_OACC_KERNELS_LOOP,
	EXEC_OACC_PARALLEL_LOOP, EXEC_OACC_PARALLEL, EXEC_OACC_KERNELS,
	EXEC_OACC_DATA, EXEC_OACC_HOST_DATA, EXEC_OACC_LOOP,
	EXEC_OACC_UPDATE, EXEC_OACC_WAIT, EXEC_OACC_CACHE,
	EXEC_OACC_ENTER_DATA, EXEC_OACC_EXIT_DATA.
	(gfc_free_expr_list, gfc_resolve_oacc_directive)
	(gfc_resolve_oacc_declare, gfc_resolve_oacc_parallel_loop_blocks)
	(gfc_resolve_oacc_blocks): New prototypes.
	* match.c (match_exit_cycle): Handle EXEC_OACC_LOOP and
	EXEC_OACC_PARALLEL_LOOP.
	* match.h (gfc_match_oacc_cache, gfc_match_oacc_wait)
	(gfc_match_oacc_update, gfc_match_oacc_declare)
	(gfc_match_oacc_loop, gfc_match_oacc_host_data)
	(gfc_match_oacc_data, gfc_match_oacc_kernels)
	(gfc_match_oacc_kernels_loop, gfc_match_oacc_parallel)
	(gfc_match_oacc_parallel_loop, gfc_match_oacc_enter_data)
	(gfc_match_oacc_exit_data, gfc_match_oacc_routine): New
	prototypes.
	* openmp.c: Include "diagnostic.h" and "gomp-constants.h".
	(gfc_free_omp_clauses): Update for members added to struct
	gfc_omp_clauses.
	(gfc_match_omp_clauses): Change mask paramter to uint64_t.  Add
	openacc parameter.
	(resolve_omp_clauses): Add openacc parameter.  Update for OpenACC.
	(struct fortran_omp_context): Add is_openmp member.
	(gfc_resolve_omp_parallel_blocks): Initialize it.
	(gfc_resolve_do_iterator): Update for OpenACC.
	(gfc_resolve_omp_directive): Call
	resolve_omp_directive_inside_oacc_region.
	(OMP_CLAUSE_PRIVATE, OMP_CLAUSE_FIRSTPRIVATE)
	(OMP_CLAUSE_LASTPRIVATE, OMP_CLAUSE_COPYPRIVATE)
	(OMP_CLAUSE_SHARED, OMP_CLAUSE_COPYIN, OMP_CLAUSE_REDUCTION)
	(OMP_CLAUSE_IF, OMP_CLAUSE_NUM_THREADS, OMP_CLAUSE_SCHEDULE)
	(OMP_CLAUSE_DEFAULT, OMP_CLAUSE_ORDERED, OMP_CLAUSE_COLLAPSE)
	(OMP_CLAUSE_UNTIED, OMP_CLAUSE_FINAL, OMP_CLAUSE_MERGEABLE)
	(OMP_CLAUSE_ALIGNED, OMP_CLAUSE_DEPEND, OMP_CLAUSE_INBRANCH)
	(OMP_CLAUSE_LINEAR, OMP_CLAUSE_NOTINBRANCH, OMP_CLAUSE_PROC_BIND)
	(OMP_CLAUSE_SAFELEN, OMP_CLAUSE_SIMDLEN, OMP_CLAUSE_UNIFORM)
	(OMP_CLAUSE_DEVICE, OMP_CLAUSE_MAP, OMP_CLAUSE_TO)
	(OMP_CLAUSE_FROM, OMP_CLAUSE_NUM_TEAMS, OMP_CLAUSE_THREAD_LIMIT)
	(OMP_CLAUSE_DIST_SCHEDULE): Use uint64_t.
	(OMP_CLAUSE_ASYNC, OMP_CLAUSE_NUM_GANGS, OMP_CLAUSE_NUM_WORKERS)
	(OMP_CLAUSE_VECTOR_LENGTH, OMP_CLAUSE_COPY, OMP_CLAUSE_COPYOUT)
	(OMP_CLAUSE_CREATE, OMP_CLAUSE_PRESENT)
	(OMP_CLAUSE_PRESENT_OR_COPY, OMP_CLAUSE_PRESENT_OR_COPYIN)
	(OMP_CLAUSE_PRESENT_OR_COPYOUT, OMP_CLAUSE_PRESENT_OR_CREATE)
	(OMP_CLAUSE_DEVICEPTR, OMP_CLAUSE_GANG, OMP_CLAUSE_WORKER)
	(OMP_CLAUSE_VECTOR, OMP_CLAUSE_SEQ, OMP_CLAUSE_INDEPENDENT)
	(OMP_CLAUSE_USE_DEVICE, OMP_CLAUSE_DEVICE_RESIDENT)
	(OMP_CLAUSE_HOST_SELF, OMP_CLAUSE_OACC_DEVICE, OMP_CLAUSE_WAIT)
	(OMP_CLAUSE_DELETE, OMP_CLAUSE_AUTO, OMP_CLAUSE_TILE): New macros.
	(gfc_match_omp_clauses): Handle those.
	(OACC_PARALLEL_CLAUSES, OACC_KERNELS_CLAUSES, OACC_DATA_CLAUSES)
	(OACC_LOOP_CLAUSES, OACC_PARALLEL_LOOP_CLAUSES)
	(OACC_KERNELS_LOOP_CLAUSES, OACC_HOST_DATA_CLAUSES)
	(OACC_DECLARE_CLAUSES, OACC_UPDATE_CLAUSES)
	(OACC_ENTER_DATA_CLAUSES, OACC_EXIT_DATA_CLAUSES)
	(OACC_WAIT_CLAUSES): New macros.
	(gfc_free_expr_list, match_oacc_expr_list, match_oacc_clause_gang)
	(gfc_match_omp_map_clause, gfc_match_oacc_parallel_loop)
	(gfc_match_oacc_parallel, gfc_match_oacc_kernels_loop)
	(gfc_match_oacc_kernels, gfc_match_oacc_data)
	(gfc_match_oacc_host_data, gfc_match_oacc_loop)
	(gfc_match_oacc_declare, gfc_match_oacc_update)
	(gfc_match_oacc_enter_data, gfc_match_oacc_exit_data)
	(gfc_match_oacc_wait, gfc_match_oacc_cache)
	(gfc_match_oacc_routine, oacc_is_loop)
	(resolve_oacc_scalar_int_expr, resolve_oacc_positive_int_expr)
	(check_symbol_not_pointer, check_array_not_assumed)
	(resolve_oacc_data_clauses, resolve_oacc_deviceptr_clause)
	(oacc_compatible_clauses, oacc_is_parallel, oacc_is_kernels)
	(omp_code_to_statement, oacc_code_to_statement)
	(resolve_oacc_directive_inside_omp_region)
	(resolve_omp_directive_inside_oacc_region)
	(resolve_oacc_nested_loops, resolve_oacc_params_in_parallel)
	(resolve_oacc_loop_blocks, gfc_resolve_oacc_blocks)
	(resolve_oacc_loop, resolve_oacc_cache, gfc_resolve_oacc_declare)
	(gfc_resolve_oacc_directive): New functions.
	* parse.c (next_free): Update for OpenACC.  Move some code into...
	(verify_token_free): ... this new function.
	(next_fixed): Update for OpenACC.  Move some code into...
	(verify_token_fixed): ... this new function.
	(case_executable): Add ST_OACC_UPDATE, ST_OACC_WAIT,
	ST_OACC_CACHE, ST_OACC_ENTER_DATA, and ST_OACC_EXIT_DATA.
	(case_exec_markers): Add ST_OACC_PARALLEL_LOOP, ST_OACC_PARALLEL,
	ST_OACC_KERNELS, ST_OACC_DATA, ST_OACC_HOST_DATA, ST_OACC_LOOP,
	ST_OACC_KERNELS_LOOP.
	(case_decl): Add ST_OACC_ROUTINE.
	(push_state, parse_critical_block, parse_progunit): Update for
	OpenACC.
	(gfc_ascii_statement): Handle ST_OACC_PARALLEL_LOOP,
	ST_OACC_END_PARALLEL_LOOP, ST_OACC_PARALLEL, ST_OACC_END_PARALLEL,
	ST_OACC_KERNELS, ST_OACC_END_KERNELS, ST_OACC_KERNELS_LOOP,
	ST_OACC_END_KERNELS_LOOP, ST_OACC_DATA, ST_OACC_END_DATA,
	ST_OACC_HOST_DATA, ST_OACC_END_HOST_DATA, ST_OACC_LOOP,
	ST_OACC_END_LOOP, ST_OACC_DECLARE, ST_OACC_UPDATE, ST_OACC_WAIT,
	ST_OACC_CACHE, ST_OACC_ENTER_DATA, ST_OACC_EXIT_DATA,
	ST_OACC_ROUTINE.
	(verify_st_order, parse_spec): Handle ST_OACC_DECLARE.
	(parse_executable): Handle ST_OACC_PARALLEL_LOOP,
	ST_OACC_KERNELS_LOOP, ST_OACC_LOOP, ST_OACC_PARALLEL,
	ST_OACC_KERNELS, ST_OACC_DATA, ST_OACC_HOST_DATA.
	(decode_oacc_directive, parse_oacc_structured_block)
	(parse_oacc_loop, is_oacc): New functions.
	* parse.h (struct gfc_state_data): Add oacc_declare_clauses
	member.
	(is_oacc): New prototype.
	* resolve.c (gfc_resolve_blocks, gfc_resolve_code): Handle
	EXEC_OACC_PARALLEL_LOOP, EXEC_OACC_PARALLEL,
	EXEC_OACC_KERNELS_LOOP, EXEC_OACC_KERNELS, EXEC_OACC_DATA,
	EXEC_OACC_HOST_DATA, EXEC_OACC_LOOP, EXEC_OACC_UPDATE,
	EXEC_OACC_WAIT, EXEC_OACC_CACHE, EXEC_OACC_ENTER_DATA,
	EXEC_OACC_EXIT_DATA.
	(resolve_codes): Call gfc_resolve_oacc_declare.
	* scanner.c (openacc_flag, openacc_locus): New variables.
	(skip_free_comments): Update for OpenACC.  Move some code into...
	(skip_omp_attribute): ... this new function.
	(skip_oacc_attribute): New function.
	(skip_fixed_comments, gfc_next_char_literal): Update for OpenACC.
	* st.c (gfc_free_statement): Handle EXEC_OACC_PARALLEL_LOOP,
	EXEC_OACC_PARALLEL, EXEC_OACC_KERNELS_LOOP, EXEC_OACC_KERNELS,
	EXEC_OACC_DATA, EXEC_OACC_HOST_DATA, EXEC_OACC_LOOP,
	EXEC_OACC_UPDATE, EXEC_OACC_WAIT, EXEC_OACC_CACHE,
	EXEC_OACC_ENTER_DATA, EXEC_OACC_EXIT_DATA.
	* trans-decl.c (gfc_generate_function_code): Update for OpenACC.
	* trans-openmp.c: Include "gomp-constants.h".
	(gfc_omp_finish_clause, gfc_trans_omp_clauses): Use GOMP_MAP_*
	instead of OMP_CLAUSE_MAP_*.  Use OMP_CLAUSE_SET_MAP_KIND.
	(gfc_trans_omp_clauses): Handle OMP_LIST_USE_DEVICE,
	OMP_LIST_DEVICE_RESIDENT, OMP_LIST_CACHE, and OMP_MAP_FORCE_ALLOC,
	OMP_MAP_FORCE_DEALLOC, OMP_MAP_FORCE_TO, OMP_MAP_FORCE_FROM,
	OMP_MAP_FORCE_TOFROM, OMP_MAP_FORCE_PRESENT,
	OMP_MAP_FORCE_DEVICEPTR, and gfc_omp_clauses' async, seq,
	independent, wait_list, num_gangs_expr, num_workers_expr,
	vector_length_expr, vector, vector_expr, worker, worker_expr,
	gang, gang_expr members.
	(gfc_trans_omp_do): Handle EXEC_OACC_LOOP.
	(gfc_convert_expr_to_tree, gfc_trans_oacc_construct)
	(gfc_trans_oacc_executable_directive)
	(gfc_trans_oacc_wait_directive, gfc_trans_oacc_combined_directive)
	(gfc_trans_oacc_declare, gfc_trans_oacc_directive): New functions.
	* trans-stmt.c (gfc_trans_block_construct): Update for OpenACC.
	* trans-stmt.h (gfc_trans_oacc_directive, gfc_trans_oacc_declare):
	New prototypes.
	* trans.c (tranc_code): Handle EXEC_OACC_CACHE, EXEC_OACC_WAIT,
	EXEC_OACC_UPDATE, EXEC_OACC_LOOP, EXEC_OACC_HOST_DATA,
	EXEC_OACC_DATA, EXEC_OACC_KERNELS, EXEC_OACC_KERNELS_LOOP,
	EXEC_OACC_PARALLEL, EXEC_OACC_PARALLEL_LOOP, EXEC_OACC_ENTER_DATA,
	EXEC_OACC_EXIT_DATA.
	* gfortran.texi: Update for OpenACC.
	* intrinsic.texi: Likewise.
	* invoke.texi: Likewise.
	gcc/lto/
	* lto-lang.c (DEF_FUNCTION_TYPE_VAR_8, DEF_FUNCTION_TYPE_VAR_12):
	New macros.
	* lto.c: Include "gomp-constants.h".
	gcc/testsuite/
	* lib/target-supports.exp (check_effective_target_fopenacc): New
	procedure.
	* g++.dg/goacc-gomp/goacc-gomp.exp: New file.
	* g++.dg/goacc/goacc.exp: Likewise.
	* gcc.dg/goacc-gomp/goacc-gomp.exp: Likewise.
	* gcc.dg/goacc/goacc.exp: Likewise.
	* gfortran.dg/goacc/goacc.exp: Likewise.
	* c-c++-common/cpp/openacc-define-1.c: New file.
	* c-c++-common/cpp/openacc-define-2.c: Likewise.
	* c-c++-common/cpp/openacc-define-3.c: Likewise.
	* c-c++-common/goacc-gomp/nesting-1.c: Likewise.
	* c-c++-common/goacc-gomp/nesting-fail-1.c: Likewise.
	* c-c++-common/goacc/acc_on_device-2-off.c: Likewise.
	* c-c++-common/goacc/acc_on_device-2.c: Likewise.
	* c-c++-common/goacc/asyncwait-1.c: Likewise.
	* c-c++-common/goacc/cache-1.c: Likewise.
	* c-c++-common/goacc/clauses-fail.c: Likewise.
	* c-c++-common/goacc/collapse-1.c: Likewise.
	* c-c++-common/goacc/data-1.c: Likewise.
	* c-c++-common/goacc/data-2.c: Likewise.
	* c-c++-common/goacc/data-clause-duplicate-1.c: Likewise.
	* c-c++-common/goacc/deviceptr-1.c: Likewise.
	* c-c++-common/goacc/deviceptr-2.c: Likewise.
	* c-c++-common/goacc/deviceptr-3.c: Likewise.
	* c-c++-common/goacc/if-clause-1.c: Likewise.
	* c-c++-common/goacc/if-clause-2.c: Likewise.
	* c-c++-common/goacc/kernels-1.c: Likewise.
	* c-c++-common/goacc/loop-1.c: Likewise.
	* c-c++-common/goacc/loop-private-1.c: Likewise.
	* c-c++-common/goacc/nesting-1.c: Likewise.
	* c-c++-common/goacc/nesting-data-1.c: Likewise.
	* c-c++-common/goacc/nesting-fail-1.c: Likewise.
	* c-c++-common/goacc/parallel-1.c: Likewise.
	* c-c++-common/goacc/pcopy.c: Likewise.
	* c-c++-common/goacc/pcopyin.c: Likewise.
	* c-c++-common/goacc/pcopyout.c: Likewise.
	* c-c++-common/goacc/pcreate.c: Likewise.
	* c-c++-common/goacc/pragma_context.c: Likewise.
	* c-c++-common/goacc/present-1.c: Likewise.
	* c-c++-common/goacc/reduction-1.c: Likewise.
	* c-c++-common/goacc/reduction-2.c: Likewise.
	* c-c++-common/goacc/reduction-3.c: Likewise.
	* c-c++-common/goacc/reduction-4.c: Likewise.
	* c-c++-common/goacc/sb-1.c: Likewise.
	* c-c++-common/goacc/sb-2.c: Likewise.
	* c-c++-common/goacc/sb-3.c: Likewise.
	* c-c++-common/goacc/update-1.c: Likewise.
	* gcc.dg/goacc/acc_on_device-1.c: Likewise.
	* gfortran.dg/goacc/acc_on_device-1.f95: Likewise.
	* gfortran.dg/goacc/acc_on_device-2-off.f95: Likewise.
	* gfortran.dg/goacc/acc_on_device-2.f95: Likewise.
	* gfortran.dg/goacc/assumed.f95: Likewise.
	* gfortran.dg/goacc/asyncwait-1.f95: Likewise.
	* gfortran.dg/goacc/asyncwait-2.f95: Likewise.
	* gfortran.dg/goacc/asyncwait-3.f95: Likewise.
	* gfortran.dg/goacc/asyncwait-4.f95: Likewise.
	* gfortran.dg/goacc/branch.f95: Likewise.
	* gfortran.dg/goacc/cache-1.f95: Likewise.
	* gfortran.dg/goacc/coarray.f95: Likewise.
	* gfortran.dg/goacc/continuation-free-form.f95: Likewise.
	* gfortran.dg/goacc/cray.f95: Likewise.
	* gfortran.dg/goacc/critical.f95: Likewise.
	* gfortran.dg/goacc/data-clauses.f95: Likewise.
	* gfortran.dg/goacc/data-tree.f95: Likewise.
	* gfortran.dg/goacc/declare-1.f95: Likewise.
	* gfortran.dg/goacc/enter-exit-data.f95: Likewise.
	* gfortran.dg/goacc/fixed-1.f: Likewise.
	* gfortran.dg/goacc/fixed-2.f: Likewise.
	* gfortran.dg/goacc/fixed-3.f: Likewise.
	* gfortran.dg/goacc/fixed-4.f: Likewise.
	* gfortran.dg/goacc/host_data-tree.f95: Likewise.
	* gfortran.dg/goacc/if.f95: Likewise.
	* gfortran.dg/goacc/kernels-tree.f95: Likewise.
	* gfortran.dg/goacc/list.f95: Likewise.
	* gfortran.dg/goacc/literal.f95: Likewise.
	* gfortran.dg/goacc/loop-1.f95: Likewise.
	* gfortran.dg/goacc/loop-2.f95: Likewise.
	* gfortran.dg/goacc/loop-3.f95: Likewise.
	* gfortran.dg/goacc/loop-tree-1.f90: Likewise.
	* gfortran.dg/goacc/omp.f95: Likewise.
	* gfortran.dg/goacc/parallel-kernels-clauses.f95: Likewise.
	* gfortran.dg/goacc/parallel-kernels-regions.f95: Likewise.
	* gfortran.dg/goacc/parallel-tree.f95: Likewise.
	* gfortran.dg/goacc/parameter.f95: Likewise.
	* gfortran.dg/goacc/private-1.f95: Likewise.
	* gfortran.dg/goacc/private-2.f95: Likewise.
	* gfortran.dg/goacc/private-3.f95: Likewise.
	* gfortran.dg/goacc/pure-elemental-procedures.f95: Likewise.
	* gfortran.dg/goacc/reduction-2.f95: Likewise.
	* gfortran.dg/goacc/reduction.f95: Likewise.
	* gfortran.dg/goacc/routine-1.f90: Likewise.
	* gfortran.dg/goacc/routine-2.f90: Likewise.
	* gfortran.dg/goacc/sentinel-free-form.f95: Likewise.
	* gfortran.dg/goacc/several-directives.f95: Likewise.
	* gfortran.dg/goacc/sie.f95: Likewise.
	* gfortran.dg/goacc/subarrays.f95: Likewise.
	* gfortran.dg/gomp/map-1.f90: Likewise.
	* gfortran.dg/openacc-define-1.f90: Likewise.
	* gfortran.dg/openacc-define-2.f90: Likewise.
	* gfortran.dg/openacc-define-3.f90: Likewise.
	* g++.dg/gomp/block-1.C: Update for changed compiler output.
	* g++.dg/gomp/block-2.C: Likewise.
	* g++.dg/gomp/block-3.C: Likewise.
	* g++.dg/gomp/block-5.C: Likewise.
	* g++.dg/gomp/target-1.C: Likewise.
	* g++.dg/gomp/target-2.C: Likewise.
	* g++.dg/gomp/taskgroup-1.C: Likewise.
	* g++.dg/gomp/teams-1.C: Likewise.
	* gcc.dg/cilk-plus/jump-openmp.c: Likewise.
	* gcc.dg/cilk-plus/jump.c: Likewise.
	* gcc.dg/gomp/block-1.c: Likewise.
	* gcc.dg/gomp/block-10.c: Likewise.
	* gcc.dg/gomp/block-2.c: Likewise.
	* gcc.dg/gomp/block-3.c: Likewise.
	* gcc.dg/gomp/block-4.c: Likewise.
	* gcc.dg/gomp/block-5.c: Likewise.
	* gcc.dg/gomp/block-6.c: Likewise.
	* gcc.dg/gomp/block-7.c: Likewise.
	* gcc.dg/gomp/block-8.c: Likewise.
	* gcc.dg/gomp/block-9.c: Likewise.
	* gcc.dg/gomp/target-1.c: Likewise.
	* gcc.dg/gomp/target-2.c: Likewise.
	* gcc.dg/gomp/taskgroup-1.c: Likewise.
	* gcc.dg/gomp/teams-1.c: Likewise.
	include/
	* gomp-constants.h: New file.
	libgomp/
	* Makefile.am (search_path): Add $(top_srcdir)/../include.
	(libgomp_la_SOURCES): Add splay-tree.c, libgomp-plugin.c,
	oacc-parallel.c, oacc-host.c, oacc-init.c, oacc-mem.c,
	oacc-async.c, oacc-plugin.c, oacc-cuda.c.
	[USE_FORTRAN] (libgomp_la_SOURCES): Add openacc.f90.
	Include $(top_srcdir)/plugin/Makefrag.am.
	(nodist_libsubinclude_HEADERS): Add openacc.h.
	[USE_FORTRAN] (nodist_finclude_HEADERS): Add openacc_lib.h,
	openacc.f90, openacc.mod, openacc_kinds.mod.
	(omp_lib.mod): Generalize into...
	(%.mod): ... this new rule.
	(openacc_kinds.mod, openacc.mod): New rules.
	* plugin/configfrag.ac: New file.
	* configure.ac: Move plugin/offloading support into it.  Include
	it.  Instantiate testsuite/libgomp-test-support.pt.exp.
	* plugin/Makefrag.am: New file.
	* testsuite/Makefile.am (OFFLOAD_TARGETS)
	(OFFLOAD_ADDITIONAL_OPTIONS, OFFLOAD_ADDITIONAL_LIB_PATHS): Don't
	export.
	(libgomp-test-support.exp): New rule.
	(all-local): Depend on it.
	* Makefile.in: Regenerate.
	* testsuite/Makefile.in: Regenerate.
	* config.h.in: Likewise.
	* configure: Likewise.
	* configure.tgt: Harden shell syntax.
	* env.c: Include "oacc-int.h".
	(parse_acc_device_type): New function.
	(gomp_debug_var, goacc_device_type, goacc_device_num): New
	variables.
	(initialize_env): Initialize those.  Call
	goacc_runtime_initialize.
	* error.c (gomp_vdebug, gomp_debug, gomp_vfatal): New functions.
	(gomp_fatal): Call gomp_vfatal.
	* libgomp.h: Include "libgomp-plugin.h" and <stdarg.h>.
	(gomp_debug_var, goacc_device_type, goacc_device_num, gomp_vdebug)
	(gomp_debug, gomp_verror, gomp_vfatal, gomp_init_targets_once)
	(splay_tree_node, splay_tree, splay_tree_key)
	(struct target_mem_desc, struct splay_tree_key_s)
	(struct gomp_memory_mapping, struct acc_dispatch_t)
	(struct gomp_device_descr, gomp_acc_insert_pointer)
	(gomp_acc_remove_pointer, target_mem_desc, gomp_copy_from_async)
	(gomp_unmap_vars, gomp_init_device, gomp_init_tables)
	(gomp_free_memmap, gomp_fini_device): New declarations.
	(gomp_vdebug, gomp_debug): New macros.
	Include "splay-tree.h".
	* libgomp.map (OACC_2.0): New symbol version.  Use for
	acc_get_num_devices, acc_get_num_devices_h_, acc_set_device_type,
	acc_set_device_type_h_, acc_get_device_type,
	acc_get_device_type_h_, acc_set_device_num, acc_set_device_num_h_,
	acc_get_device_num, acc_get_device_num_h_, acc_async_test,
	acc_async_test_h_, acc_async_test_all, acc_async_test_all_h_,
	acc_wait, acc_wait_h_, acc_wait_async, acc_wait_async_h_,
	acc_wait_all, acc_wait_all_h_, acc_wait_all_async,
	acc_wait_all_async_h_, acc_init, acc_init_h_, acc_shutdown,
	acc_shutdown_h_, acc_on_device, acc_on_device_h_, acc_malloc,
	acc_free, acc_copyin, acc_copyin_32_h_, acc_copyin_64_h_,
	acc_copyin_array_h_, acc_present_or_copyin,
	acc_present_or_copyin_32_h_, acc_present_or_copyin_64_h_,
	acc_present_or_copyin_array_h_, acc_create, acc_create_32_h_,
	acc_create_64_h_, acc_create_array_h_, acc_present_or_create,
	acc_present_or_create_32_h_, acc_present_or_create_64_h_,
	acc_present_or_create_array_h_, acc_copyout, acc_copyout_32_h_,
	acc_copyout_64_h_, acc_copyout_array_h_, acc_delete,
	acc_delete_32_h_, acc_delete_64_h_, acc_delete_array_h_,
	acc_update_device, acc_update_device_32_h_,
	acc_update_device_64_h_, acc_update_device_array_h_,
	acc_update_self, acc_update_self_32_h_, acc_update_self_64_h_,
	acc_update_self_array_h_, acc_map_data, acc_unmap_data,
	acc_deviceptr, acc_hostptr, acc_is_present, acc_is_present_32_h_,
	acc_is_present_64_h_, acc_is_present_array_h_,
	acc_memcpy_to_device, acc_memcpy_from_device,
	acc_get_current_cuda_device, acc_get_current_cuda_context,
	acc_get_cuda_stream, acc_set_cuda_stream.
	(GOACC_2.0): New symbol version.  Use for GOACC_data_end,
	GOACC_data_start, GOACC_enter_exit_data, GOACC_parallel,
	GOACC_update, GOACC_wait, GOACC_get_thread_num,
	GOACC_get_num_threads.
	(GOMP_PLUGIN_1.0): New symbol version.  Use for
	GOMP_PLUGIN_malloc, GOMP_PLUGIN_malloc_cleared,
	GOMP_PLUGIN_realloc, GOMP_PLUGIN_debug, GOMP_PLUGIN_error,
	GOMP_PLUGIN_fatal, GOMP_PLUGIN_async_unmap_vars,
	GOMP_PLUGIN_acc_thread.
	* libgomp.texi: Update for OpenACC changes, and GOMP_DEBUG
	environment variable.
	* libgomp_g.h (GOACC_data_start, GOACC_data_end)
	(GOACC_enter_exit_data, GOACC_parallel, GOACC_update, GOACC_wait)
	(GOACC_get_num_threads, GOACC_get_thread_num): New declarations.
	* splay-tree.h (splay_tree_lookup, splay_tree_insert)
	(splay_tree_remove): New declarations.
	(rotate_left, rotate_right, splay_tree_splay, splay_tree_insert)
	(splay_tree_remove, splay_tree_lookup): Move into...
	* splay-tree.c: ... this new file.
	* target.c: Include "oacc-plugin.h", "oacc-int.h", <assert.h>.
	(splay_tree_node, splay_tree, splay_tree_key)
	(struct target_mem_desc, struct splay_tree_key_s)
	(struct gomp_device_descr): Don't declare.
	(num_devices_openmp): New variable.
	(gomp_get_num_devices ): Use it.
	(gomp_init_targets_once): New function.
	(gomp_get_num_devices ): Use it.
	(get_kind, gomp_copy_from_async, gomp_free_memmap)
	(gomp_fini_device, gomp_register_image_for_device): New functions.
	(gomp_map_vars): Add devaddrs parameter.
	(gomp_update): Add mm parameter.
	(gomp_init_device): Move most of it into...
	(gomp_init_tables): ... this new function.
	(gomp_register_images_for_device): Remove function.
	(splay_compare, gomp_map_vars, gomp_unmap_vars, gomp_init_device):
	Make them hidden instead of static.
	(gomp_map_vars_existing, gomp_map_vars, gomp_unmap_vars)
	(gomp_update, gomp_init_device, GOMP_target, GOMP_target_data)
	(GOMP_target_end_data, GOMP_target_update)
	(gomp_load_plugin_for_device, gomp_target_init): Update for
	OpenACC changes.
	* oacc-async.c: New file.
	* oacc-cuda.c: Likewise.
	* oacc-host.c: Likewise.
	* oacc-init.c: Likewise.
	* oacc-int.h: Likewise.
	* oacc-mem.c: Likewise.
	* oacc-parallel.c: Likewise.
	* oacc-plugin.c: Likewise.
	* oacc-plugin.h: Likewise.
	* oacc-ptx.h: Likewise.
	* openacc.f90: Likewise.
	* openacc.h: Likewise.
	* openacc_lib.h: Likewise.
	* plugin/plugin-host.c: Likewise.
	* plugin/plugin-nvptx.c: Likewise.
	* libgomp-plugin.c: Likewise.
	* libgomp-plugin.h: Likewise.
	* libgomp_target.h: Remove file after merging content into the
	former file.  Update all users.
	* testsuite/lib/libgomp.exp: Load libgomp-test-support.exp.
	(offload_targets_s, offload_targets_s_openacc): New variables.
	(check_effective_target_openacc_nvidia_accel_present)
	(check_effective_target_openacc_nvidia_accel_selected): New
	procedures.
	(libgomp_init): Update for OpenACC changes.
	* testsuite/libgomp-test-support.exp.in: New file.
	* testsuite/libgomp.oacc-c++/c++.exp: Likewise.
	* testsuite/libgomp.oacc-c/c.exp: Likewise.
	* testsuite/libgomp.oacc-fortran/fortran.exp: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/abort-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/abort-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/abort-3.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/abort-4.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/acc_on_device-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/asyncwait-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/cache-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/clauses-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/clauses-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/collapse-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/collapse-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/collapse-3.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/collapse-4.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/context-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/context-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/context-3.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/context-4.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-3.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-3.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-4.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-5.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-6.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-7.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/data-already-8.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/deviceptr-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/if-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/kernels-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/kernels-empty.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-10.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-11.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-12.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-13.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-14.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-15.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-16.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-17.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-18.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-19.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-20.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-21.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-22.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-23.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-24.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-25.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-26.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-27.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-28.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-29.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-3.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-30.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-31.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-32.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-33.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-34.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-35.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-36.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-37.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-38.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-39.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-4.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-40.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-41.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-42.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-43.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-44.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-45.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-46.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-47.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-48.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-49.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-5.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-50.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-51.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-52.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-53.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-54.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-55.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-56.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-57.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-58.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-59.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-6.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-60.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-61.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-62.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-63.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-64.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-65.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-66.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-67.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-68.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-69.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-7.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-70.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-71.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-72.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-73.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-74.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-75.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-76.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-77.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-78.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-79.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-80.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-81.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-82.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-83.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-84.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-85.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-86.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-87.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-88.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-89.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-9.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-90.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-91.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/lib-92.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/nested-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/nested-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/offset-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/parallel-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/parallel-empty.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/pointer-align-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/present-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/present-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-3.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-4.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-5.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-initial-1.c:
	Likewise.
	* testsuite/libgomp.oacc-c-c++-common/subr.h: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/subr.ptx: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/timer.h: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/update-1-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/update-1.c: Likewise.
	* testsuite/libgomp.oacc-fortran/abort-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/abort-2.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/acc_on_device-1-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/acc_on_device-1-2.f: Likewise.
	* testsuite/libgomp.oacc-fortran/acc_on_device-1-3.f: Likewise.
	* testsuite/libgomp.oacc-fortran/asyncwait-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/asyncwait-2.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/asyncwait-3.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/collapse-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/collapse-2.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/collapse-3.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/collapse-4.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/collapse-5.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/collapse-6.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/collapse-7.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/collapse-8.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/data-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/data-2.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/data-3.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/data-4-2.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/data-4.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-1.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-2.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-3.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-4.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-5.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-6.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-7.f: Likewise.
	* testsuite/libgomp.oacc-fortran/data-already-8.f: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-10.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-2.f: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-3.f: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-4.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-5.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-6.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-7.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/lib-8.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/map-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/openacc_version-1.f: Likewise.
	* testsuite/libgomp.oacc-fortran/openacc_version-2.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/pointer-align-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/pset-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reduction-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reduction-2.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reduction-3.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reduction-4.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reduction-5.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/reduction-6.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/routine-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/routine-2.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/routine-3.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/routine-4.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/subarrays-1.f90: Likewise.
	* testsuite/libgomp.oacc-fortran/subarrays-2.f90: Likewise.
	liboffloadmic/
	* plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_get_name)
	(GOMP_OFFLOAD_get_caps, GOMP_OFFLOAD_fini_device): New functions.

Co-Authored-By: Bernd Schmidt <bernds@codesourcery.com>
Co-Authored-By: Cesar Philippidis <cesar@codesourcery.com>
Co-Authored-By: Dmitry Bocharnikov <dmitry.b@samsung.com>
Co-Authored-By: Evgeny Gavrin <e.gavrin@samsung.com>
Co-Authored-By: Ilmir Usmanov <i.usmanov@samsung.com>
Co-Authored-By: Jakub Jelinek <jakub@redhat.com>
Co-Authored-By: James Norris <jnorris@codesourcery.com>
Co-Authored-By: Julian Brown <julian@codesourcery.com>
Co-Authored-By: Nathan Sidwell <nathan@codesourcery.com>
Co-Authored-By: Tobias Burnus <burnus@net-b.de>
Co-Authored-By: Tom de Vries <tom@codesourcery.com>

From-SVN: r219682

204 files changed, 15315 insertions, 30 deletions

diff --git a/libgomp/testsuite/Makefile.am b/libgomp/testsuite/Makefile.am
index 9cc103a..66a9d94 100644
--- a/libgomp/testsuite/Makefile.am
+++ b/libgomp/testsuite/Makefile.am
@@ -12,7 +12,16 @@ _RUNTEST = $(shell if test -f $(top_srcdir)/../dejagnu/runtest; then \
 	     echo $(top_srcdir)/../dejagnu/runtest; else echo runtest; fi)
 RUNTEST = "$(_RUNTEST) $(AM_RUNTESTFLAGS)"
 
-# Used for support non-fallback offloading.
-export OFFLOAD_TARGETS = $(offload_targets)
-export OFFLOAD_ADDITIONAL_OPTIONS = $(offload_additional_options)
-export OFFLOAD_ADDITIONAL_LIB_PATHS = $(offload_additional_lib_paths)
+
+# Instead of directly in ../testsuite/libgomp-test-support.exp.in, the
+# following variables have to be "routed through" this Makefile, for expansion
+# of the several (Makefile) variables used therein.
+libgomp-test-support.exp: libgomp-test-support.pt.exp Makefile
+	cp $< $@.tmp
+	echo >> $@.tmp \
+	  'set offload_additional_options "$(offload_additional_options)"'
+	echo >> $@.tmp \
+	  'set offload_additional_lib_paths "$(offload_additional_lib_paths)"'
+	mv $@.tmp $@
+
+all-local: libgomp-test-support.exp
diff --git a/libgomp/testsuite/Makefile.in b/libgomp/testsuite/Makefile.in
index 2f845f0..352fc3f 100644
--- a/libgomp/testsuite/Makefile.in
+++ b/libgomp/testsuite/Makefile.in
@@ -35,7 +35,8 @@ build_triplet = @build@
 host_triplet = @host@
 target_triplet = @target@
 subdir = testsuite
-DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/Makefile.am
+DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/Makefile.am \
+	$(srcdir)/libgomp-test-support.exp.in
 ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
 am__aclocal_m4_deps = $(top_srcdir)/../config/acx.m4 \
 	$(top_srcdir)/../config/depstand.m4 \
@@ -49,12 +50,13 @@ am__aclocal_m4_deps = $(top_srcdir)/../config/acx.m4 \
 	$(top_srcdir)/../config/tls.m4 $(top_srcdir)/../ltoptions.m4 \
 	$(top_srcdir)/../ltsugar.m4 $(top_srcdir)/../ltversion.m4 \
 	$(top_srcdir)/../lt~obsolete.m4 $(top_srcdir)/acinclude.m4 \
-	$(top_srcdir)/../libtool.m4 $(top_srcdir)/configure.ac
+	$(top_srcdir)/../libtool.m4 $(top_srcdir)/plugin/configfrag.ac \
+	$(top_srcdir)/configure.ac
 am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \
 	$(ACLOCAL_M4)
 mkinstalldirs = $(SHELL) $(top_srcdir)/../mkinstalldirs
 CONFIG_HEADER = $(top_builddir)/config.h
-CONFIG_CLEAN_FILES =
+CONFIG_CLEAN_FILES = libgomp-test-support.pt.exp
 CONFIG_CLEAN_VPATH_FILES =
 SOURCES =
 DEJATOOL = $(PACKAGE)
@@ -71,6 +73,8 @@ CCDEPMODE = @CCDEPMODE@
 CFLAGS = @CFLAGS@
 CPP = @CPP@
 CPPFLAGS = @CPPFLAGS@
+CUDA_DRIVER_INCLUDE = @CUDA_DRIVER_INCLUDE@
+CUDA_DRIVER_LIB = @CUDA_DRIVER_LIB@
 CYGPATH_W = @CYGPATH_W@
 DEFS = @DEFS@
 DEPDIR = @DEPDIR@
@@ -129,6 +133,10 @@ PACKAGE_URL = @PACKAGE_URL@
 PACKAGE_VERSION = @PACKAGE_VERSION@
 PATH_SEPARATOR = @PATH_SEPARATOR@
 PERL = @PERL@
+PLUGIN_NVPTX = @PLUGIN_NVPTX@
+PLUGIN_NVPTX_CPPFLAGS = @PLUGIN_NVPTX_CPPFLAGS@
+PLUGIN_NVPTX_LDFLAGS = @PLUGIN_NVPTX_LDFLAGS@
+PLUGIN_NVPTX_LIBS = @PLUGIN_NVPTX_LIBS@
 RANLIB = @RANLIB@
 SECTION_LDFLAGS = @SECTION_LDFLAGS@
 SED = @SED@
@@ -250,6 +258,8 @@ $(top_srcdir)/configure: @MAINTAINER_MODE_TRUE@ $(am__configure_deps)
 $(ACLOCAL_M4): @MAINTAINER_MODE_TRUE@ $(am__aclocal_m4_deps)
 	cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh
 $(am__aclocal_m4_deps):
+libgomp-test-support.pt.exp: $(top_builddir)/config.status $(srcdir)/libgomp-test-support.exp.in
+	cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@
 
 mostlyclean-libtool:
 	-rm -f *.lo
@@ -303,7 +313,7 @@ distclean-DEJAGNU:
 check-am: all-am
 	$(MAKE) $(AM_MAKEFLAGS) check-DEJAGNU
 check: check-am
-all-am: Makefile
+all-am: Makefile all-local
 installdirs:
 install: install-am
 install-exec: install-exec-am
@@ -398,23 +408,31 @@ uninstall-am:
 
 .MAKE: check-am install-am install-strip
 
-.PHONY: all all-am check check-DEJAGNU check-am clean clean-generic \
-	clean-libtool distclean distclean-DEJAGNU distclean-generic \
-	distclean-libtool dvi dvi-am html html-am info info-am install \
-	install-am install-data install-data-am install-dvi \
-	install-dvi-am install-exec install-exec-am install-html \
-	install-html-am install-info install-info-am install-man \
-	install-pdf install-pdf-am install-ps install-ps-am \
-	install-strip installcheck installcheck-am installdirs \
-	maintainer-clean maintainer-clean-generic mostlyclean \
-	mostlyclean-generic mostlyclean-libtool pdf pdf-am ps ps-am \
-	uninstall uninstall-am
-
-
-# Used for support non-fallback offloading.
-export OFFLOAD_TARGETS = $(offload_targets)
-export OFFLOAD_ADDITIONAL_OPTIONS = $(offload_additional_options)
-export OFFLOAD_ADDITIONAL_LIB_PATHS = $(offload_additional_lib_paths)
+.PHONY: all all-am all-local check check-DEJAGNU check-am clean \
+	clean-generic clean-libtool distclean distclean-DEJAGNU \
+	distclean-generic distclean-libtool dvi dvi-am html html-am \
+	info info-am install install-am install-data install-data-am \
+	install-dvi install-dvi-am install-exec install-exec-am \
+	install-html install-html-am install-info install-info-am \
+	install-man install-pdf install-pdf-am install-ps \
+	install-ps-am install-strip installcheck installcheck-am \
+	installdirs maintainer-clean maintainer-clean-generic \
+	mostlyclean mostlyclean-generic mostlyclean-libtool pdf pdf-am \
+	ps ps-am uninstall uninstall-am
+
+
+# Instead of directly in ../testsuite/libgomp-test-support.exp.in, the
+# following variables have to be "routed through" this Makefile, for expansion
+# of the several (Makefile) variables used therein.
+libgomp-test-support.exp: libgomp-test-support.pt.exp Makefile
+	cp $< $@.tmp
+	echo >> $@.tmp \
+	  'set offload_additional_options "$(offload_additional_options)"'
+	echo >> $@.tmp \
+	  'set offload_additional_lib_paths "$(offload_additional_lib_paths)"'
+	mv $@.tmp $@
+
+all-local: libgomp-test-support.exp
 
 # Tell versions [3.59,3.63) of GNU make to not export all variables.
 # Otherwise a system limit (for SysV at least) may be exceeded.
diff --git a/libgomp/testsuite/lib/libgomp.exp b/libgomp/testsuite/lib/libgomp.exp
index 2d6f822..5a6eec1 100644
--- a/libgomp/testsuite/lib/libgomp.exp
+++ b/libgomp/testsuite/lib/libgomp.exp
@@ -32,6 +32,29 @@ load_gcc_lib timeout-dg.exp
 load_gcc_lib torture-options.exp
 load_gcc_lib fortran-modules.exp
 
+# Try to load a test support file, built during libgomp configuration.
+load_file libgomp-test-support.exp
+
+# Populate offload_targets_s (offloading targets separated by a space), and
+# offload_targets_s_openacc (the same, but with OpenACC names; OpenACC spells
+# some of them a little differently).
+set offload_targets_s [split $offload_targets ","]
+set offload_targets_s_openacc {}
+foreach offload_target_openacc $offload_targets_s {
+    switch $offload_target_openacc {
+	intelmic {
+	    # Skip; will all FAIL because of missing
+	    # GOMP_OFFLOAD_CAP_OPENACC_200.
+	    continue
+	}
+	nvptx {
+	    set offload_target_openacc "nvidia"
+	}
+    }
+    lappend offload_targets_s_openacc "$offload_target_openacc"
+}
+lappend offload_targets_s_openacc "host"
+
 set dg-do-what-default run
 
 #
@@ -108,13 +131,9 @@ proc libgomp_init { args } {
     # Compute what needs to be put into LD_LIBRARY_PATH
     set always_ld_library_path ".:${blddir}/.libs"
 
-    # Get offload-related variables from environment (exported by Makefile)
-    set offload_targets [getenv OFFLOAD_TARGETS]
-    set offload_additional_options [getenv OFFLOAD_ADDITIONAL_OPTIONS]
-    set offload_additional_lib_paths [getenv OFFLOAD_ADDITIONAL_LIB_PATHS]
-
     # Add liboffloadmic build directory in LD_LIBRARY_PATH to support
     # non-fallback testing for Intel MIC targets
+    global offload_targets
     if { [string match "*,intelmic,*" ",$offload_targets,"] } {
 	append always_ld_library_path ":${blddir}/../liboffloadmic/.libs"
 	append always_ld_library_path ":${blddir}/../liboffloadmic/plugin/.libs"
@@ -122,6 +141,7 @@ proc libgomp_init { args } {
 	append always_ld_library_path ":${blddir}/../libstdc++-v3/src/.libs"
     }
 
+    global offload_additional_lib_paths
     if { $offload_additional_lib_paths != "" } {
 	append always_ld_library_path "${offload_additional_lib_paths}"
     }
@@ -158,9 +178,29 @@ proc libgomp_init { args } {
         lappend ALWAYS_CFLAGS "additional_flags=-B${blddir}/.libs"
         lappend ALWAYS_CFLAGS "additional_flags=-I${blddir}"
         lappend ALWAYS_CFLAGS "ldflags=-L${blddir}/.libs"
+	# The top-level include directory, for gomp-constants.h.
+	lappend ALWAYS_CFLAGS "additional_flags=-I${srcdir}/../../include"
     }
     lappend ALWAYS_CFLAGS "additional_flags=-I${srcdir}/.."
 
+    # For build-tree testing, also consider the CUDA paths used for builing.
+    # For installed testing, we assume all that to be provided in the sysroot.
+    if { $blddir != "" } {
+	global cuda_driver_include
+	global cuda_driver_lib
+	if { $cuda_driver_include != "" } {
+	    # Stop gfortran from freaking out:
+	    # Warning: Nonexistent include directory "[...]"
+	    if {[file exists $cuda_driver_include]} {
+		lappend ALWAYS_CFLAGS "additional_flags=-I$cuda_driver_include"
+	    }
+	}
+	if { $cuda_driver_lib != "" } {
+	    lappend ALWAYS_CFLAGS "additional_flags=-L$cuda_driver_lib"
+	    append always_ld_library_path ":$cuda_driver_lib"
+	}
+    }
+
     # We use atomic operations in the testcases to validate results.
     if { ([istarget i?86-*-*] || [istarget x86_64-*-*])
 	 && [check_effective_target_ia32] } {
@@ -191,6 +231,7 @@ proc libgomp_init { args } {
 
     # Used for support non-fallback offloading.
     # Help GCC to find target mkoffload.
+    global offload_additional_options
     if { $offload_additional_options != "" } {
 	lappend ALWAYS_CFLAGS "additional_flags=${offload_additional_options}"
     }
@@ -278,3 +319,29 @@ proc check_effective_target_offload_device { } {
 	}
     } ]
 }
+
+# Return 1 if at least one nvidia board is present.
+
+proc check_effective_target_openacc_nvidia_accel_present { } {
+    return [check_runtime openacc_nvidia_accel_present {
+	#include <openacc.h>
+	int main () {
+	return !(acc_get_num_devices (acc_device_nvidia) > 0);
+	}
+    } "" ]
+}
+
+# Return 1 if at least one nvidia board is present, and the nvidia device type
+# is selected by default by means of setting the environment variable
+# ACC_DEVICE_TYPE.
+
+proc check_effective_target_openacc_nvidia_accel_selected { } {
+    if { ![check_effective_target_openacc_nvidia_accel_present] } {
+	return 0;
+    }
+    global offload_target_openacc
+    if { $offload_target_openacc == "nvidia" } {
+        return 1;
+    }
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp-test-support.exp.in b/libgomp/testsuite/libgomp-test-support.exp.in
new file mode 100644
index 0000000..764bec0
--- /dev/null
+++ b/libgomp/testsuite/libgomp-test-support.exp.in
@@ -0,0 +1,4 @@
+set cuda_driver_include "@CUDA_DRIVER_INCLUDE@"
+set cuda_driver_lib "@CUDA_DRIVER_LIB@"
+
+set offload_targets "@offload_targets@"
diff --git a/libgomp/testsuite/libgomp.oacc-c++/c++.exp b/libgomp/testsuite/libgomp.oacc-c++/c++.exp
new file mode 100644
index 0000000..f486f9b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c++/c++.exp
@@ -0,0 +1,107 @@
+# This whole file adapted from libgomp.c++/c++.exp.
+
+load_lib libgomp-dg.exp
+load_gcc_lib gcc-dg.exp
+
+global shlib_ext
+
+set shlib_ext [get_shlib_extension]
+set lang_link_flags "-lstdc++"
+set lang_test_file_found 0
+set lang_library_path "../libstdc++-v3/src/.libs"
+if [info exists lang_include_flags] then {
+    unset lang_include_flags
+}
+
+# Initialize dg.
+dg-init
+
+# Turn on OpenACC.
+lappend ALWAYS_CFLAGS "additional_flags=-fopenacc"
+
+# Switch into C++ mode.  Otherwise, the libgomp.oacc-c-c++-common/*.c
+# files would be compiled as C files.
+set SAVE_GCC_UNDER_TEST "$GCC_UNDER_TEST"
+set GCC_UNDER_TEST "$GCC_UNDER_TEST -x c++"
+
+set blddir [lookfor_file [get_multilibs] libgomp]
+
+
+if { $blddir != "" } {
+    # Look for a static libstdc++ first.
+    if [file exists "${blddir}/${lang_library_path}/libstdc++.a"] {
+        set lang_test_file "${lang_library_path}/libstdc++.a"
+        set lang_test_file_found 1
+        # We may have a shared only build, so look for a shared libstdc++.
+    } elseif [file exists "${blddir}/${lang_library_path}/libstdc++.${shlib_ext}"] {
+        set lang_test_file "${lang_library_path}/libstdc++.${shlib_ext}"
+        set lang_test_file_found 1
+    } else {
+        puts "No libstdc++ library found, will not execute c++ tests"
+    }
+} elseif { [info exists GXX_UNDER_TEST] } {
+    set lang_test_file_found 1
+    # Needs to exist for libgomp.exp.
+    set lang_test_file ""
+} else {
+    puts "GXX_UNDER_TEST not defined, will not execute c++ tests"
+}
+
+if { $lang_test_file_found } {
+    # Gather a list of all tests.
+    set tests [lsort [concat \
+			  [find $srcdir/$subdir *.C] \
+			  [find $srcdir/$subdir/../libgomp.oacc-c-c++-common *.c]]]
+
+    if { $blddir != "" } {
+        set ld_library_path "$always_ld_library_path:${blddir}/${lang_library_path}"
+    } else {
+        set ld_library_path "$always_ld_library_path"
+    }
+    append ld_library_path [gcc-set-multilib-library-path $GCC_UNDER_TEST]
+    set_ld_library_path_env_vars
+
+    set flags_file "${blddir}/../libstdc++-v3/scripts/testsuite_flags"
+    if { [file exists $flags_file] } {
+	set libstdcxx_includes [exec sh $flags_file --build-includes]
+    } else {
+	set libstdcxx_includes ""
+    }
+
+    # Test OpenACC with available accelerators.
+    foreach offload_target_openacc $offload_targets_s_openacc {
+	set tagopt "-DACC_DEVICE_TYPE_$offload_target_openacc=1"
+
+	switch $offload_target_openacc {
+	    host {
+		set acc_mem_shared 1
+	    }
+	    host_nonshm {
+		set acc_mem_shared 0
+	    }
+	    nvidia {
+		# Copy ptx file (TEMPORARY)
+		remote_download host $srcdir/libgomp.oacc-c-c++-common/subr.ptx
+
+		# Where timer.h lives
+		lappend ALWAYS_CFLAGS "additional_flags=-I${srcdir}/libgomp.oacc-c-c++-common"
+
+		set acc_mem_shared 0
+	    }
+	    default {
+		set acc_mem_shared 0
+	    }
+	}
+	set tagopt "$tagopt -DACC_MEM_SHARED=$acc_mem_shared"
+
+	setenv ACC_DEVICE_TYPE $offload_target_openacc
+
+	dg-runtest $tests "$tagopt" $libstdcxx_includes
+    }
+}
+
+# See above.
+set GCC_UNDER_TEST "$SAVE_GCC_UNDER_TEST"
+
+# All done.
+dg-finish
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-1.c
new file mode 100644
index 0000000..f88b9e3
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-1.c
@@ -0,0 +1,17 @@
+/* { dg-do run } */
+/* { dg-shouldfail "" { *-*-* } { "*" } { "" } } */
+
+#include <stdlib.h>
+
+int
+main (void)
+{
+
+#pragma acc parallel
+  {
+    abort ();
+  }
+
+  return 0;
+}
+
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-2.c
new file mode 100644
index 0000000..debb81e
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-2.c
@@ -0,0 +1,17 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int
+main (int argc, char **argv)
+{
+
+#pragma acc parallel
+  {
+    if (argc != 1)
+      abort ();
+  }
+
+  return 0;
+}
+
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-3.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-3.c
new file mode 100644
index 0000000..be7aaa8
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-3.c
@@ -0,0 +1,17 @@
+/* { dg-do run } */
+/* { dg-shouldfail "" { *-*-* } { "*" } { "" } } */
+
+#include <stdlib.h>
+
+int
+main (void)
+{
+
+#pragma acc kernels
+  {
+    abort ();
+  }
+
+  return 0;
+}
+
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-4.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-4.c
new file mode 100644
index 0000000..c29ca3f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/abort-4.c
@@ -0,0 +1,17 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int
+main (int argc, char **argv)
+{
+
+#pragma acc kernels
+  {
+    if (argc != 1)
+      abort ();
+  }
+
+  return 0;
+}
+
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/acc_on_device-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/acc_on_device-1.c
new file mode 100644
index 0000000..81ea476
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/acc_on_device-1.c
@@ -0,0 +1,75 @@
+/* Disable the acc_on_device builtin; we want to test the libgomp library
+   function.  */
+/* { dg-additional-options "-fno-builtin-acc_on_device" } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char *argv[])
+{
+  /* Host.  */
+
+  {
+    if (!acc_on_device (acc_device_none))
+      abort ();
+    if (!acc_on_device (acc_device_host))
+      abort ();
+    if (acc_on_device (acc_device_host_nonshm))
+      abort ();
+    if (acc_on_device (acc_device_not_host))
+      abort ();
+    if (acc_on_device (acc_device_nvidia))
+      abort ();
+  }
+
+
+  /* Host via offloading fallback mode.  */
+
+#pragma acc parallel if(0)
+  {
+    if (!acc_on_device (acc_device_none))
+      abort ();
+    if (!acc_on_device (acc_device_host))
+      abort ();
+    if (acc_on_device (acc_device_host_nonshm))
+      abort ();
+    if (acc_on_device (acc_device_not_host))
+      abort ();
+    if (acc_on_device (acc_device_nvidia))
+      abort ();
+  }
+
+
+#if !ACC_DEVICE_TYPE_host
+
+  /* Offloaded.  */
+
+#pragma acc parallel
+  {
+    if (acc_on_device (acc_device_none))
+      abort ();
+    if (acc_on_device (acc_device_host))
+      abort ();
+#if ACC_DEVICE_TYPE_host_nonshm
+    if (!acc_on_device (acc_device_host_nonshm))
+      abort ();
+#else
+    if (acc_on_device (acc_device_host_nonshm))
+      abort ();
+#endif
+    if (!acc_on_device (acc_device_not_host))
+      abort ();
+#if ACC_DEVICE_TYPE_nvidia
+    if (!acc_on_device (acc_device_nvidia))
+      abort ();
+#else
+    if (acc_on_device (acc_device_nvidia))
+      abort ();
+#endif
+  }
+
+#endif
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/asyncwait-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/asyncwait-1.c
new file mode 100644
index 0000000..22cef6d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/asyncwait-1.c
@@ -0,0 +1,466 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <openacc.h>
+#include <stdlib.h>
+#include "cuda.h"
+
+#include <stdio.h>
+#include <sys/time.h>
+
+int
+main (int argc, char **argv)
+{
+    CUresult r;
+    CUstream stream1;
+    int N = 128; //1024 * 1024;
+    float *a, *b, *c, *d, *e;
+    int i;
+    int nbytes;
+
+    acc_init (acc_device_nvidia);
+
+    nbytes = N * sizeof (float);
+
+    a = (float *) malloc (nbytes);
+    b = (float *) malloc (nbytes);
+    c = (float *) malloc (nbytes);
+    d = (float *) malloc (nbytes);
+    e = (float *) malloc (nbytes);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc data copy (a[0:N]) copy (b[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc wait
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 2.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc data copy (a[0:N]) copy (b[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc wait (1)
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 2.0)
+            abort ();
+
+        if (b[i] != 2.0)
+            abort ();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 0.0;
+        c[i] = 0.0;
+        d[i] = 0.0;
+    }
+
+#pragma acc data copy (a[0:N]) copy (b[0:N]) copy (c[0:N]) copy (d[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = (a[ii] * a[ii] * a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            c[ii] = (a[ii] + a[ii] + a[ii] + a[ii]) / a[ii];
+    }
+
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            d[ii] = ((a[ii] * a[ii] + a[ii]) / a[ii]) - a[ii];
+    }
+
+#pragma acc wait (1)
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 9.0)
+            abort ();
+
+        if (c[i] != 4.0)
+            abort ();
+
+        if (d[i] != 1.0)
+            abort ();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 2.0;
+        b[i] = 0.0;
+        c[i] = 0.0;
+        d[i] = 0.0;
+        e[i] = 0.0;
+    }
+
+#pragma acc data copy (a[0:N], b[0:N], c[0:N], d[0:N], e[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = (a[ii] * a[ii] * a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            c[ii] = (a[ii] + a[ii] + a[ii] + a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            d[ii] = ((a[ii] * a[ii] + a[ii]) / a[ii]) - a[ii];
+    }
+
+#pragma acc parallel wait (1) async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            e[ii] = a[ii] + b[ii] + c[ii] + d[ii];
+    }
+
+#pragma acc wait (1)
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 2.0)
+            abort ();
+
+        if (b[i] != 4.0)
+            abort ();
+
+        if (c[i] != 4.0)
+            abort ();
+
+        if (d[i] != 1.0)
+            abort ();
+
+        if (e[i] != 11.0)
+            abort ();
+    }
+
+
+    r = cuStreamCreate (&stream1, CU_STREAM_NON_BLOCKING);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+        abort ();
+    }
+
+    acc_set_cuda_stream (1, stream1);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc data copy (a[0:N], b[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc wait (1)
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 7.0;
+        b[i] = 0.0;
+        c[i] = 0.0;
+        d[i] = 0.0;
+    }
+
+#pragma acc data copy (a[0:N]) copy (b[0:N]) copy (c[0:N]) copy (d[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = (a[ii] * a[ii] * a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            c[ii] = (a[ii] + a[ii] + a[ii] + a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            d[ii] = ((a[ii] * a[ii] + a[ii]) / a[ii]) - a[ii];
+    }
+
+#pragma acc wait (1)
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 7.0)
+            abort ();
+
+        if (b[i] != 49.0)
+            abort ();
+
+        if (c[i] != 4.0)
+            abort ();
+
+        if (d[i] != 1.0)
+            abort ();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 0.0;
+        c[i] = 0.0;
+        d[i] = 0.0;
+        e[i] = 0.0;
+    }
+
+#pragma acc data copy (a[0:N], b[0:N], c[0:N], d[0:N], e[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = (a[ii] * a[ii] * a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            c[ii] = (a[ii] + a[ii] + a[ii] + a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            d[ii] = ((a[ii] * a[ii] + a[ii]) / a[ii]) - a[ii];
+    }
+
+#pragma acc parallel wait (1) async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            e[ii] = a[ii] + b[ii] + c[ii] + d[ii];
+    }
+
+#pragma acc wait (1)
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 9.0)
+            abort ();
+
+        if (c[i] != 4.0)
+            abort ();
+
+        if (d[i] != 1.0)
+            abort ();
+
+        if (e[i] != 17.0)
+            abort ();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 0.0;
+        c[i] = 0.0;
+        d[i] = 0.0;
+        e[i] = 0.0;
+    }
+
+#pragma acc data copyin (a[0:N], b[0:N], c[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = (a[ii] * a[ii] * a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            c[ii] = (a[ii] + a[ii] + a[ii] + a[ii]) / a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N], c[0:N]) wait (1)
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 16.0)
+            abort ();
+
+        if (c[i] != 4.0)
+            abort ();
+    }
+
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 0.0;
+        c[i] = 0.0;
+        d[i] = 0.0;
+        e[i] = 0.0;
+    }
+
+#pragma acc data copyin (a[0:N], b[0:N], c[0:N]) copyin (N)
+    {
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = (a[ii] * a[ii] * a[ii]) / a[ii];
+    }
+
+#pragma acc parallel async (1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            c[ii] = (a[ii] + a[ii] + a[ii] + a[ii]) / a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N], c[0:N]) async (1)
+
+#pragma acc wait (1)
+
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 25.0)
+            abort ();
+
+        if (c[i] != 4.0)
+            abort ();
+    }
+
+    acc_shutdown (acc_device_nvidia);
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/cache-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/cache-1.c
new file mode 100644
index 0000000..3f1f0bb
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/cache-1.c
@@ -0,0 +1,48 @@
+int
+main (int argc, char **argv)
+{
+#define N   2
+    int a[N], b[N];
+    int i;
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3;
+        b[i] = 0;
+    }
+
+#pragma acc parallel copyin (a[0:N]) copyout (b[0:N])
+{
+    int ii;
+
+    for (ii = 0; ii < N; ii++)
+    {
+        const int idx = ii;
+        int n = 1;
+        const int len = n;
+
+#pragma acc cache (a[0:N])
+
+#pragma acc cache (a[0:N], b[0:N])
+
+#pragma acc cache (a[0])
+
+#pragma acc cache (a[0], a[1], b[0:N])
+
+#pragma acc cache (a[idx])
+
+#pragma acc cache (a[idx:len])
+
+        b[ii] = a[ii];
+    }
+}
+
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != b[i])
+            __builtin_abort ();
+    }
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/clauses-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/clauses-1.c
new file mode 100644
index 0000000..51c0cf5
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/clauses-1.c
@@ -0,0 +1,623 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+    int N = 8;
+    float *a, *b, *c, *d;
+    int i;
+
+    a = (float *) malloc (N * sizeof (float));
+    b = (float *) malloc (N * sizeof (float));
+    c = (float *) malloc (N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc parallel copyin (a[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 1.0;
+    }
+
+#pragma acc parallel copyin (a[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+    d = (float *) acc_copyin (&a[0], N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc parallel present_or_copyin (a[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc parallel copyin (a[0:N]) present_or_copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 2.0;
+    }
+
+    d = (float *) acc_copyin (&b[0], N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) present_or_copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 2.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 4.0;
+    }
+
+#pragma acc parallel copy (a[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            a[ii] = a[ii] + 1;
+            b[ii] = a[ii] + 2;
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 7.0;
+    }
+
+#pragma acc parallel present_or_copy (a[0:N]) present_or_copy (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            a[ii] = a[ii] + 1;
+            b[ii] = b[ii] + 2;
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 9.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 7.0;
+    }
+
+    d = (float *) acc_copyin (&a[0], N * sizeof (float));
+    d = (float *) acc_copyin (&b[0], N * sizeof (float));
+
+#pragma acc parallel present_or_copy (a[0:N]) present_or_copy (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            a[ii] = a[ii] + 1;
+            b[ii] = b[ii] + 2;
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 7.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    d = (float *) acc_deviceptr (&a[0]);
+    acc_unmap_data (&a[0]);
+    acc_free (d);
+
+    d = (float *) acc_deviceptr (&b[0]);
+    acc_unmap_data (&b[0]);
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 7.0;
+    }
+
+#pragma acc parallel copyin (a[0:N]) create (c[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            c[ii] = a[ii];
+            b[ii] = c[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&c[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 8.0;
+    }
+
+#pragma acc parallel copyin (a[0:N]) present_or_create (c[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            c[ii] = a[ii];
+            b[ii] = c[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 4.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&c[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 2.0;
+        b[i] = 5.0;
+    }
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) present_or_create (c[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            c[ii] = a[ii];
+            b[ii] = c[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 2.0)
+            abort ();
+
+        if (b[i] != 2.0)
+            abort ();
+    }
+
+    if (acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    d = (float *) acc_deviceptr (c);
+
+    acc_unmap_data (c);
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 8.0;
+    }
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) present (c[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            c[ii] = a[ii];
+            b[ii] = c[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 4.0)
+            abort ();
+    }
+
+    if (acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    acc_unmap_data (c);
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 8.0;
+    }
+
+    acc_copyin (a, N * sizeof (float));
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (b, d, N * sizeof (float));
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc parallel present (a[0:N]) present (c[0:N]) present (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            c[ii] = a[ii];
+            b[ii] = c[ii];
+        }
+    }
+
+    if (!acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    acc_copyout (b, N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 4.0)
+            abort ();
+    }
+
+    d = (float *) acc_deviceptr (a);
+
+    acc_unmap_data (a);
+
+    acc_free (d);
+
+    d = (float *) acc_deviceptr (c);
+
+    acc_unmap_data (c);
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 6.0;
+    }
+
+    d = (float *) acc_malloc (N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) deviceptr (d) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            d[ii] = a[ii];
+            b[ii] = d[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    if (acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+    d = (float *) acc_copyin (&a[0], N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc parallel pcopyin (a[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc parallel copyin (a[0:N]) pcopyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 7.0;
+    }
+
+#pragma acc parallel copyin (a[0:N]) pcreate (c[0:N]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            c[ii] = a[ii];
+            b[ii] = c[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&c[0], (N * sizeof (float))))
+      abort ();
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/clauses-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/clauses-2.c
new file mode 100644
index 0000000..8dc45cb
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/clauses-2.c
@@ -0,0 +1,67 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+    int N = 8;
+    float *a, *b, *c, *d;
+    int i;
+
+    a = (float *) malloc (N * sizeof (float));
+    b = (float *) malloc (N * sizeof (float));
+    c = (float *) malloc (N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 2.0;
+        b[i] = 5.0;
+    }
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) present_or_create (c[0:N+1]) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            c[ii] = a[ii];
+            b[ii] = c[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 2.0)
+            abort ();
+
+        if (b[i] != 2.0)
+            abort ();
+    }
+
+    if (acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    d = (float *) acc_deviceptr (c);
+
+    acc_unmap_data (c);
+
+    acc_free (d);
+
+    return 0;
+}
+/* { dg-shouldfail "libgomp: \[\h+,\d+\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-1.c
new file mode 100644
index 0000000..80fed6c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-1.c
@@ -0,0 +1,31 @@
+/* { 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 acc parallel
+  #pragma acc loop collapse(4 - 1)
+    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 acc parallel
+    {
+      #pragma acc loop 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.oacc-c-c++-common/collapse-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-2.c
new file mode 100644
index 0000000..44a77f7
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-2.c
@@ -0,0 +1,37 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int
+main (void)
+{
+  int i, j, k, l = 0, f = 0, x = 0;
+  int m1 = 4, m2 = -5, m3 = 17;
+
+  #pragma acc parallel
+  #pragma acc loop collapse(3) reduction(+:l)
+    for (i = -2; i < m1; i++)
+      for (j = m2; j < -2; j++)
+	{
+	  for (k = 13; k < m3; k++)
+	    {
+              if ((i + 2) * 12 + (j + 5) * 4 + (k - 13) !=  9 + f++)
+		l++;
+	    }
+	}
+
+    for (i = -2; i < m1; i++)
+      for (j = m2; j < -2; j++)
+	{
+	  for (k = 13; k < m3; k++)
+	    {
+              if ((i + 2) * 12 + (j + 5) * 4 + (k - 13) !=  9 + f++)
+		x++;
+	    }
+	}
+
+  if (l != x)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-3.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-3.c
new file mode 100644
index 0000000..a5be728
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-3.c
@@ -0,0 +1,40 @@
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+int
+main (void)
+{
+  int i2, l = 0, r = 0;
+  int a[3][3][3];
+
+  memset (a, '\0', sizeof (a));
+  #pragma acc parallel
+  #pragma acc loop collapse(4 - 1)
+    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 acc parallel
+    {
+      #pragma acc loop 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;
+    }
+
+    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)
+	    r += 1;
+
+  if (l != r)
+    abort ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-4.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-4.c
new file mode 100644
index 0000000..52dd435
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/collapse-4.c
@@ -0,0 +1,27 @@
+/* { dg-do run } */
+
+#include <string.h>
+
+int
+main (void)
+{
+  int l = 0;
+  int b[3][3];
+  int i, j;
+
+  memset (b, '\0', sizeof (b));
+
+#pragma acc parallel copy(b[0:3][0:3]) copy(l)
+    {
+#pragma acc loop collapse(2) reduction(+:l)
+	for (i = 0; i < 2; i++)
+	  for (j = 0; j < 2; j++)
+	    if (b[i][j] != 16)
+		  l += 1;
+    }
+
+  if (l != 2 * 2)
+    __builtin_abort();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/context-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/context-1.c
new file mode 100644
index 0000000..dabc706
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/context-1.c
@@ -0,0 +1,213 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda -lcublas -lcudart" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <cublas_v2.h>
+#include <openacc.h>
+
+void
+saxpy (int n, float a, float *x, float *y)
+{
+    int i;
+
+    for (i = 0; i < n; i++)
+    {
+        y[i] = a * x[i] + y[i];
+    }
+}
+
+void
+context_check (CUcontext ctx1)
+{
+    CUcontext ctx2, ctx3;
+    CUresult r;
+
+    r = cuCtxGetCurrent (&ctx2);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    if (ctx1 != ctx2)
+    {
+        fprintf (stderr, "new context established\n");
+        exit (EXIT_FAILURE);
+    }
+
+    ctx3 = (CUcontext) acc_get_current_cuda_context ();
+
+    if (ctx1 != ctx3)
+    {
+        fprintf (stderr, "acc_get_current_cuda_context returned wrong value\n");
+        exit (EXIT_FAILURE);
+    }
+
+    return;
+}
+
+int
+main (int argc, char **argv)
+{
+    cublasStatus_t s;
+    cudaError_t e;
+    cublasHandle_t h;
+    CUcontext pctx, ctx;
+    CUresult r;
+    int dev;
+    int i;
+    const int N = 256;
+    float *h_X, *h_Y1, *h_Y2;
+    float *d_X,*d_Y;
+    float alpha = 2.0f;
+    float error_norm;
+    float ref_norm;
+
+    /* Test 1 - cuBLAS creates, OpenACC shares.  */
+
+    s = cublasCreate (&h);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasCreate failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    r = cuCtxGetCurrent (&pctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    e = cudaGetDevice (&dev);
+    if (e != cudaSuccess)
+    {
+        fprintf (stderr, "cudaGetDevice failed: %d\n", e);
+        exit (EXIT_FAILURE);
+    }
+
+    acc_set_device_num (dev, acc_device_nvidia);
+
+    h_X = (float *) malloc (N * sizeof (float));
+    if (!h_X)
+    {
+        fprintf (stderr, "malloc failed: for h_X\n");
+        exit (EXIT_FAILURE);
+    }
+
+    h_Y1 = (float *) malloc (N * sizeof (float));
+    if (!h_Y1)
+    {
+        fprintf (stderr, "malloc failed: for h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    h_Y2 = (float *) malloc (N * sizeof (float));
+    if (!h_Y2)
+    {
+        fprintf (stderr, "malloc failed: for h_Y2\n");
+        exit (EXIT_FAILURE);
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        h_X[i] = rand () / (float) RAND_MAX;
+        h_Y2[i] = h_Y1[i] = rand () / (float) RAND_MAX;
+    }
+
+    d_X = (float *) acc_copyin (&h_X[0], N * sizeof (float));
+    if (d_X == NULL)
+    {
+        fprintf (stderr, "copyin error h_X\n");
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    d_Y = (float *) acc_copyin (&h_Y1[0], N * sizeof (float));
+    if (d_Y == NULL)
+    {
+        fprintf (stderr, "copyin error h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    s = cublasSaxpy (h, N, &alpha, d_X, 1, d_Y, 1);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasSaxpy failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    acc_memcpy_from_device (&h_Y1[0], d_Y, N * sizeof (float));
+
+    context_check (pctx);
+
+    saxpy (N, alpha, h_X, h_Y2);
+
+    error_norm = 0;
+    ref_norm = 0;
+
+    for (i = 0; i < N; ++i)
+    {
+        float diff;
+
+        diff = h_Y1[i] - h_Y2[i];
+        error_norm += diff * diff;
+        ref_norm += h_Y2[i] * h_Y2[i];
+    }
+
+    error_norm = (float) sqrt ((double) error_norm);
+    ref_norm = (float) sqrt ((double) ref_norm);
+
+    if ((fabs (ref_norm) < 1e-7) || ((error_norm / ref_norm) >= 1e-6f))
+    {
+        fprintf (stderr, "math error\n");
+        exit (EXIT_FAILURE);
+    }
+
+    free (h_X);
+    free (h_Y1);
+    free (h_Y2);
+
+    acc_free (d_X);
+    acc_free (d_Y);
+
+    context_check (pctx);
+
+    s = cublasDestroy (h);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasDestroy failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    acc_shutdown (acc_device_nvidia);
+
+    r = cuCtxGetCurrent (&ctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    if (!ctx)
+    {
+        fprintf (stderr, "Expected context\n");
+        exit (EXIT_FAILURE);
+    }
+
+    if (pctx != ctx)
+    {
+        fprintf (stderr, "Unexpected new context\n");
+        exit (EXIT_FAILURE);
+    }
+
+    return EXIT_SUCCESS;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/context-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/context-2.c
new file mode 100644
index 0000000..6a52f74
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/context-2.c
@@ -0,0 +1,223 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda -lcublas -lcudart" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <cublas_v2.h>
+#include <openacc.h>
+
+void
+saxpy (int n, float a, float *x, float *y)
+{
+    int i;
+
+    for (i = 0; i < n; i++)
+    {
+        y[i] = a * x[i] + y[i];
+    }
+}
+
+void
+context_check (CUcontext ctx1)
+{
+    CUcontext ctx2, ctx3;
+    CUresult r;
+
+    r = cuCtxGetCurrent (&ctx2);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    if (ctx1 != ctx2)
+    {
+        fprintf (stderr, "new context established\n");
+        exit (EXIT_FAILURE);
+    }
+
+    ctx3 = (CUcontext) acc_get_current_cuda_context ();
+
+    if (ctx1 != ctx3)
+    {
+        fprintf (stderr, "acc_get_current_cuda_context returned wrong value\n");
+        exit (EXIT_FAILURE);
+    }
+
+    return;
+}
+
+int
+main (int argc, char **argv)
+{
+    cublasStatus_t s;
+    cudaError_t e;
+    cublasHandle_t h;
+    CUcontext pctx, ctx;
+    CUresult r;
+    int dev;
+    int i;
+    const int N = 256;
+    float *h_X, *h_Y1, *h_Y2;
+    float *d_X,*d_Y;
+    float alpha = 2.0f;
+    float error_norm;
+    float ref_norm;
+
+    /* Test 2 - cuBLAS creates, OpenACC shares.  */
+
+    s = cublasCreate (&h);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasCreate failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    r = cuCtxGetCurrent (&pctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    e = cudaGetDevice (&dev);
+    if (e != cudaSuccess)
+    {
+        fprintf (stderr, "cudaGetDevice failed: %d\n", e);
+        exit (EXIT_FAILURE);
+    }
+
+    acc_set_device_num (dev, acc_device_nvidia);
+
+    h_X = (float *) malloc (N * sizeof (float));
+    if (h_X == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_X\n");
+        exit (EXIT_FAILURE);
+    }
+
+    h_Y1 = (float *) malloc (N * sizeof (float));
+    if (h_Y1 == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    h_Y2 = (float *) malloc (N * sizeof (float));
+    if (h_Y2 == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_Y2\n");
+        exit (EXIT_FAILURE);
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        h_X[i] = rand () / (float) RAND_MAX;
+        h_Y2[i] = h_Y1[i] = rand () / (float) RAND_MAX;
+    }
+
+    d_X = (float *) acc_copyin (&h_X[0], N * sizeof (float));
+    if (d_X == NULL)
+    {
+        fprintf (stderr, "copyin error h_X\n");
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    d_Y = (float *) acc_copyin (&h_Y1[0], N * sizeof (float));
+    if (d_Y == NULL)
+    {
+        fprintf (stderr, "copyin error h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    s = cublasSaxpy (h, N, &alpha, d_X, 1, d_Y, 1);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasSaxpy failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    acc_memcpy_from_device (&h_Y1[0], d_Y, N * sizeof (float));
+
+    context_check (pctx);
+
+#pragma acc parallel present (h_X[0:N]), copy (h_Y2[0:N]) copyin (alpha)
+    {
+        int i;
+
+        for (i = 0; i < N; i++)
+        {
+            h_Y2[i] = alpha * h_X[i] + h_Y2[i];
+        }
+    }
+
+    context_check (pctx);
+
+    error_norm = 0;
+    ref_norm = 0;
+
+    for (i = 0; i < N; ++i)
+    {
+        float diff;
+
+        diff = h_Y1[i] - h_Y2[i];
+        error_norm += diff * diff;
+        ref_norm += h_Y2[i] * h_Y2[i];
+    }
+
+    error_norm = (float) sqrt ((double) error_norm);
+    ref_norm = (float) sqrt ((double) ref_norm);
+
+    if ((fabs (ref_norm) < 1e-7) || ((error_norm / ref_norm) >= 1e-6f))
+    {
+        fprintf (stderr, "math error\n");
+        exit (EXIT_FAILURE);
+    }
+
+    free (h_X);
+    free (h_Y1);
+    free (h_Y2);
+
+    acc_free (d_X);
+    acc_free (d_Y);
+
+    context_check (pctx);
+
+    s = cublasDestroy (h);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasDestroy failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    acc_shutdown (acc_device_nvidia);
+
+    r = cuCtxGetCurrent (&ctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    if (!ctx)
+    {
+        fprintf (stderr, "Expected context\n");
+        exit (EXIT_FAILURE);
+    }
+
+    if (pctx != ctx)
+    {
+        fprintf (stderr, "Unexpected new context\n");
+        exit (EXIT_FAILURE);
+    }
+
+    return EXIT_SUCCESS;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/context-3.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/context-3.c
new file mode 100644
index 0000000..ccd276c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/context-3.c
@@ -0,0 +1,200 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda -lcublas -lcudart" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <cublas_v2.h>
+#include <openacc.h>
+
+void
+saxpy (int n, float a, float *x, float *y)
+{
+    int i;
+
+    for (i = 0; i < n; i++)
+    {
+        y[i] = a * x[i] + y[i];
+    }
+}
+
+void
+context_check (CUcontext ctx1)
+{
+    CUcontext ctx2, ctx3;
+    CUresult r;
+
+    r = cuCtxGetCurrent (&ctx2);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    if (ctx1 != ctx2)
+    {
+        fprintf (stderr, "new context established\n");
+        exit (EXIT_FAILURE);
+    }
+
+    ctx3 = (CUcontext) acc_get_current_cuda_context ();
+
+    if (ctx1 != ctx3)
+    {
+        fprintf (stderr, "acc_get_current_cuda_context returned wrong value\n");
+        exit (EXIT_FAILURE);
+    }
+
+    return;
+}
+
+int
+main (int argc, char **argv)
+{
+    cublasStatus_t s;
+    cublasHandle_t h;
+    CUcontext pctx;
+    CUresult r;
+    int i;
+    const int N = 256;
+    float *h_X, *h_Y1, *h_Y2;
+    float *d_X,*d_Y;
+    float alpha = 2.0f;
+    float error_norm;
+    float ref_norm;
+
+    /* Test 3 - OpenACC creates, cuBLAS shares.  */
+
+    acc_set_device_num (0, acc_device_nvidia);
+
+    r = cuCtxGetCurrent (&pctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    h_X = (float *) malloc (N * sizeof (float));
+    if (h_X == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_X\n");
+        exit (EXIT_FAILURE);
+    }
+
+    h_Y1 = (float *) malloc (N * sizeof (float));
+    if (h_Y1 == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    h_Y2 = (float *) malloc (N * sizeof (float));
+    if (h_Y2 == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_Y2\n");
+        exit (EXIT_FAILURE);
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        h_X[i] = rand () / (float) RAND_MAX;
+        h_Y2[i] = h_Y1[i] = rand () / (float) RAND_MAX;
+    }
+
+    d_X = (float *) acc_copyin (&h_X[0], N * sizeof (float));
+    if (d_X == NULL)
+    {
+        fprintf (stderr, "copyin error h_X\n");
+        exit (EXIT_FAILURE);
+    }
+
+    d_Y = (float *) acc_copyin (&h_Y1[0], N * sizeof (float));
+    if (d_Y == NULL)
+    {
+        fprintf (stderr, "copyin error h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    s = cublasCreate (&h);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasCreate failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    s = cublasSaxpy (h, N, &alpha, d_X, 1, d_Y, 1);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasSaxpy failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    acc_memcpy_from_device (&h_Y1[0], d_Y, N * sizeof (float));
+
+    context_check (pctx);
+
+    saxpy (N, alpha, h_X, h_Y2);
+
+    error_norm = 0;
+    ref_norm = 0;
+
+    for (i = 0; i < N; ++i)
+    {
+        float diff;
+
+        diff = h_Y1[i] - h_Y2[i];
+        error_norm += diff * diff;
+        ref_norm += h_Y2[i] * h_Y2[i];
+    }
+
+    error_norm = (float) sqrt ((double) error_norm);
+    ref_norm = (float) sqrt ((double) ref_norm);
+
+    if ((fabs (ref_norm) < 1e-7) || ((error_norm / ref_norm) >= 1e-6f))
+    {
+        fprintf (stderr, "math error\n");
+        exit (EXIT_FAILURE);
+    }
+
+    free (h_X);
+    free (h_Y1);
+    free (h_Y2);
+
+    acc_free (d_X);
+    acc_free (d_Y);
+
+    context_check (pctx);
+
+    s = cublasDestroy (h);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasDestroy failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    acc_shutdown (acc_device_nvidia);
+
+    r = cuCtxGetCurrent (&pctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    if (pctx)
+    {
+        fprintf (stderr, "Unexpected context\n");
+        exit (EXIT_FAILURE);
+    }
+
+    return EXIT_SUCCESS;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/context-4.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/context-4.c
new file mode 100644
index 0000000..71365e8
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/context-4.c
@@ -0,0 +1,213 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda -lcublas -lcudart" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <cublas_v2.h>
+#include <openacc.h>
+
+void
+saxpy (int n, float a, float *x, float *y)
+{
+    int i;
+
+    for (i = 0; i < n; i++)
+    {
+        y[i] = a * x[i] + y[i];
+    }
+}
+
+void
+context_check (CUcontext ctx1)
+{
+    CUcontext ctx2, ctx3;
+    CUresult r;
+
+    r = cuCtxGetCurrent (&ctx2);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    if (ctx1 != ctx2)
+    {
+        fprintf (stderr, "new context established\n");
+        exit (EXIT_FAILURE);
+    }
+
+    ctx3 = (CUcontext) acc_get_current_cuda_context ();
+
+    if (ctx1 != ctx3)
+    {
+        fprintf (stderr, "acc_get_current_cuda_context returned wrong value\n");
+        exit (EXIT_FAILURE);
+    }
+
+    return;
+}
+
+int
+main (int argc, char **argv)
+{
+    cublasStatus_t s;
+    cublasHandle_t h;
+    CUcontext pctx;
+    CUresult r;
+    int i;
+    const int N = 256;
+    float *h_X, *h_Y1, *h_Y2;
+    float *d_X,*d_Y;
+    float alpha = 2.0f;
+    float error_norm;
+    float ref_norm;
+
+    /* Test 4 - OpenACC creates, cuBLAS shares.  */
+
+    acc_set_device_num (0, acc_device_nvidia);
+
+    r = cuCtxGetCurrent (&pctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    h_X = (float *) malloc (N * sizeof (float));
+    if (h_X == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_X\n");
+        exit (EXIT_FAILURE);
+    }
+
+    h_Y1 = (float *) malloc (N * sizeof (float));
+    if (h_Y1 == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    h_Y2 = (float *) malloc (N * sizeof (float));
+    if (h_Y2 == 0)
+    {
+        fprintf (stderr, "malloc failed: for h_Y2\n");
+        exit (EXIT_FAILURE);
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        h_X[i] = rand () / (float) RAND_MAX;
+        h_Y2[i] = h_Y1[i] = rand () / (float) RAND_MAX;
+    }
+
+#pragma acc parallel copyin (h_X[0:N]), copy (h_Y2[0:N]) copy (alpha)
+    {
+        int i;
+
+        for (i = 0; i < N; i++)
+        {
+            h_Y2[i] = alpha * h_X[i] + h_Y2[i];
+        }
+    }
+
+    r = cuCtxGetCurrent (&pctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    d_X = (float *) acc_copyin (&h_X[0], N * sizeof (float));
+    if (d_X == NULL)
+    {
+        fprintf (stderr, "copyin error h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    d_Y = (float *) acc_copyin (&h_Y1[0], N * sizeof (float));
+    if (d_Y == NULL)
+    {
+        fprintf (stderr, "copyin error h_Y1\n");
+        exit (EXIT_FAILURE);
+    }
+
+    s = cublasCreate (&h);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasCreate failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    s = cublasSaxpy (h, N, &alpha, d_X, 1, d_Y, 1);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasSaxpy failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    acc_memcpy_from_device (&h_Y1[0], d_Y, N * sizeof (float));
+
+    context_check (pctx);
+
+    error_norm = 0;
+    ref_norm = 0;
+
+    for (i = 0; i < N; ++i)
+    {
+        float diff;
+
+        diff = h_Y1[i] - h_Y2[i];
+        error_norm += diff * diff;
+        ref_norm += h_Y2[i] * h_Y2[i];
+    }
+
+    error_norm = (float) sqrt ((double) error_norm);
+    ref_norm = (float) sqrt ((double) ref_norm);
+
+    if ((fabs (ref_norm) < 1e-7) || ((error_norm / ref_norm) >= 1e-6f))
+    {
+        fprintf (stderr, "math error\n");
+        exit (EXIT_FAILURE);
+    }
+
+    free (h_X);
+    free (h_Y1);
+    free (h_Y2);
+
+    acc_free (d_X);
+    acc_free (d_Y);
+
+    context_check (pctx);
+
+    s = cublasDestroy (h);
+    if (s != CUBLAS_STATUS_SUCCESS)
+    {
+        fprintf (stderr, "cublasDestroy failed: %d\n", s);
+        exit (EXIT_FAILURE);
+    }
+
+    context_check (pctx);
+
+    acc_shutdown (acc_device_nvidia);
+
+    r = cuCtxGetCurrent (&pctx);
+    if (r != CUDA_SUCCESS)
+    {
+        fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+        exit (EXIT_FAILURE);
+    }
+
+    if (pctx)
+    {
+        fprintf (stderr, "Unexpected context\n");
+        exit (EXIT_FAILURE);
+    }
+
+    return EXIT_SUCCESS;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-1.c
new file mode 100644
index 0000000..e7564cc
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-1.c
@@ -0,0 +1,188 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int i;
+
+int
+is_mapped (void *p, size_t n)
+{
+#if ACC_MEM_SHARED
+  return 1;
+#else
+  return acc_is_present (p, n);
+#endif
+}
+
+int main(void)
+{
+  int j;
+
+  i = -1;
+  j = -2;
+#pragma acc data copyin (i, j)
+  {
+    if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+      abort ();
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+  }
+  if (i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+#pragma acc data copyout (i, j)
+  {
+    if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+      abort ();
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+
+#pragma acc parallel present (i, j)
+    {
+      i = 4;
+      j = 2;
+    }
+  }
+  if (i != 4 || j != 2)
+    abort ();
+
+  i = -1;
+  j = -2;
+#pragma acc data create (i, j)
+  {
+    if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+      abort ();
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+  }
+  if (i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+#pragma acc data present_or_copyin (i, j)
+  {
+    if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+      abort ();
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+  }
+  if (i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+#pragma acc data present_or_copyout (i, j)
+  {
+    if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+      abort ();
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+
+#pragma acc parallel present (i, j)
+    {
+      i = 4;
+      j = 2;
+    }
+  }
+  if (i != 4 || j != 2)
+    abort ();
+
+  i = -1;
+  j = -2;
+#pragma acc data present_or_copy (i, j)
+  {
+    if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+      abort ();
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+  }
+#if ACC_MEM_SHARED
+  if (i != 2 || j != 1)
+    abort ();
+#else
+  if (i != -1 || j != -2)
+    abort ();
+#endif
+
+  i = -1;
+  j = -2;
+#pragma acc data present_or_create (i, j)
+  {
+    if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+  }
+
+  if (i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+#pragma acc data copyin (i, j)
+  {
+#pragma acc data present (i, j)
+    {
+      if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+        abort ();
+      if (i != -1 || j != -2)
+        abort ();
+      i = 2;
+      j = 1;
+      if (i != 2 || j != 1)
+        abort ();
+    }
+  }
+  if (i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+#pragma acc data
+  {
+#if !ACC_MEM_SHARED
+    if (is_mapped (&i, sizeof (i)) || is_mapped (&j, sizeof (j)))
+      abort ();
+#endif
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+  }
+  if (i != 2 || j != 1)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-2.c
new file mode 100644
index 0000000..f867a66
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-2.c
@@ -0,0 +1,162 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int
+main (int argc, char **argv)
+{
+  int N = 128; //1024 * 1024;
+  float *a, *b, *c, *d, *e;
+  int i;
+  int nbytes;
+
+  nbytes = N * sizeof (float);
+
+  a = (float *) malloc (nbytes);
+  b = (float *) malloc (nbytes);
+  c = (float *) malloc (nbytes);
+  d = (float *) malloc (nbytes);
+  e = (float *) malloc (nbytes);
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 3.0;
+      b[i] = 0.0;
+    }
+
+#pragma acc enter data copyin (a[0:N]) copyin (b[0:N]) copyin (N) async
+#pragma acc parallel async wait
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    b[i] = a[i];
+
+#pragma acc exit data copyout (a[0:N]) copyout (b[0:N]) wait async
+#pragma acc wait
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 3.0)
+	abort ();
+
+      if (b[i] != 3.0)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 2.0;
+      b[i] = 0.0;
+    }
+
+#pragma acc enter data copyin (a[0:N]) copyin (b[0:N]) copyin (N) async (1)
+#pragma acc parallel async (1)
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    b[i] = a[i];
+
+#pragma acc exit data copyout (a[0:N]) copyout (b[0:N]) wait (1) async (1)
+#pragma acc wait (1)
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 2.0)
+	abort ();
+
+      if (b[i] != 2.0)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 3.0;
+      b[i] = 0.0;
+      c[i] = 0.0;
+      d[i] = 0.0;
+    }
+
+#pragma acc enter data copyin (a[0:N]) copyin (b[0:N]) copyin (c[0:N]) copyin (d[0:N]) copyin (N) async (1)
+
+#pragma acc parallel async (1) wait (1)
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    b[i] = (a[i] * a[i] * a[i]) / a[i];
+
+#pragma acc parallel async (2) wait (1)
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    c[i] = (a[i] + a[i] + a[i] + a[i]) / a[i];
+
+#pragma acc parallel async (3) wait (1)
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    d[i] = ((a[i] * a[i] + a[i]) / a[i]) - a[i];
+
+#pragma acc exit data copyout (a[0:N]) copyout (b[0:N]) copyout (c[0:N]) copyout (d[0:N]) wait (1, 2, 3) async (1)
+#pragma acc wait (1)
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 3.0)
+	abort ();
+
+      if (b[i] != 9.0)
+	abort ();
+
+      if (c[i] != 4.0)
+	abort ();
+
+      if (d[i] != 1.0)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 2.0;
+      b[i] = 0.0;
+      c[i] = 0.0;
+      d[i] = 0.0;
+      e[i] = 0.0;
+    }
+
+#pragma acc enter data copyin (a[0:N]) copyin (b[0:N]) copyin (c[0:N]) copyin (d[0:N]) copyin (e[0:N]) copyin (N) async (1)
+
+#pragma acc parallel async (1) wait (1)
+  for (int ii = 0; ii < N; ii++)
+    b[ii] = (a[ii] * a[ii] * a[ii]) / a[ii];
+
+#pragma acc parallel async (2) wait (1)
+  for (int ii = 0; ii < N; ii++)
+    c[ii] = (a[ii] + a[ii] + a[ii] + a[ii]) / a[ii];
+
+#pragma acc parallel async (3) wait (1)
+  for (int ii = 0; ii < N; ii++)
+    d[ii] = ((a[ii] * a[ii] + a[ii]) / a[ii]) - a[ii];
+
+#pragma acc parallel wait (1) async (4)
+  for (int ii = 0; ii < N; ii++)
+    e[ii] = a[ii] + b[ii] + c[ii] + d[ii];
+
+#pragma acc exit data copyout (a[0:N]) copyout (b[0:N]) copyout (c[0:N]) copyout (d[0:N]) copyout (e[0:N]) wait (1, 2, 3, 4) async (1)
+#pragma acc wait (1)
+
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 2.0)
+	abort ();
+
+      if (b[i] != 4.0)
+	abort ();
+
+      if (c[i] != 4.0)
+	abort ();
+
+      if (d[i] != 1.0)
+	abort ();
+
+      if (e[i] != 11.0)
+	abort ();
+    }
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-3.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-3.c
new file mode 100644
index 0000000..747109f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-3.c
@@ -0,0 +1,166 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int
+main (int argc, char **argv)
+{
+  int N = 128; //1024 * 1024;
+  float *a, *b, *c, *d, *e;
+  int i;
+  int nbytes;
+
+  nbytes = N * sizeof (float);
+
+  a = (float *) malloc (nbytes);
+  b = (float *) malloc (nbytes);
+  c = (float *) malloc (nbytes);
+  d = (float *) malloc (nbytes);
+  e = (float *) malloc (nbytes);
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 3.0;
+      b[i] = 0.0;
+    }
+
+#pragma acc enter data copyin (a[0:N]) copyin (b[0:N]) copyin (N) async
+#pragma acc parallel async wait
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    b[i] = a[i];
+
+#pragma acc update host (a[0:N], b[0:N]) async wait
+#pragma acc wait
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 3.0)
+	abort ();
+
+      if (b[i] != 3.0)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 2.0;
+      b[i] = 0.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N]) async (1)
+#pragma acc parallel async (1)
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    b[i] = a[i];
+
+#pragma acc update host (a[0:N], b[0:N]) async (1) wait (1)
+#pragma acc wait (1)
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 2.0)
+	abort ();
+
+      if (b[i] != 2.0)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 3.0;
+      b[i] = 0.0;
+      c[i] = 0.0;
+      d[i] = 0.0;
+    }
+
+#pragma acc update device (a[0:N]) async (1)
+#pragma acc update device (b[0:N]) async (2)
+#pragma acc enter data copyin (c[0:N], d[0:N]) async (3)
+
+#pragma acc parallel async (1) wait (1,2)
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    b[i] = (a[i] * a[i] * a[i]) / a[i];
+
+#pragma acc parallel async (2) wait (1,3)
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    c[i] = (a[i] + a[i] + a[i] + a[i]) / a[i];
+
+#pragma acc parallel async (3) wait (1,3)
+#pragma acc loop
+  for (i = 0; i < N; i++)
+    d[i] = ((a[i] * a[i] + a[i]) / a[i]) - a[i];
+
+#pragma acc update host (a[0:N], b[0:N], c[0:N], d[0:N]) async (1) wait (1,2,3)
+#pragma acc wait (1)
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 3.0)
+	abort ();
+
+      if (b[i] != 9.0)
+	abort ();
+
+      if (c[i] != 4.0)
+	abort ();
+
+      if (d[i] != 1.0)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 2.0;
+      b[i] = 0.0;
+      c[i] = 0.0;
+      d[i] = 0.0;
+      e[i] = 0.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N], c[0:N], d[0:N]) async (1)
+#pragma acc enter data copyin (e[0:N]) async (5)
+
+#pragma acc parallel async (1) wait (1)
+  for (int ii = 0; ii < N; ii++)
+    b[ii] = (a[ii] * a[ii] * a[ii]) / a[ii];
+
+#pragma acc parallel async (2) wait (1)
+  for (int ii = 0; ii < N; ii++)
+    c[ii] = (a[ii] + a[ii] + a[ii] + a[ii]) / a[ii];
+
+#pragma acc parallel async (3) wait (1)
+  for (int ii = 0; ii < N; ii++)
+    d[ii] = ((a[ii] * a[ii] + a[ii]) / a[ii]) - a[ii];
+
+#pragma acc parallel wait (1,5) async (4)
+  for (int ii = 0; ii < N; ii++)
+    e[ii] = a[ii] + b[ii] + c[ii] + d[ii];
+
+#pragma acc exit data copyout (a[0:N]) copyout (b[0:N]) copyout (c[0:N]) copyout (d[0:N]) copyout (e[0:N]) wait (1, 2, 3, 4) async (1)
+#pragma acc exit data delete (N)
+#pragma acc wait (1)
+
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 2.0)
+	abort ();
+
+      if (b[i] != 4.0)
+	abort ();
+
+      if (c[i] != 4.0)
+	abort ();
+
+      if (d[i] != 1.0)
+	abort ();
+
+      if (e[i] != 11.0)
+	abort ();
+    }
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-1.c
new file mode 100644
index 0000000..83c0a42
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-1.c
@@ -0,0 +1,19 @@
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+
+int
+main (int argc, char *argv[])
+{
+  int i;
+
+  acc_copyin (&i, sizeof i);
+
+#pragma acc data copy (i)
+  ++i;
+
+  return 0;
+}
+
+/* { dg-shouldfail "" }
+   { dg-output "Trying to map into device .* object when .* is already mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-2.c
new file mode 100644
index 0000000..137d8ce
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-2.c
@@ -0,0 +1,16 @@
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+int
+main (int argc, char *argv[])
+{
+  int i;
+
+#pragma acc data present_or_copy (i)
+#pragma acc data copyout (i)
+  ++i;
+
+  return 0;
+}
+
+/* { dg-shouldfail "" }
+   { dg-output "Trying to map into device .* object when .* is already mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-3.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-3.c
new file mode 100644
index 0000000..b993b78
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-3.c
@@ -0,0 +1,17 @@
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+
+int
+main (int argc, char *argv[])
+{
+  int i;
+
+#pragma acc data present_or_copy (i)
+  acc_copyin (&i, sizeof i);
+
+  return 0;
+}
+
+/* { dg-shouldfail "" }
+   { dg-output "already mapped to" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-4.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-4.c
new file mode 100644
index 0000000..82523f4
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-4.c
@@ -0,0 +1,17 @@
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+
+int
+main (int argc, char *argv[])
+{
+  int i;
+
+  acc_present_or_copyin (&i, sizeof i);
+  acc_copyin (&i, sizeof i);
+
+  return 0;
+}
+
+/* { dg-shouldfail "" }
+   { dg-output "already mapped to" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-5.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-5.c
new file mode 100644
index 0000000..4961fe5
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-5.c
@@ -0,0 +1,17 @@
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+
+int
+main (int argc, char *argv[])
+{
+  int i;
+
+#pragma acc enter data create (i)
+  acc_copyin (&i, sizeof i);
+
+  return 0;
+}
+
+/* { dg-shouldfail "" }
+   { dg-output "already mapped to" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-6.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-6.c
new file mode 100644
index 0000000..77b56a9
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-6.c
@@ -0,0 +1,17 @@
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+
+int
+main (int argc, char *argv[])
+{
+  int i;
+
+  acc_present_or_copyin (&i, sizeof i);
+#pragma acc enter data create (i)
+
+  return 0;
+}
+
+/* { dg-shouldfail "" }
+   { dg-output "already mapped to" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-7.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-7.c
new file mode 100644
index 0000000..b08417b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-7.c
@@ -0,0 +1,17 @@
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+
+int
+main (int argc, char *argv[])
+{
+  int i;
+
+#pragma acc enter data create (i)
+  acc_create (&i, sizeof i);
+
+  return 0;
+}
+
+/* { dg-shouldfail "" }
+   { dg-output "already mapped to" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-8.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-8.c
new file mode 100644
index 0000000..a50f7de
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/data-already-8.c
@@ -0,0 +1,16 @@
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+int
+main (int argc, char *argv[])
+{
+  int i;
+
+#pragma acc data create (i)
+#pragma acc parallel copyin (i)
+  ++i;
+
+  return 0;
+}
+
+/* { dg-shouldfail "" }
+   { dg-output "Trying to map into device .* object when .* is already mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/deviceptr-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/deviceptr-1.c
new file mode 100644
index 0000000..e271a37
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/deviceptr-1.c
@@ -0,0 +1,32 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int main (void)
+{
+  void *a, *a_1, *a_2;
+
+#define A (void *) 0x123
+  a = A;
+
+#pragma acc data copyout (a_1, a_2)
+#pragma acc kernels deviceptr (a)
+  {
+    a_1 = a;
+    a_2 = &a;
+  }
+
+  if (a != A)
+    abort ();
+  if (a_1 != a)
+    abort ();
+#if ACC_MEM_SHARED
+  if (a_2 != &a)
+    abort ();
+#else
+  if (a_2 == &a)
+    abort ();
+#endif
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/if-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/if-1.c
new file mode 100644
index 0000000..184b355
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/if-1.c
@@ -0,0 +1,613 @@
+/* { dg-do run } */
+/* { dg-additional-options "-fno-builtin-acc_on_device" } */
+
+#include <openacc.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+#define N   32
+
+int
+main(int argc, char **argv)
+{
+    float *a, *b, *d_a, *d_b, exp, exp2;
+    int i;
+    const int one = 1;
+    const int zero = 0;
+    int n;
+
+    a = (float *) malloc (N * sizeof (float));
+    b = (float *) malloc (N * sizeof (float));
+    d_a = (float *) acc_malloc (N * sizeof (float));
+    d_b = (float *) acc_malloc (N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+        a[i] = 4.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+#if ACC_MEM_SHARED
+    exp = 5.0;
+#else
+    exp = 4.0;
+#endif
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != exp)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 16.0;
+
+#pragma acc parallel if(0)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 17.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 8.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(one)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+#if ACC_MEM_SHARED
+    exp = 9.0;
+#else
+    exp = 8.0;
+#endif
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != exp)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 22.0;
+
+#pragma acc parallel if(zero)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 23.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 16.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(true)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+#if ACC_MEM_SHARED
+    exp = 17.0;
+#else
+    exp = 16.0;
+#endif
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != exp)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 76.0;
+
+#pragma acc parallel if(false)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 77.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 22.0;
+
+    n = 1;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(n)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+#if ACC_MEM_SHARED
+    exp = 23.0;
+#else
+    exp = 22.0;
+#endif
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != exp)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 18.0;
+
+    n = 0;
+
+#pragma acc parallel if(n)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 19.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 49.0;
+
+    n = 1;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(n + n)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+#if ACC_MEM_SHARED
+    exp = 50.0;
+#else
+    exp = 49.0;
+#endif
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != exp)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 38.0;
+
+    n = 0;
+
+#pragma acc parallel if(n + n)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 39.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 91.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(-2)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+#if ACC_MEM_SHARED
+    exp = 92.0;
+#else
+    exp = 91.0;
+#endif
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != exp)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 43.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(one == 1)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+#if ACC_MEM_SHARED
+    exp = 44.0;
+#else
+    exp = 43.0;
+#endif
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != exp)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+        a[i] = 87.0;
+
+#pragma acc parallel if(one == 0)
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            if (acc_on_device (acc_device_host))
+                b[ii] = a[ii] + 1;
+            else
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 88.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 9.0;
+    }
+
+#if ACC_MEM_SHARED
+    exp = 0.0;
+    exp2 = 0.0;
+#else
+    acc_map_data (a, d_a, N * sizeof (float));
+    acc_map_data (b, d_b, N * sizeof (float));
+    exp = 3.0;
+    exp2 = 9.0;
+#endif
+
+#pragma acc update device(a[0:N], b[0:N]) if(1)
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 0.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc update host(a[0:N], b[0:N]) if(1)
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != exp)
+            abort();
+
+        if (b[i] != exp2)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 12.0;
+    }
+
+#pragma acc update device(a[0:N], b[0:N]) if(0)
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 0.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc update host(a[0:N], b[0:N]) if(1)
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != exp)
+            abort();
+
+        if (b[i] != exp2)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 26.0;
+        b[i] = 21.0;
+    }
+
+#pragma acc update device(a[0:N], b[0:N]) if(1)
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 0.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc update host(a[0:N], b[0:N]) if(0)
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 0.0)
+            abort();
+
+        if (b[i] != 0.0)
+            abort();
+    }
+
+#if !ACC_MEM_SHARED
+    acc_unmap_data (a);
+    acc_unmap_data (b);
+#endif
+
+    acc_free (d_a);
+    acc_free (d_b);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc data copyin(a[0:N]) copyout(b[0:N]) if(1)
+{
+#pragma acc parallel present(a[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            b[ii] = a[ii];
+        }
+    }
+}
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 4.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 8.0;
+        b[i] = 1.0;
+    }
+
+#pragma acc data copyin(a[0:N]) copyout(b[0:N]) if(0)
+{
+#if !ACC_MEM_SHARED
+    if (acc_is_present (a, N * sizeof (float)))
+        abort ();
+#endif
+
+#if !ACC_MEM_SHARED
+    if (acc_is_present (b, N * sizeof (float)))
+        abort ();
+#endif
+}
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 18.0;
+        b[i] = 21.0;
+    }
+
+#pragma acc data copyin(a[0:N]) if(1)
+{
+#if !ACC_MEM_SHARED
+    if (!acc_is_present (a, N * sizeof (float)))
+        abort ();
+#endif
+
+#pragma acc data copyout(b[0:N]) if(0)
+    {
+#if !ACC_MEM_SHARED
+        if (acc_is_present (b, N * sizeof (float)))
+            abort ();
+#endif
+
+#pragma acc data copyout(b[0:N]) if(1)
+        {
+#pragma acc parallel present(a[0:N]) present(b[0:N])
+            {
+                int ii;
+
+                for (ii = 0; ii < N; ii++)
+                {
+                    b[ii] = a[ii];
+                }
+            }
+        }
+
+#if !ACC_MEM_SHARED
+        if (acc_is_present (b, N * sizeof (float)))
+            abort ();
+#endif
+    }
+}
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 18.0)
+            abort ();
+    }
+
+#pragma acc enter data copyin (b[0:N]) if (0)
+
+#if !ACC_MEM_SHARED
+    if (acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+#pragma acc exit data delete (b[0:N]) if (0)
+
+#pragma acc enter data copyin (b[0:N]) if (1)
+
+#if !ACC_MEM_SHARED
+    if (!acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+#pragma acc exit data delete (b[0:N]) if (1)
+
+#if !ACC_MEM_SHARED
+    if (acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+#pragma acc enter data copyin (b[0:N]) if (zero)
+
+#if !ACC_MEM_SHARED
+    if (acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+#pragma acc exit data delete (b[0:N]) if (zero)
+
+#pragma acc enter data copyin (b[0:N]) if (one)
+
+#if !ACC_MEM_SHARED
+    if (!acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+#pragma acc exit data delete (b[0:N]) if (one)
+
+#if !ACC_MEM_SHARED
+    if (acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+#pragma acc enter data copyin (b[0:N]) if (one == 0)
+
+#if !ACC_MEM_SHARED
+    if (acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+#pragma acc exit data delete (b[0:N]) if (one == 0)
+
+#pragma acc enter data copyin (b[0:N]) if (one == 1)
+
+#if !ACC_MEM_SHARED
+    if (!acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+#pragma acc exit data delete (b[0:N]) if (one == 1)
+
+#if !ACC_MEM_SHARED
+    if (acc_is_present (b, N * sizeof (float)))
+	abort ();
+#endif
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/kernels-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/kernels-1.c
new file mode 100644
index 0000000..3acfdf5
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/kernels-1.c
@@ -0,0 +1,184 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int i;
+
+int main (void)
+{
+  int j, v;
+
+#if 0
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) copyin (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != -1 || j != -2)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) copyout (i, j)
+  {
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) copy (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) create (i, j)
+  {
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != -1 || j != -2)
+    abort ();
+#endif
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) present_or_copyin (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1)
+    abort ();
+#if ACC_MEM_SHARED
+  if (i != 2 || j != 1)
+    abort ();
+#else
+  if (i != -1 || j != -2)
+    abort ();
+#endif
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) present_or_copyout (i, j)
+  {
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) present_or_copy (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) present_or_create (i, j)
+  {
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1)
+    abort ();
+#if ACC_MEM_SHARED
+  if (i != 2 || j != 1)
+    abort ();
+#else
+  if (i != -1 || j != -2)
+    abort ();
+#endif
+
+#if 0
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v) present (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+#endif
+
+#if 0
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc kernels /* copyout */ present_or_copyout (v)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+#endif
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/kernels-empty.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/kernels-empty.c
new file mode 100644
index 0000000..a68a7cd
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/kernels-empty.c
@@ -0,0 +1,6 @@
+int
+main (void)
+{
+#pragma acc kernels
+  ;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-1.c
new file mode 100644
index 0000000..17129d8
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-1.c
@@ -0,0 +1,24 @@
+/* { dg-do run } */
+
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  acc_device_t devtype = acc_device_host;
+
+#if ACC_DEVICE_TYPE_nvidia
+  devtype = acc_device_nvidia;
+
+  if (acc_get_num_devices (devtype) == 0)
+    return 0;
+#endif
+
+  acc_init (devtype);
+
+  acc_init (devtype);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: device already active" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-10.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-10.c
new file mode 100644
index 0000000..cf1af8c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-10.c
@@ -0,0 +1,58 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  void *d;
+  acc_device_t devtype = acc_device_host;
+
+#if ACC_DEVICE_TYPE_nvidia
+  devtype = acc_device_nvidia;
+
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+#endif
+
+  acc_init (devtype);
+
+  d = acc_malloc (0);
+  if (d != NULL)
+    abort ();
+
+  acc_free (0);
+
+  acc_shutdown (devtype);
+
+  acc_set_device_type (devtype);
+
+  d = acc_malloc (0);
+  if (d != NULL)
+    abort ();
+
+  acc_shutdown (devtype);
+
+  acc_init (devtype);
+
+  d = acc_malloc (1024);
+  if (d == NULL)
+    abort ();
+
+  acc_free (d);
+
+  acc_shutdown (devtype);
+
+  acc_set_device_type (devtype);
+
+  d = acc_malloc (1024);
+  if (d == NULL)
+    abort ();
+
+  acc_free (d);
+
+  acc_shutdown (devtype);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-11.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-11.c
new file mode 100644
index 0000000..eccdb8c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-11.c
@@ -0,0 +1,23 @@
+/* Only nvptx plugin does the required error checking.
+   { dg-do run { target openacc_nvidia_accel_selected } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+#include <stdint.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 512;
+  void *d;
+
+  d = acc_malloc (N);
+  if (d == NULL)
+    abort ();
+
+  acc_free ((void *)((uintptr_t) d + (uintptr_t) (N >> 1)));
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: mem free failed 1" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-12.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-12.c
new file mode 100644
index 0000000..b46f590
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-12.c
@@ -0,0 +1,37 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  (void) acc_copyin (h, N);
+
+  memset (h, 0, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-13.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-13.c
new file mode 100644
index 0000000..7098ef3
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-13.c
@@ -0,0 +1,60 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+
+  if (acc_is_present (h, 1) != 1)
+    abort ();
+
+  if (acc_is_present (h, N + 1) != 0)
+    abort ();
+
+  if (acc_is_present (h + 1, N) != 0)
+    abort ();
+
+  if (acc_is_present (h - 1, N) != 0)
+    abort ();
+
+  if (acc_is_present (h - 1, N - 1) != 0)
+    abort ();
+
+  if (acc_is_present (h + N, 0) != 0)
+    abort ();
+
+  if (acc_is_present (h + N, N) != 0)
+    abort ();
+
+  if (acc_is_present (0, N) != 0)
+    abort ();
+   
+  if (acc_is_present (h, 0) != 0)
+    abort ();
+
+  acc_free (d);
+
+  if (acc_is_present (h, 1) != 0)
+    abort ();
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-14.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-14.c
new file mode 100644
index 0000000..a9632f7
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-14.c
@@ -0,0 +1,61 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+
+  if (acc_is_present (h, 1) != 1)
+    abort ();
+
+  if (acc_is_present (h + N - 1, 1) != 1)
+    abort ();
+
+  if (acc_is_present (h - 1, 1) != 0)
+    abort ();
+
+  if (acc_is_present (h + N, 1) != 0)
+    abort ();
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, 1) != 1)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, N - i) != 1)
+	abort ();
+    }
+
+  acc_free (d);
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, N - i) != 0)
+	abort ();
+    }
+
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-15.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-15.c
new file mode 100644
index 0000000..4f6a731
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-15.c
@@ -0,0 +1,33 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  (void) acc_copyin (h, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, 1) != 0)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-16.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-16.c
new file mode 100644
index 0000000..9d277ac
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-16.c
@@ -0,0 +1,29 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  (void) acc_copyin (h, N);
+
+  (void) acc_copyin (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+256\] already mapped to \[\h+,\+256\]" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-17.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-17.c
new file mode 100644
index 0000000..5ff894c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-17.c
@@ -0,0 +1,31 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  (void) acc_copyin (h, N);
+
+  acc_copyout (h, N);
+
+  acc_copyout (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-18.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-18.c
new file mode 100644
index 0000000..2bc32637
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-18.c
@@ -0,0 +1,34 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+
+  acc_free (d);
+
+  acc_copyout (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-19.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-19.c
new file mode 100644
index 0000000..3581616
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-19.c
@@ -0,0 +1,60 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h[N];
+
+  for (i = 0; i < N; i++)
+    {
+      int j;
+      unsigned char *p;
+
+      h[i] = (unsigned char *) malloc (N);
+      p = h[i];
+
+      for (j = 0; j < N; j++)
+	{
+	  p[j] = i;
+	}
+
+      (void) acc_copyin (p, N);
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      memset (h[i], 0, i);
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      int j;
+      unsigned char *p;
+
+      acc_copyout (h[i], N);
+
+      p = h[i];
+
+      for (j = 0; j < N; j++)
+	{
+	  if (p[j] != i)
+	    abort ();
+	}
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      free (h[i]);
+    }
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-2.c
new file mode 100644
index 0000000..9a4501f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-2.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  acc_device_t devtype = acc_device_host;
+
+#if ACC_DEVICE_TYPE_nvidia
+  devtype = acc_device_nvidia;
+
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+#endif
+
+  acc_init (devtype);
+
+  acc_shutdown (devtype);
+
+  acc_shutdown (devtype);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: no device initialized" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-20.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-20.c
new file mode 100644
index 0000000..b379a8f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-20.c
@@ -0,0 +1,29 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  (void) acc_copyin (h, N);
+
+  acc_copyout (h, N + 1);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] surounds2 \[\h+,\+257\]" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-21.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-21.c
new file mode 100644
index 0000000..3a67400
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-21.c
@@ -0,0 +1,29 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  (void) acc_copyin (h, N);
+
+  acc_copyout (h, 0);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,0\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-22.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-22.c
new file mode 100644
index 0000000..2b86da8
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-22.c
@@ -0,0 +1,29 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  (void) acc_copyin (h, N);
+
+  acc_copyout (h + 1, N - 1);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] surrounds2 \[\h+,\+255\]" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-23.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-23.c
new file mode 100644
index 0000000..38f236d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-23.c
@@ -0,0 +1,39 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h1, *h2;
+
+  h1 = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h1[i] = 0xab;
+    }
+
+  (void) acc_copyin (h1, N);
+
+  h2 = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h2[i] = 0xde;
+    }
+
+  (void) acc_copyin (h2, N);
+
+  acc_copyout (h1, N + N);
+
+  free (h1);
+  free (h2);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] surrounds2 \[\h+,\+512\]" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-24.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-24.c
new file mode 100644
index 0000000..d7de8e3
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-24.c
@@ -0,0 +1,55 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_create (h, N);
+  if (!d)
+    abort ();
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, 1) != 1)
+	abort ();
+    }
+
+  acc_delete (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, 1) != 0)
+	abort ();
+    }
+
+  d = acc_create (h, N);
+  if (!d)
+    abort ();
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, 1) != 1)
+	abort ();
+    }
+
+  acc_delete (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, 1) != 0)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-25.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-25.c
new file mode 100644
index 0000000..1145828
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-25.c
@@ -0,0 +1,30 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_create (h, N);
+  if (!d)
+    abort ();
+
+  d = acc_create (h, N);
+  if (!d)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] already mapped to \[\h+,256\]" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-26.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-26.c
new file mode 100644
index 0000000..a23f56e
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-26.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_create (h, 0);
+  if (!d)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+0\] is a bad range" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-27.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-27.c
new file mode 100644
index 0000000..074fddb
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-27.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_create (0, N);
+  if (!d)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\)\] is a bad range" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-28.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-28.c
new file mode 100644
index 0000000..027f7cc
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-28.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_create (h, N);
+  if (!d)
+    abort ();
+
+  acc_delete (0, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),256\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-29.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-29.c
new file mode 100644
index 0000000..a66de0f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-29.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_create (h, N);
+  if (!d)
+    abort ();
+
+  acc_delete (h, 0);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,0\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-3.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-3.c
new file mode 100644
index 0000000..e823a41
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-3.c
@@ -0,0 +1,15 @@
+/* { dg-do run } */
+
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  acc_init (acc_device_host);
+
+  acc_shutdown (acc_device_not_host);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: device 4(4) is initialized" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-30.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-30.c
new file mode 100644
index 0000000..ce2bdb4
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-30.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_create (h, N);
+  if (!d)
+    abort ();
+
+  acc_delete (h, N - 2);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] surrounds2 \[\h+,\+254\]" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-31.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-31.c
new file mode 100644
index 0000000..25ce5a9
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-31.c
@@ -0,0 +1,27 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_present_or_create (h, N);
+  if (!d)
+    abort ();
+
+  if (acc_is_present (h, 1) != 1)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-32.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-32.c
new file mode 100644
index 0000000..e3f87a8
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-32.c
@@ -0,0 +1,38 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d1, *d2;
+
+  h = (unsigned char *) malloc (N);
+
+  d1 = acc_present_or_create (h, N);
+  if (!d1)
+    abort ();
+
+  d2 = acc_present_or_create (h, N);
+  if (!d2)
+    abort ();
+
+  if (d1 != d2)
+    abort ();
+
+  d2 = acc_pcreate (h, N);
+  if (!d2)
+    abort ();
+
+  if (d1 != d2)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-33.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-33.c
new file mode 100644
index 0000000..4abaa02
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-33.c
@@ -0,0 +1,31 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d1, *d2;
+
+  h = (unsigned char *) malloc (N);
+
+  d1 = acc_present_or_create (h, N);
+  if (!d1)
+    abort ();
+
+  d2 = acc_present_or_create (h, N - 2);
+  if (!d2)
+    abort ();
+
+  if (d1 != d2)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-34.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-34.c
new file mode 100644
index 0000000..32d5d51
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-34.c
@@ -0,0 +1,33 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d1, *d2;
+
+  h = (unsigned char *) malloc (N);
+
+  d1 = acc_present_or_create (h, N);
+  if (!d1)
+    abort ();
+
+  d2 = acc_present_or_create (h + 2, N);
+  if (!d2)
+    abort ();
+
+  if (d1 != d2)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+256\] not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-35.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-35.c
new file mode 100644
index 0000000..ca8edab
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-35.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_present_or_create (0, N);
+  if (!d)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),+256\] is a bad range" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-36.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-36.c
new file mode 100644
index 0000000..cb29397
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-36.c
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_present_or_create (h, 0);
+  if (!d)
+    abort ();
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+0\] is a bad range" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-37.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-37.c
new file mode 100644
index 0000000..5a7d533
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-37.c
@@ -0,0 +1,40 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_present_or_copyin (h, N);
+  if (!d)
+    abort ();
+
+  memset (&h[0], 0, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-38.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-38.c
new file mode 100644
index 0000000..05d8498
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-38.c
@@ -0,0 +1,64 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d1, *d2;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d1 = acc_present_or_copyin (h, N);
+  if (!d1)
+    abort ();
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = 0xab;
+    }
+
+  d2 = acc_present_or_copyin (h, N);
+  if (!d2)
+    abort ();
+
+  if (d1 != d2)
+    abort ();
+
+  memset (&h[0], 0, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  d2 = acc_pcopyin (h, N);
+  if (!d2)
+    abort ();
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-39.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-39.c
new file mode 100644
index 0000000..db1e0b3
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-39.c
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_present_or_copyin (0, N);
+  if (!d)
+    abort ();
+
+  memset (&h[0], 0, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),+256\] is a bad range" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-4.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-4.c
new file mode 100644
index 0000000..060275b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-4.c
@@ -0,0 +1,13 @@
+/* { dg-do run } */
+
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  acc_init ((acc_device_t) 99);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: device 99 is out of range" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-40.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-40.c
new file mode 100644
index 0000000..cb6c422
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-40.c
@@ -0,0 +1,42 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_present_or_copyin (h, 0);
+  if (!d)
+    abort ();
+
+  memset (&h[0], 0, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+0\] is a bad range" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-41.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-41.c
new file mode 100644
index 0000000..01c5f3c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-41.c
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+  if (!d)
+    abort ();
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = 0xab;
+    }
+
+  acc_update_device (h, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != 0xab)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-42.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-42.c
new file mode 100644
index 0000000..d577fe3
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-42.c
@@ -0,0 +1,35 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  acc_update_device (h, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != 0xab)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-43.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-43.c
new file mode 100644
index 0000000..ceeb155
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-43.c
@@ -0,0 +1,45 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+  if (!d)
+    abort ();
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = 0xab;
+    }
+
+  acc_update_device (0, N);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != 0xab)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),256\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-44.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-44.c
new file mode 100644
index 0000000..0cabb0d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-44.c
@@ -0,0 +1,45 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+  if (!d)
+    abort ();
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = 0xab;
+    }
+
+  acc_update_device (h, 0);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != 0xab)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,0\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-45.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-45.c
new file mode 100644
index 0000000..f9a6294
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-45.c
@@ -0,0 +1,50 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+  if (!d)
+    abort ();
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = 0xab;
+    }
+
+  acc_update_device (h, N - 2);
+
+  acc_copyout (h, N);
+
+  for (i = 0; i < N - 2; i++)
+    {
+      if (h[i] != 0xab)
+	abort ();
+    }
+
+  for (i = N - 2; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-46.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-46.c
new file mode 100644
index 0000000..b195725
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-46.c
@@ -0,0 +1,42 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+  if (!d)
+    abort ();
+
+  memset (&h[0], 0, N);
+
+  acc_update_self (h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-47.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-47.c
new file mode 100644
index 0000000..a7ff904
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-47.c
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+  if (!d)
+    abort ();
+
+  memset (&h[0], 0, N);
+
+  acc_update_self (0, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),256\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-48.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-48.c
new file mode 100644
index 0000000..01d3c6c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-48.c
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+  if (!d)
+    abort ();
+
+  memset (&h[0], 0, N);
+
+  acc_update_self (h, 0);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,0\] is not mapped" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-49.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-49.c
new file mode 100644
index 0000000..a33324c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-49.c
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_copyin (h, N);
+  if (!d)
+    abort ();
+
+  memset (&h[0], 0, N);
+
+  acc_update_self (h, N - 2);
+
+  for (i = 0; i < N - 2; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  for (i = N - 2; i < N; i++)
+    {
+      if (h[i] != 0)
+	abort ();
+    }
+
+  acc_delete (h, N);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-5.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-5.c
new file mode 100644
index 0000000..961a62c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-5.c
@@ -0,0 +1,40 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  if (acc_get_device_type () == acc_device_default)
+    abort ();
+
+  acc_init (acc_device_default);
+
+  if (acc_get_device_type () == acc_device_default)
+    abort ();
+
+  acc_shutdown (acc_device_default);
+
+  if (acc_get_num_devices (acc_device_nvidia) != 0)
+    {
+      acc_init (acc_device_nvidia);
+
+      if (acc_get_device_type () != acc_device_nvidia)
+        abort ();
+
+      acc_shutdown (acc_device_nvidia);
+
+      acc_init (acc_device_default);
+
+      acc_set_device_type (acc_device_nvidia);
+
+      if (acc_get_device_type () != acc_device_nvidia)
+        abort ();
+
+      acc_shutdown (acc_device_nvidia);
+    }
+
+  return 0;
+
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-50.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-50.c
new file mode 100644
index 0000000..e8294e1
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-50.c
@@ -0,0 +1,30 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  acc_map_data (h, d, N);
+
+  if (acc_is_present (h, N) != 1)
+    abort ();
+
+  acc_unmap_data (h);
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-51.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-51.c
new file mode 100644
index 0000000..29d28f2
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-51.c
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h[N];
+  void *d[N];
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = (unsigned char *) malloc (N);
+      d[i] = acc_malloc (N);
+
+      acc_map_data (h[i], d[i], N);
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h[i], N) != 1)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      acc_unmap_data (h[i]);
+
+      if (acc_is_present (h[i], N) != 0)
+	abort ();
+
+      acc_free (d[i]);
+      free (h[i]);
+    }
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-52.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-52.c
new file mode 100644
index 0000000..780db31
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-52.c
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  acc_map_data (0, d, N);
+
+  acc_unmap_data (h);
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[(nil),+256\]->\[\h+,\+256\] is a bad map" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-53.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-53.c
new file mode 100644
index 0000000..657adde
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-53.c
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  acc_map_data (h, 0, N);
+
+  acc_unmap_data (h);
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+256\]->\[(nil),\+256\] is a bad map" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-54.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-54.c
new file mode 100644
index 0000000..1f3df80
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-54.c
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  acc_map_data (h, d, 0);
+
+  acc_unmap_data (h);
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+0\]->\[\h+,\+0\] is a bad map" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-55.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-55.c
new file mode 100644
index 0000000..286653f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-55.c
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+#include <stdint.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  int i;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      acc_map_data ((void *)((uintptr_t) h + (uintptr_t) i),
+                    				(void *)((uintptr_t) d + (uintptr_t) i), 1);
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + 1, 1) != 1)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      acc_unmap_data (h + i);
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + 1, 1) != 0)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-56.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-56.c
new file mode 100644
index 0000000..e3f5a80
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-56.c
@@ -0,0 +1,33 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  acc_map_data (h, d, N >> 1);
+
+  if (acc_is_present (h, 1) != 1)
+    abort ();
+
+  if (acc_is_present (h + (N >> 1), 1) != 0)
+    abort ();
+
+  acc_unmap_data (h);
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-57.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-57.c
new file mode 100644
index 0000000..f9043a4
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-57.c
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  acc_map_data (h, d, N);
+
+  acc_unmap_data (d);
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \h+ is not a mapped block" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-58.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-58.c
new file mode 100644
index 0000000..9d6e27d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-58.c
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  acc_map_data (h, d, N);
+
+  acc_unmap_data (0);
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: \(nil\) is not a mapped block" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-59.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-59.c
new file mode 100644
index 0000000..2f087ae
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-59.c
@@ -0,0 +1,55 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+#include <stdint.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  d = acc_malloc (N);
+
+  acc_map_data (h, d, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_hostptr ((void *)((uintptr_t) d + (uintptr_t) i)) !=
+                            (void *)((uintptr_t) h + (uintptr_t) i))
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_deviceptr ((void *)((uintptr_t) h + (uintptr_t) i)) !=
+                            (void *)((uintptr_t) d + (uintptr_t) i))
+	abort ();
+    }
+
+  acc_unmap_data (h);
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_hostptr ((void *)((uintptr_t) d + (uintptr_t) i)) != 0)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_deviceptr (h + i) != 0)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-6.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-6.c
new file mode 100644
index 0000000..afdd480
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-6.c
@@ -0,0 +1,39 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  int devnum;
+
+  if (acc_get_device_type () == acc_device_default)
+    abort ();
+
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+
+  acc_set_device_type (acc_device_nvidia);
+
+  if (acc_get_device_type () != acc_device_nvidia)
+    abort ();
+
+  acc_shutdown (acc_device_nvidia);
+
+  acc_set_device_type (acc_device_nvidia);
+
+  if (acc_get_device_type () != acc_device_nvidia)
+    abort ();
+
+  devnum = acc_get_num_devices (acc_device_host);
+  if (devnum != 1)
+    abort ();
+
+  acc_shutdown (acc_device_nvidia);
+
+  if (acc_get_device_type () == acc_device_default)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-60.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-60.c
new file mode 100644
index 0000000..ccae728e
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-60.c
@@ -0,0 +1,54 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_memcpy_to_device (d, h, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, 1) != 0)
+	abort ();
+    }
+
+  memset (&h[0], 0, N);
+
+  acc_memcpy_from_device (h, d, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_is_present (h + i, 1) != 0)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-61.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-61.c
new file mode 100644
index 0000000..ce66ced
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-61.c
@@ -0,0 +1,70 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h[N];
+  void *d[N];
+
+  for (i = 0; i < N; i++)
+    {
+      int j;
+      unsigned char *p;
+
+      h[i] = (unsigned char *) malloc (N);
+
+      p = h[i];
+
+      for (j = 0; j < N; j++)
+	{
+	  p[j] = i;
+	}
+
+      d[i] = acc_malloc (N);
+
+      acc_memcpy_to_device (d[i], h[i], N);
+
+      for (j = 0; j < N; j++)
+	{
+	  if (acc_is_present (h[i] + j, 1) != 0)
+	    abort ();
+	}
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      int j;
+      unsigned char *p;
+
+      memset (h[i], 0, N);
+
+      acc_memcpy_from_device (h[i], d[i], N);
+
+      p = h[i];
+
+      for (j = 0; j < N; j++)
+	{
+	  if (p[j] != i)
+	    abort ();
+	}
+
+      for (j = 0; j < N; j++)
+	{
+	  if (acc_is_present (h[i] + j, 1) != 0)
+	    abort ();
+	}
+
+      acc_free (d[i]);
+
+      free (h[i]);
+    }
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-62.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-62.c
new file mode 100644
index 0000000..e6178e2
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-62.c
@@ -0,0 +1,49 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  acc_init (acc_device_nvidia);
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_memcpy_to_device (d, h, N);
+
+  memset (&h[0], 0, N);
+
+  acc_memcpy_to_device (d, h, N << 1);
+
+  acc_memcpy_from_device (h, d, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid size" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-63.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-63.c
new file mode 100644
index 0000000..ca237ec
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-63.c
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_memcpy_to_device (0, h, N);
+
+  memset (&h[0], 0, N);
+
+  acc_memcpy_from_device (h, d, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid device address" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-64.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-64.c
new file mode 100644
index 0000000..850fd2e
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-64.c
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_memcpy_to_device (d, 0, N);
+
+  memset (&h[0], 0, N);
+
+  acc_memcpy_from_device (h, d, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid host address" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-65.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-65.c
new file mode 100644
index 0000000..26c8cef
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-65.c
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_memcpy_to_device (d, d, N);
+
+  memset (&h[0], 0, N);
+
+  acc_memcpy_from_device (h, d, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid host or device address" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-66.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-66.c
new file mode 100644
index 0000000..398dc2a
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-66.c
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  acc_init (acc_device_default);
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_memcpy_to_device (d, h, N);
+
+  memset (&h[0], 0, N);
+
+  acc_memcpy_to_device (d, h, 0);
+
+  acc_memcpy_from_device (h, d, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  acc_shutdown (acc_device_default);
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-67.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-67.c
new file mode 100644
index 0000000..01b8b2d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-67.c
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_memcpy_to_device (d, h, N);
+
+  memset (&h[0], 0, N);
+
+  acc_memcpy_from_device (0, d, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid host address" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-68.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-68.c
new file mode 100644
index 0000000..3ff5bd7
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-68.c
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 256;
+  int i;
+  unsigned char *h;
+  void *d;
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_memcpy_to_device (d, h, N);
+
+  memset (&h[0], 0, N);
+
+  acc_memcpy_from_device (h, 0, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (h[i] != i)
+	abort ();
+    }
+
+  acc_free (d);
+
+  free (h);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid device address" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-69.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-69.c
new file mode 100644
index 0000000..5462f12
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-69.c
@@ -0,0 +1,124 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  CUstream stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  stream = (CUstream) acc_get_cuda_stream (0);
+  if (stream != NULL)
+    abort ();
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (0, stream))
+    abort ();
+
+  r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+      abort ();
+    }
+
+  if (acc_async_test (0) != 0)
+    {
+      fprintf (stderr, "asynchronous operation not running\n");
+      abort ();
+    }
+
+  sleep (1);
+
+  if (acc_async_test (0) != 1)
+    {
+      fprintf (stderr, "found asynchronous operation still running\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-7.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-7.c
new file mode 100644
index 0000000..e78734b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-7.c
@@ -0,0 +1,18 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  if (acc_get_num_devices (acc_device_none) != 0)
+    abort ();
+
+  if (acc_get_num_devices (acc_device_host) == 0)
+    abort ();
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-70.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-70.c
new file mode 100644
index 0000000..912b266
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-70.c
@@ -0,0 +1,136 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  const int N = 10;
+  int i;
+  CUstream streams[N];
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  for (i = 0; i < N; i++)
+    {
+      streams[i] = (CUstream) acc_get_cuda_stream (i);
+      if (streams[i] != NULL)
+	abort ();
+
+      r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+        if (!acc_set_cuda_stream (i, streams[i]))
+	  abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+	  abort ();
+	}
+
+      if (acc_async_test (i) != 0)
+	{
+	  fprintf (stderr, "asynchronous operation not running\n");
+	  abort ();
+	}
+    }
+
+  sleep ((int) (dtime / 1000.0f) + 1);
+
+  for (i = 0; i < N; i++)
+    {
+      if (acc_async_test (i) != 1)
+	{
+	  fprintf (stderr, "found asynchronous operation still running\n");
+	  abort ();
+	}
+    }
+
+  acc_unmap_data (a);
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-71.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-71.c
new file mode 100644
index 0000000..a045379
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-71.c
@@ -0,0 +1,119 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  CUstream stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+  acc_set_cuda_stream (0, stream);
+
+  r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+      abort ();
+    }
+
+  if (acc_async_test (1) != 0)
+    {
+      fprintf (stderr, "asynchronous operation not running\n");
+      abort ();
+    }
+
+  sleep ((int) (dtime / 1000.0f) + 1);
+
+  if (acc_async_test (1) != 1)
+    {
+      fprintf (stderr, "found asynchronous operation still running\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: unknown async \d" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-72.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-72.c
new file mode 100644
index 0000000..e383ba0
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-72.c
@@ -0,0 +1,121 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  CUstream stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (0, stream))
+    abort ();
+    
+  r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+      abort ();
+    }
+
+  if (acc_async_test_all () != 0)
+    {
+      fprintf (stderr, "asynchronous operation not running\n");
+      abort ();
+    }
+
+  sleep ((int) (dtime / 1000.f) + 1);
+
+  if (acc_async_test_all () != 1)
+    {
+      fprintf (stderr, "found asynchronous operation still running\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-73.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-73.c
new file mode 100644
index 0000000..43a8b7e
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-73.c
@@ -0,0 +1,134 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  const int N = 10;
+  int i;
+  CUstream streams[N];
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  for (i = 0; i < N; i++)
+    {
+      streams[i] = (CUstream) acc_get_cuda_stream (i);
+      if (streams[i] != NULL)
+	abort ();
+
+      r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+        if (!acc_set_cuda_stream (i, streams[i]))
+	  abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+	  abort ();
+	}
+
+    }
+
+  if (acc_async_test_all () != 0)
+    {
+      fprintf (stderr, "asynchronous operation not running\n");
+      abort ();
+    }
+
+  sleep ((int) (dtime / 1000.0f) + 1);
+
+  if (acc_async_test_all () != 1)
+    {
+      fprintf (stderr, "asynchronous operation not running\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-74.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-74.c
new file mode 100644
index 0000000..0726ee4
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-74.c
@@ -0,0 +1,139 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  CUstream stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float atime, dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  stream = (CUstream) acc_get_cuda_stream (0);
+  if (stream != NULL)
+    abort ();
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (0, stream))
+    abort ();
+
+  init_timers (1);
+
+  start_timer (0);
+
+  r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+      abort ();
+    }
+
+  acc_wait (0);
+
+  atime = stop_timer (0);
+
+  if (atime < dtime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  start_timer (0);
+
+  acc_wait (0);
+
+  atime = stop_timer (0);
+
+  if (0.010 < atime)
+    {
+      fprintf (stderr, "actual time too long\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  fini_timers ();
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-75.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-75.c
new file mode 100644
index 0000000..1942211
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-75.c
@@ -0,0 +1,141 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  int N;
+  int i;
+  CUstream stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float atime, dtime, hitime, lotime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  N = nprocs;
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  stream = (CUstream) acc_get_cuda_stream (0);
+  if (stream != NULL)
+    abort ();
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (0, stream))
+    abort ();
+
+  init_timers (1);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  start_timer (0);
+
+  for (i = 0; i < N; i++)
+    {
+      r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+	  abort ();
+	}
+
+      acc_wait (0);
+    }
+
+  atime = stop_timer (0);
+
+  hitime = dtime * N;
+  hitime += hitime * 0.02;
+
+  lotime = dtime * N;
+  lotime -= lotime * 0.02;
+
+  if (atime > hitime || atime < lotime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  fini_timers ();
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-76.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-76.c
new file mode 100644
index 0000000..11d9d62
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-76.c
@@ -0,0 +1,147 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  int N;
+  int i;
+  CUstream *streams;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float atime, dtime, hitime, lotime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  N = nprocs;
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  streams = (CUstream *) malloc (N * sizeof (void *));
+
+  for (i = 0; i < N; i++)
+    {
+      streams[i] = (CUstream) acc_get_cuda_stream (i);
+      if (streams[i] != NULL)
+	abort ();
+
+      r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+        if (!acc_set_cuda_stream (i, streams[i]))
+	  abort ();
+    }
+
+  init_timers (1);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  start_timer (0);
+
+  for (i = 0; i < N; i++)
+    {
+      r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+	  abort ();
+	}
+
+      acc_wait (i);
+    }
+
+  atime = stop_timer (0);
+
+  hitime = dtime * N;
+  hitime += hitime * 0.02;
+
+  lotime = dtime * N;
+  lotime -= lotime * 0.02;
+
+  if (atime > hitime || atime < lotime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  fini_timers ();
+
+  free (streams);
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-77.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-77.c
new file mode 100644
index 0000000..e47212b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-77.c
@@ -0,0 +1,135 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  CUstream stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float atime, dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+  acc_set_cuda_stream (0, stream);
+
+  init_timers (1);
+
+  start_timer (0);
+
+  r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+      abort ();
+    }
+
+  acc_wait (1);
+
+  atime = stop_timer (0);
+
+  if (atime < dtime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  start_timer (0);
+
+  acc_wait (1);
+
+  atime = stop_timer (0);
+
+  if (0.010 < atime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  fini_timers ();
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: unknown async \d" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-78.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-78.c
new file mode 100644
index 0000000..4f58fb2
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-78.c
@@ -0,0 +1,140 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  CUstream stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float atime, dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  stream = (CUstream) acc_get_cuda_stream (0);
+  if (stream != NULL)
+    abort ();
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (0, stream))
+    abort ();
+
+  init_timers (1);
+
+  start_timer (0);
+
+  r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+      abort ();
+    }
+
+  acc_wait_all ();
+
+  atime = stop_timer (0);
+
+  if (atime < dtime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  start_timer (0);
+
+  acc_wait_all ();
+
+  atime = stop_timer (0);
+
+  if (0.010 < atime)
+    {
+      fprintf (stderr, "actual time too long\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  fini_timers ();
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-79.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-79.c
new file mode 100644
index 0000000..ef3df13
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-79.c
@@ -0,0 +1,167 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  int N;
+  int i;
+  CUstream stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float atime, dtime, hitime, lotime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  devnum = 2;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  N = nprocs;
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (1, stream))
+    abort ();
+
+  stream = (CUstream) acc_get_cuda_stream (0);
+  if (stream != NULL)
+    abort ();
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (0, stream))
+    abort ();
+
+  init_timers (1);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  start_timer (0);
+
+  for (i = 0; i < N; i++)
+    {
+      r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+	  abort ();
+	}
+    }
+
+  acc_wait_async (0, 1);
+
+  if (acc_async_test (0) != 0)
+    abort ();
+
+  if (acc_async_test (1) != 0)
+    abort ();
+
+  acc_wait (1);
+
+  atime = stop_timer (0);
+
+  if (acc_async_test (0) != 1)
+    abort ();
+
+  if (acc_async_test (1) != 1)
+    abort ();
+
+  hitime = dtime * N;
+  hitime += hitime * 0.02;
+
+  lotime = dtime * N;
+  lotime -= lotime * 0.02;
+
+  if (atime > hitime || atime < lotime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  fini_timers ();
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-80.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-80.c
new file mode 100644
index 0000000..0b5ec24
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-80.c
@@ -0,0 +1,132 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  CUstream stream;
+  int N;
+  int i;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float atime, dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 200.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  N = nprocs;
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+  acc_set_cuda_stream (1, stream);
+
+  init_timers (1);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  start_timer (0);
+
+  for (i = 0; i < N; i++)
+    {
+      r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+	  abort ();
+	}
+    }
+
+  acc_wait_async (1, 1);
+
+  acc_wait (1);
+
+  atime = stop_timer (0);
+
+  if (atime < dtime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  fini_timers ();
+
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-shouldfail "libgomp: identical parameters" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-81.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-81.c
new file mode 100644
index 0000000..d5f18f0
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-81.c
@@ -0,0 +1,211 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay;
+  CUmodule module;
+  CUresult r;
+  int N;
+  int i;
+  CUstream *streams, stream;
+  unsigned long *a, *d_a, dticks;
+  int nbytes;
+  float atime, dtime;
+  void *kargs[2];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay, module, "delay");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = nprocs * sizeof (unsigned long);
+
+  dtime = 500.0;
+
+  dticks = (unsigned long) (dtime * clkrate);
+
+  N = nprocs;
+
+  a = (unsigned long *) malloc (nbytes);
+  d_a = (unsigned long *) acc_malloc (nbytes);
+
+  acc_map_data (a, d_a, nbytes);
+
+  streams = (CUstream *) malloc (N * sizeof (void *));
+
+  for (i = 0; i < N; i++)
+    {
+      streams[i] = (CUstream) acc_get_cuda_stream (i);
+      if (streams[i] != NULL)
+	abort ();
+
+      r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+        if (!acc_set_cuda_stream (i, streams[i]))
+	  abort ();
+    }
+
+  init_timers (1);
+
+  kargs[0] = (void *) &d_a;
+  kargs[1] = (void *) &dticks;
+
+  stream = (CUstream) acc_get_cuda_stream (N);
+  if (stream != NULL)
+    abort ();
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (N, stream))
+    abort ();
+
+  start_timer (0);
+
+  for (i = 0; i < N; i++)
+    {
+      r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+	  abort ();
+	}
+    }
+
+  acc_wait_all_async (N);
+
+  for (i = 0; i <= N; i++)
+    {
+      if (acc_async_test (i) != 0)
+	abort ();
+    }
+
+  acc_wait (N);
+
+  for (i = 0; i <= N; i++)
+    {
+      if (acc_async_test (i) != 1)
+	abort ();
+    }
+
+  atime = stop_timer (0);
+
+  if (atime < dtime)
+    {
+      fprintf (stderr, "actual time < delay time\n");
+      abort ();
+    }
+
+  start_timer (0);
+
+  stream = (CUstream) acc_get_cuda_stream (N + 1);
+  if (stream != NULL)
+    abort ();
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (N + 1, stream))
+    abort ();
+
+  acc_wait_all_async (N + 1);
+
+  acc_wait (N + 1);
+
+  atime = stop_timer (0);
+
+  if (0.10 < atime)
+    {
+      fprintf (stderr, "actual time too long\n");
+      abort ();
+    }
+
+  start_timer (0);
+
+  acc_wait_all_async (N);
+
+  acc_wait (N);
+
+  atime = stop_timer (0);
+
+  if (0.10 < atime)
+    {
+      fprintf (stderr, "actual time too long\n");
+      abort ();
+    }
+
+  acc_unmap_data (a);
+
+  fini_timers ();
+
+  free (streams);
+  free (a);
+  acc_free (d_a);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-82.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-82.c
new file mode 100644
index 0000000..be30a7f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-82.c
@@ -0,0 +1,144 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  CUdevice dev;
+  CUfunction delay2;
+  CUmodule module;
+  CUresult r;
+  int N;
+  int i;
+  CUstream *streams;
+  unsigned long **a, **d_a, *tid, ticks;
+  int nbytes;
+  void *kargs[3];
+  int clkrate;
+  int devnum, nprocs;
+
+  acc_init (acc_device_nvidia);
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+
+  r = cuDeviceGet (&dev, devnum);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+      abort ();
+    }
+
+  r =
+    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+			  dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleLoad (&module, "subr.ptx");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuModuleGetFunction (&delay2, module, "delay2");
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+      abort ();
+    }
+
+  nbytes = sizeof (int);
+
+  ticks = (unsigned long) (200.0 * clkrate);
+
+  N = nprocs;
+
+  streams = (CUstream *) malloc (N * sizeof (void *));
+
+  a = (unsigned long **) malloc (N * sizeof (unsigned long *));
+  d_a = (unsigned long **) malloc (N * sizeof (unsigned long *));
+  tid = (unsigned long *) malloc (N * sizeof (unsigned long));
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = (unsigned long *) malloc (sizeof (unsigned long));
+      *a[i] = N;
+      d_a[i] = (unsigned long *) acc_malloc (nbytes);
+      tid[i] = i;
+
+      acc_map_data (a[i], d_a[i], nbytes);
+
+      streams[i] = (CUstream) acc_get_cuda_stream (i);
+      if (streams[i] != NULL)
+        abort ();
+
+      r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+      if (r != CUDA_SUCCESS)
+        {
+          fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+          abort ();
+        }
+
+       if (!acc_set_cuda_stream (i, streams[i]))
+        abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      kargs[0] = (void *) &d_a[i];
+      kargs[1] = (void *) &ticks;
+      kargs[2] = (void *) &tid[i];
+
+      r = cuLaunchKernel (delay2, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+	  abort ();
+	}
+
+      ticks = (unsigned long) (50.0 * clkrate);
+    }
+
+  acc_wait_all_async (0);
+
+  for (i = 0; i < N; i++)
+    {
+      acc_copyout (a[i], nbytes);
+      if (*a[i] != i)
+	abort ();
+    }
+
+  free (streams);
+
+  for (i = 0; i < N; i++)
+    {
+      free (a[i]);
+    }
+
+  free (a);
+  free (d_a);
+  free (tid);
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-83.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-83.c
new file mode 100644
index 0000000..1c2e52b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-83.c
@@ -0,0 +1,58 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+  float atime;
+  CUstream stream;
+  CUresult r;
+
+  acc_init (acc_device_nvidia);
+
+  (void) acc_get_device_num (acc_device_nvidia);
+
+  init_timers (1);
+
+  stream = (CUstream) acc_get_cuda_stream (0);
+  if (stream != NULL)
+    abort ();
+
+  r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  if (!acc_set_cuda_stream (0, stream))
+    abort ();
+
+  start_timer (0);
+
+  acc_wait_all_async (0);
+
+  acc_wait (0);
+
+  atime = stop_timer (0);
+
+  if (0.010 < atime)
+    {
+      fprintf (stderr, "actual time too long\n");
+      abort ();
+    }
+
+  fini_timers ();
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-84.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-84.c
new file mode 100644
index 0000000..786b908
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-84.c
@@ -0,0 +1,66 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 100;
+  int i;
+  CUstream *streams;
+  CUstream s;
+  CUresult r;
+
+  acc_init (acc_device_nvidia);
+
+  (void) acc_get_device_num (acc_device_nvidia);
+
+  streams = (CUstream *) malloc (N * sizeof (void *));
+
+  for (i = 0; i < N; i++)
+    {
+      streams[i] = (CUstream) acc_get_cuda_stream (i);
+      if (streams[i] != NULL)
+	abort ();
+
+      r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+        if (!acc_set_cuda_stream (i, streams[i]))
+	  abort ();
+    }
+
+  for (i = 0; i < N; i++)
+    {
+      int j;
+      int cnt;
+
+      cnt = 0;
+
+      s = streams[i];
+
+      for (j = 0; j < N; j++)
+	{
+	  if (s == streams[j])
+	    cnt++;
+	}
+
+      if (cnt != 1)
+	abort ();
+    }
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-85.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-85.c
new file mode 100644
index 0000000..cf925a7
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-85.c
@@ -0,0 +1,52 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <stdio.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 100;
+  int i;
+  CUstream *streams;
+  CUstream s;
+  CUresult r;
+
+  acc_init (acc_device_nvidia);
+
+  (void) acc_get_device_num (acc_device_nvidia);
+
+  streams = (CUstream *) malloc (N * sizeof (void *));
+
+  for (i = 0; i < N; i++)
+    {
+      streams[i] = (CUstream) acc_get_cuda_stream (i);
+      if (streams[i] != NULL)
+	abort ();
+
+      r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+        if (!acc_set_cuda_stream (i, streams[i]))
+	  abort ();
+    }
+
+  s = NULL;
+
+  if (acc_set_cuda_stream (N + 1, s) != 0)
+    abort ();
+
+  acc_shutdown (acc_device_nvidia);
+
+  exit (0);
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-86.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-86.c
new file mode 100644
index 0000000..b8a8ee9
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-86.c
@@ -0,0 +1,42 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+
+  if (acc_get_current_cuda_device () != 0)
+    abort ();
+
+  acc_init (acc_device_host);
+
+  if (acc_get_current_cuda_device () != 0)
+    abort ();
+
+  acc_shutdown (acc_device_host);
+
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+
+  if (acc_get_current_cuda_device () != 0)
+    abort ();
+
+  acc_init (acc_device_nvidia);
+
+  if (acc_get_current_cuda_device () == 0)
+    abort ();
+
+  acc_shutdown (acc_device_nvidia);
+
+  if (acc_get_current_cuda_device () != 0)
+    abort ();
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-87.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-87.c
new file mode 100644
index 0000000..147d443
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-87.c
@@ -0,0 +1,42 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+
+  if (acc_get_current_cuda_context () != 0)
+    abort ();
+
+  acc_init (acc_device_host);
+
+  if (acc_get_current_cuda_context () != 0)
+    abort ();
+
+  acc_shutdown (acc_device_host);
+
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+
+  if (acc_get_current_cuda_context () != 0)
+    abort ();
+
+  acc_init (acc_device_nvidia);
+
+  if (acc_get_current_cuda_context () == 0)
+    abort ();
+
+  acc_shutdown (acc_device_nvidia);
+
+  if (acc_get_current_cuda_context () != 0)
+    abort ();
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-88.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-88.c
new file mode 100644
index 0000000..10f4ad8
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-88.c
@@ -0,0 +1,111 @@
+/* { dg-do run } */
+
+#include <stdio.h>
+#include <pthread.h>
+#include <string.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <openacc.h>
+
+unsigned char *x;
+void *d_x;
+const int N = 256;
+
+static void *
+test (void *arg)
+{
+  int i;
+
+  if (acc_get_current_cuda_context () != NULL)
+    abort ();
+
+  if (acc_is_present (x, N) != 1)
+    abort ();
+
+  memset (x, 0, N);
+
+  acc_copyout (x, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (x[i] != i)
+	abort ();
+
+      x[i] = N - i - 1;
+    }
+
+  d_x = acc_copyin (x, N);
+
+  return 0;
+}
+
+int
+main (int argc, char **argv)
+{
+  const int nthreads = 1;
+  int i;
+  pthread_attr_t attr;
+  pthread_t *tid;
+
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+
+  acc_init (acc_device_nvidia);
+
+  x = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      x[i] = i;
+    }
+
+  d_x = acc_copyin (x, N);
+
+  if (acc_is_present (x, N) != 1)
+    abort ();
+
+  if (pthread_attr_init (&attr) != 0)
+    perror ("pthread_attr_init failed");
+
+  tid = (pthread_t *) malloc (nthreads * sizeof (pthread_t));
+
+  for (i = 0; i < nthreads; i++)
+    {
+      if (pthread_create (&tid[i], &attr, &test, (void *) (unsigned long) (i))
+	  != 0)
+	perror ("pthread_create failed");
+    }
+
+  if (pthread_attr_destroy (&attr) != 0)
+    perror ("pthread_attr_destroy failed");
+
+  for (i = 0; i < nthreads; i++)
+    {
+      void *res;
+
+      if (pthread_join (tid[i], &res) != 0)
+	perror ("pthread join failed");
+    }
+
+  if (acc_is_present (x, N) != 1)
+    abort ();
+
+  memset (x, 0, N);
+
+  acc_copyout (x, N);
+
+  for (i = 0; i < N; i++)
+    {
+      if (x[i] != N - i - 1)
+	abort ();
+    }
+
+  if (acc_is_present (x, N) != 0)
+    abort ();
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-89.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-89.c
new file mode 100644
index 0000000..061c409
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-89.c
@@ -0,0 +1,118 @@
+/* { dg-do run } */
+
+#include <stdio.h>
+#include <pthread.h>
+#include <string.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <ctype.h>
+#include <openacc.h>
+
+unsigned char **x;
+void **d_x;
+const int N = 16;
+const int NTHREADS = 32;
+
+static void *
+test (void *arg)
+{
+  int i;
+  int tid;
+  unsigned char *p;
+  int devnum;
+
+  tid = (int) (long) arg;
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+  acc_set_device_num (devnum, acc_device_nvidia);
+
+  if (acc_get_current_cuda_context () == NULL)
+    abort ();
+
+  p = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      p[i] = tid;
+    }
+
+  x[tid] = p;
+
+  d_x[tid] = acc_copyin (p, N);
+
+  return 0;
+}
+
+int
+main (int argc, char **argv)
+{
+  int i;
+  pthread_attr_t attr;
+  pthread_t *tid;
+
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+
+  acc_init (acc_device_nvidia);
+
+  x = (unsigned char **) malloc (NTHREADS * N);
+  d_x = (void **) malloc (NTHREADS * N);
+
+  if (pthread_attr_init (&attr) != 0)
+    perror ("pthread_attr_init failed");
+
+  tid = (pthread_t *) malloc (NTHREADS * sizeof (pthread_t));
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      if (pthread_create (&tid[i], &attr, &test, (void *) (unsigned long) (i))
+	  != 0)
+	perror ("pthread_create failed");
+    }
+
+  if (pthread_attr_destroy (&attr) != 0)
+    perror ("pthread_attr_destroy failed");
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      void *res;
+
+      if (pthread_join (tid[i], &res) != 0)
+	perror ("pthread join failed");
+    }
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      if (acc_is_present (x[i], N) != 1)
+	abort ();
+    }
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      memset (x[i], 0, N);
+      acc_copyout (x[i], N);
+    }
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      unsigned char *p;
+      int j;
+
+      p = x[i];
+
+      for (j = 0; j < N; j++)
+	{
+	  if (p[j] != i)
+	    abort ();
+	}
+
+      if (acc_is_present (x[i], N) != 0)
+	abort ();
+    }
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-9.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-9.c
new file mode 100644
index 0000000..84045db
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-9.c
@@ -0,0 +1,70 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+  int i;
+  int num_devices;
+  int devnum;
+  acc_device_t devtype = acc_device_host;
+
+#if ACC_DEVICE_TYPE_nvidia
+  devtype = acc_device_nvidia;
+#endif
+
+  num_devices = acc_get_num_devices (devtype);
+  if (num_devices == 0)
+    return 0;
+
+  acc_init (devtype);
+
+  for (i = 0; i < num_devices; i++)
+    {
+      acc_set_device_num (i, devtype);
+      devnum = acc_get_device_num (devtype);
+      if (devnum != i)
+	abort ();
+    }
+
+  acc_shutdown (devtype);
+
+  num_devices = acc_get_num_devices (devtype);
+  if (num_devices == 0)
+    abort ();
+
+  for (i = 0; i < num_devices; i++)
+    {
+      acc_set_device_num (i, devtype);
+      devnum = acc_get_device_num (devtype);
+      if (devnum != i)
+	abort ();
+    }
+
+  acc_shutdown (devtype);
+
+  acc_init (devtype);
+
+  acc_set_device_num (0, devtype);
+
+  devnum = acc_get_device_num (devtype);
+  if (devnum != 0)
+    abort ();
+
+  if (num_devices > 1)
+    {
+      acc_set_device_num (1, (acc_device_t) 0);
+
+      devnum = acc_get_device_num (devtype);
+      if (devnum != 0)
+	abort ();
+  }
+
+  acc_shutdown (devtype);
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-90.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-90.c
new file mode 100644
index 0000000..d17755b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-90.c
@@ -0,0 +1,137 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <pthread.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <ctype.h>
+#include <openacc.h>
+#include <cuda.h>
+
+unsigned char **x;
+void **d_x;
+const int N = 16;
+const int NTHREADS = 32;
+
+static void *
+test (void *arg)
+{
+  int i;
+  int tid;
+  unsigned char *p;
+  int devnum;
+
+  tid = (int) (long) arg;
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+  acc_set_device_num (devnum, acc_device_nvidia);
+
+  if (acc_get_current_cuda_context () == NULL)
+    abort ();
+
+  p = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      p[i] = tid;
+    }
+
+  x[tid] = p;
+
+  d_x[tid] = acc_copyin (p, N);
+
+  acc_wait_all ();
+
+  return 0;
+}
+
+int
+main (int argc, char **argv)
+{
+  int i;
+  pthread_attr_t attr;
+  pthread_t *tid;
+  CUresult r;
+  CUstream s;
+
+  acc_init (acc_device_nvidia);
+
+  x = (unsigned char **) malloc (NTHREADS * N);
+  d_x = (void **) malloc (NTHREADS * N);
+
+  if (pthread_attr_init (&attr) != 0)
+    perror ("pthread_attr_init failed");
+
+  tid = (pthread_t *) malloc (NTHREADS * sizeof (pthread_t));
+
+  r = cuStreamCreate (&s, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+  if (!acc_set_cuda_stream (0, s))
+	  abort ();
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      if (pthread_create (&tid[i], &attr, &test, (void *) (unsigned long) (i))
+	  != 0)
+	perror ("pthread_create failed");
+    }
+
+  if (pthread_attr_destroy (&attr) != 0)
+    perror ("pthread_attr_destroy failed");
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      void *res;
+
+      if (pthread_join (tid[i], &res) != 0)
+	perror ("pthread join failed");
+    }
+
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      if (acc_is_present (x[i], N) != 1)
+	abort ();
+    }
+
+  acc_get_cuda_stream (1);
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      memset (x[i], 0, N);
+      acc_copyout (x[i], N);
+    }
+
+  acc_wait_all ();
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      unsigned char *p;
+      int j;
+
+      p = x[i];
+
+      for (j = 0; j < N; j++)
+	{
+	  if (p[j] != i)
+	    abort ();
+	}
+
+      if (acc_is_present (x[i], N) != 0)
+	abort ();
+    }
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-91.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-91.c
new file mode 100644
index 0000000..e00ef4f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-91.c
@@ -0,0 +1,84 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <sys/time.h>
+#include <stdio.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+  const int N = 1024 * 1024;
+  int i;
+  unsigned char *h;
+  void *d;
+  float async, sync;
+  struct timeval start, stop;
+  CUresult r;
+  CUstream s;
+
+  acc_init (acc_device_nvidia);
+
+  h = (unsigned char *) malloc (N);
+
+  for (i = 0; i < N; i++)
+    {
+      h[i] = i;
+    }
+
+  d = acc_malloc (N);
+
+  acc_map_data (h, d, N);
+
+  gettimeofday (&start, NULL);
+
+  for (i = 0; i < 100; i++)
+    {
+#pragma acc update device(h[0:N])
+    }
+
+  gettimeofday (&stop, NULL);
+
+  sync = (float) (stop.tv_sec - start.tv_sec);
+  sync += (float) ((stop.tv_usec - start.tv_usec) / 1000000.0);
+
+  gettimeofday (&start, NULL);
+
+  r = cuStreamCreate (&s, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+	  abort ();
+	}
+
+  if (!acc_set_cuda_stream (0, s))
+	  abort ();
+
+  for (i = 0; i < 100; i++)
+    {
+#pragma acc update device(h[0:N]) async(0)
+    }
+
+  acc_wait_all ();
+
+  gettimeofday (&stop, NULL);
+
+  async = (float) (stop.tv_sec - start.tv_sec);
+  async += (float) ((stop.tv_usec - start.tv_usec) / 1000000.0);
+
+  if (async > (sync * 1.5))
+    abort ();
+
+  acc_free (d);
+
+  free (h);
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-92.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-92.c
new file mode 100644
index 0000000..18193e0
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-92.c
@@ -0,0 +1,112 @@
+/* { dg-do run } */
+
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <ctype.h>
+#include <openacc.h>
+
+unsigned char **x;
+void **d_x;
+const int N = 32;
+const int NTHREADS = 32;
+
+static void *
+test (void *arg)
+{
+  int i;
+  int tid;
+  unsigned char *p;
+  int devnum;
+
+  tid = (int) (long) arg;
+
+  devnum = acc_get_device_num (acc_device_nvidia);
+  acc_set_device_num (devnum, acc_device_nvidia);
+
+  if (acc_get_current_cuda_context () == NULL)
+    abort ();
+
+  acc_copyout (x[tid], N);
+
+  p = x[tid];
+
+  for (i = 0; i < N; i++)
+    {
+      if (p[i] != i)
+	abort ();
+    }
+
+  return 0;
+}
+
+int
+main (int argc, char **argv)
+{
+  int i;
+  pthread_attr_t attr;
+  pthread_t *tid;
+  unsigned char *p;
+
+  if (acc_get_num_devices (acc_device_nvidia) == 0)
+    return 0;
+
+  acc_init (acc_device_nvidia);
+
+  x = (unsigned char **) malloc (NTHREADS * N);
+  d_x = (void **) malloc (NTHREADS * N);
+
+  for (i = 0; i < N; i++)
+    {
+      int j;
+
+      p = (unsigned char *) malloc (N);
+
+      x[i] = p;
+
+      for (j = 0; j < N; j++)
+	{
+	  p[j] = j;
+	}
+
+      d_x[i] = acc_copyin (p, N);
+    }
+
+  if (pthread_attr_init (&attr) != 0)
+    perror ("pthread_attr_init failed");
+
+  tid = (pthread_t *) malloc (NTHREADS * sizeof (pthread_t));
+
+  acc_get_cuda_stream (1);
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      if (pthread_create (&tid[i], &attr, &test, (void *) (unsigned long) (i))
+	  != 0)
+	perror ("pthread_create failed");
+    }
+
+  if (pthread_attr_destroy (&attr) != 0)
+    perror ("pthread_attr_destroy failed");
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      void *res;
+
+      if (pthread_join (tid[i], &res) != 0)
+	perror ("pthread join failed");
+    }
+
+  for (i = 0; i < NTHREADS; i++)
+    {
+      if (acc_is_present (x[i], N) != 0)
+	abort ();
+    }
+
+  acc_shutdown (acc_device_nvidia);
+
+  return 0;
+}
+
+/* { dg-output "" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/nested-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/nested-1.c
new file mode 100644
index 0000000..ededf2b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/nested-1.c
@@ -0,0 +1,680 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+    int N = 8;
+    float *a, *b, *c, *d;
+    int i;
+
+    a = (float *) malloc (N * sizeof (float));
+    b = (float *) malloc (N * sizeof (float));
+    c = (float *) malloc (N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc data copyin (a[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 1.0;
+    }
+
+#pragma acc data copyin (a[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+    d = (float *) acc_copyin (&a[0], N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc data present_or_copyin (a[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc data copyin (a[0:N]) present_or_copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 2.0;
+    }
+
+    d = (float *) acc_copyin (&b[0], N * sizeof (float));
+
+#pragma acc data copyin (a[0:N]) present_or_copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 2.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 4.0;
+    }
+
+#pragma acc data copy (a[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                a[ii] = a[ii] + 1;
+                b[ii] = a[ii] + 2;
+            }
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 7.0;
+    }
+
+#pragma acc data present_or_copy (a[0:N]) present_or_copy (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                a[ii] = a[ii] + 1;
+                b[ii] = b[ii] + 2;
+            }
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 9.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 7.0;
+    }
+
+    d = (float *) acc_copyin (&a[0], N * sizeof (float));
+    d = (float *) acc_copyin (&b[0], N * sizeof (float));
+
+#pragma acc data present_or_copy (a[0:N]) present_or_copy (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                a[ii] = a[ii] + 1;
+                b[ii] = b[ii] + 2;
+            }
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 7.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    d = (float *) acc_deviceptr (&a[0]);
+    acc_unmap_data (&a[0]);
+    acc_free (d);
+
+    d = (float *) acc_deviceptr (&b[0]);
+    acc_unmap_data (&b[0]);
+    acc_free (d);
+
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 7.0;
+    }
+
+#pragma acc data copyin (a[0:N]) create (c[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                c[ii] = a[ii];
+                b[ii] = c[ii];
+            }
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&c[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 8.0;
+    }
+
+#pragma acc data copyin (a[0:N]) present_or_create (c[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                c[ii] = a[ii];
+                b[ii] = c[ii];
+            }
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 4.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&c[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 2.0;
+        b[i] = 5.0;
+    }
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc data copyin (a[0:N]) present_or_create (c[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                c[ii] = a[ii];
+                b[ii] = c[ii];
+            }
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 2.0)
+            abort ();
+
+        if (b[i] != 2.0)
+            abort ();
+    }
+
+    if (acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    d = (float *) acc_deviceptr (c);
+
+    acc_unmap_data (c);
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 4.0;
+        b[i] = 8.0;
+    }
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc data copyin (a[0:N]) present (c[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                c[ii] = a[ii];
+                b[ii] = c[ii];
+            }
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 4.0)
+            abort ();
+    }
+
+    if (acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    acc_unmap_data (c);
+
+    if (acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (c, d, N * sizeof (float));
+
+    if (!acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (b, d, N * sizeof (float));
+
+    if (!acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (a, d, N * sizeof (float));
+
+    if (!acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+#pragma acc data present (a[0:N]) present (c[0:N]) present (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                a[ii] = 1.0;
+                c[ii] = 2.0;
+                b[ii] = 4.0;
+            }
+        }
+    }
+
+    if (!acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (c, (N * sizeof (float))))
+      abort ();
+
+    acc_copyout (b, N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 4.0)
+            abort ();
+
+        if (b[i] != 4.0)
+            abort ();
+    }
+
+    d = (float *) acc_deviceptr (a);
+
+    acc_unmap_data (a);
+
+    acc_free (d);
+
+    d = (float *) acc_deviceptr (c);
+
+    acc_unmap_data (c);
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 6.0;
+    }
+
+    d = (float *) acc_malloc (N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) deviceptr (d) copyout (b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+        {
+            d[ii] = a[ii];
+            b[ii] = d[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    if (acc_is_present (a, (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (b, (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+    d = (float *) acc_copyin (&a[0], N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc data pcopyin (a[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    acc_free (d);
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc data copyin (a[0:N]) pcopyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+                b[ii] = a[ii];
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 7.0;
+    }
+
+#pragma acc data copyin (a[0:N]) pcreate (c[0:N]) copyout (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                c[ii] = a[ii];
+                b[ii] = c[ii];
+            }
+        }
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    if (acc_is_present (&c[0], (N * sizeof (float))))
+      abort ();
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/nested-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/nested-2.c
new file mode 100644
index 0000000..c164598
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/nested-2.c
@@ -0,0 +1,141 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int
+main (int argc, char *argv[])
+{
+#define N 10
+    char a[N];
+    int i;
+
+    for (i = 0; i < N; ++i)
+       a[i] = 0;
+
+#pragma acc data copy (a)
+    {
+#pragma acc parallel present (a)
+        {
+            int j;
+
+            for (j = 0; j < N; ++j)
+                a[j] = j;
+        }
+    }
+
+    for (i = 0; i < N; ++i)
+    {
+        if (a[i] != i)
+            abort ();
+    }
+
+    for (i = 0; i < N; ++i)
+       a[i] = 0;
+
+#pragma acc data copy (a)
+    {
+#pragma acc kernels present (a)
+        {
+            int j;
+
+            for (j = 0; j < N; ++j)
+                a[j] = j;
+        }
+    }
+
+    for (i = 0; i < N; ++i)
+    {
+        if (a[i] != i)
+            abort ();
+    }
+
+    for (i = 0; i < N; ++i)
+        a[i] = 0;
+
+#pragma acc data copy (a)
+    {
+#pragma acc data present (a)
+        {
+#pragma acc parallel present (a)
+            {
+                int j;
+
+                for (j = 0; j < N; ++j)
+                    a[j] = j;
+            }
+        }
+    }
+
+    for (i = 0; i < N; ++i)
+    {
+        if (a[i] != i)
+            abort ();
+    }
+
+#pragma acc data copy (a)
+    {
+#pragma acc data present (a)
+        {
+#pragma acc kernels present (a)
+            {
+                int j;
+
+                for (j = 0; j < N; ++j)
+                    a[j] = j;
+            }
+        }
+    }
+
+    for (i = 0; i < N; ++i)
+    {
+        if (a[i] != i)
+            abort ();
+    }
+
+    for (i = 0; i < N; ++i)
+        a[i] = 0;
+
+#pragma acc enter data copyin (a)
+
+#pragma acc data present (a)
+    {
+#pragma acc parallel present (a)
+        {
+            int j;
+
+            for (j = 0; j < N; ++j)
+                a[j] = j;
+        }
+    }
+
+#pragma acc exit data copyout (a)
+
+    for (i = 0; i < N; ++i)
+    {
+        if (a[i] != i)
+            abort ();
+    }
+
+#pragma acc enter data copyin (a)
+
+#pragma acc data present (a)
+    {
+#pragma acc kernels present (a)
+        {
+            int j;
+
+            for (j = 0; j < N; ++j)
+                a[j] = j;
+        }
+    }
+
+#pragma acc exit data copyout (a)
+
+    for (i = 0; i < N; ++i)
+    {
+        if (a[i] != i)
+            abort ();
+    }
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/offset-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/offset-1.c
new file mode 100644
index 0000000..0bae23a
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/offset-1.c
@@ -0,0 +1,97 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main(int argc, char **argv)
+{
+    int N = 8;
+    float *a, *b;
+    int i;
+
+    a = (float *) malloc(N * sizeof (float));
+    b = (float *) malloc(N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 2.0;
+        b[i] = 5.0;
+    }
+
+#pragma acc parallel copyin(a[2:4]) copyout(b[2:4])
+    {
+        b[2] = a[2];
+        b[3] = a[3];
+    }
+
+    for (i = 2; i < 4; i++)
+    {
+        if (a[i] != 2.0)
+            abort();
+
+        if (b[i] != 2.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 1.0;
+    }
+
+#pragma acc parallel copyin(a[0:4]) copyout(b[0:4])
+    {
+        b[0] = a[0];
+        b[1] = a[1];
+        b[2] = a[2];
+        b[3] = a[3];
+    }
+
+    for (i = 0; i < 4; i++)
+    {
+        if (a[i] != 3.0)
+            abort();
+
+        if (b[i] != 3.0)
+            abort();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+        b[i] = 6.0;
+    }
+
+#pragma acc parallel copyin(a[0:4]) copyout(b[4:4])
+    {
+        b[4] = a[0];
+        b[5] = a[1];
+        b[6] = a[2];
+        b[7] = a[3];
+    }
+
+    for (i = 0; i < 4; i++)
+    {
+        if (a[i] != 9.0)
+            abort();
+    }
+
+    for (i = 4; i < 8; i++)
+    {
+        if (b[i] != 9.0)
+            abort();
+    }
+
+    if (acc_is_present (a, (N * sizeof (float))))
+      abort();
+
+    if (acc_is_present (b, (N * sizeof (float))))
+      abort();
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-1.c
new file mode 100644
index 0000000..fd9df33
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-1.c
@@ -0,0 +1,206 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int i;
+
+int main(void)
+{
+  int j, v;
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc parallel /* copyout */ present_or_copyout (v) copyin (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+#if ACC_MEM_SHARED
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+#else
+  if (v != 1 || i != -1 || j != -2)
+    abort ();
+#endif
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc parallel /* copyout */ present_or_copyout (v) copyout (i, j)
+  {
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc parallel /* copyout */ present_or_copyout (v) copy (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc parallel /* copyout */ present_or_copyout (v) create (i, j)
+  {
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+#if ACC_MEM_SHARED
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+#else
+  if (v != 1 || i != -1 || j != -2)
+    abort ();
+#endif
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc parallel /* copyout */ present_or_copyout (v) present_or_copyin (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1)
+    abort ();
+#if ACC_MEM_SHARED
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+#else
+  if (v != 1 || i != -1 || j != -2)
+    abort ();
+#endif
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc parallel /* copyout */ present_or_copyout (v) present_or_copyout (i, j)
+  {
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc parallel /* copyout */ present_or_copyout (v) present_or_copy (i, j)
+  {
+    if (i != -1 || j != -2)
+      abort ();
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+
+  i = -1;
+  j = -2;
+  v = 0;
+#pragma acc parallel /* copyout */ present_or_copyout (v) present_or_create (i, j)
+  {
+    i = 2;
+    j = 1;
+    if (i != 2 || j != 1)
+      abort ();
+    v = 1;
+  }
+  if (v != 1)
+    abort ();
+#if ACC_MEM_SHARED
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+#else
+  if (v != 1 || i != -1 || j != -2)
+    abort ();
+#endif
+
+  i = -1;
+  j = -2;
+  v = 0;
+
+#pragma acc data copyin (i, j)
+  {
+#pragma acc parallel /* copyout */ present_or_copyout (v) present (i, j)
+    {
+      if (i != -1 || j != -2)
+        abort ();
+      i = 2;
+      j = 1;
+      if (i != 2 || j != 1)
+        abort ();
+      v = 1;
+    }
+  }
+#if ACC_MEM_SHARED
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+#else
+  if (v != 1 || i != -1 || j != -2)
+    abort ();
+#endif
+
+  i = -1;
+  j = -2;
+  v = 0;
+
+#pragma acc data copyin(i, j)
+  {
+#pragma acc parallel /* copyout */ present_or_copyout (v)
+    {
+      if (i != -1 || j != -2)
+        abort ();
+      i = 2;
+      j = 1;
+      if (i != 2 || j != 1)
+        abort ();
+      v = 1;
+    }
+  }
+#if ACC_MEM_SHARED
+  if (v != 1 || i != 2 || j != 1)
+    abort ();
+#else
+  if (v != 1 || i != -1 || j != -2)
+    abort ();
+#endif
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-empty.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-empty.c
new file mode 100644
index 0000000..8e3bb43
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-empty.c
@@ -0,0 +1,6 @@
+int
+main (void)
+{
+#pragma acc parallel
+  ;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/pointer-align-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/pointer-align-1.c
new file mode 100644
index 0000000..f7d5b9b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/pointer-align-1.c
@@ -0,0 +1,35 @@
+/* { dg-do run } */
+
+/* PR middle-end/63247 */
+
+#include <stdlib.h>
+
+int
+main(int argc, char **argv)
+{
+#define N 4
+    short a[N];
+
+    a[0] = 10;
+    a[1] = 10;
+    a[2] = 10;
+    a[3] = 10;
+
+#pragma acc parallel copy(a[1:N-1])
+    {
+      a[1] = 51;
+      a[2] = 52;
+      a[3] = 53;
+    }
+
+    if (a[0] != 10)
+      abort ();
+    if (a[1] != 51)
+      abort ();
+    if (a[2] != 52)
+      abort ();
+    if (a[3] != 53)
+      abort ();
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/present-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/present-1.c
new file mode 100644
index 0000000..f331f1f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/present-1.c
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+    int N = 8;
+    float *a, *b, *c, *d;
+    int i;
+
+    a = (float *) malloc (N * sizeof (float));
+    b = (float *) malloc (N * sizeof (float));
+    c = (float *) malloc (N * sizeof (float));
+
+    d = (float *) acc_malloc (N * sizeof (float));
+    acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc data present (a[0:N]) present (c[0:N]) present (b[0:N])
+    {
+#pragma acc parallel
+        {
+            int ii;
+
+            for (ii = 0; ii < N; ii++)
+            {
+                c[ii] = a[ii];
+                b[ii] = c[ii];
+            }
+        }
+    }
+
+    d = (float *) acc_deviceptr (c);
+    acc_unmap_data (c);
+    acc_free (d);
+
+    free (a);
+    free (b);
+    free (c);
+
+    return 0;
+}
+/* { dg-shouldfail "libgomp: present clause: !acc_is_present" } */
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/present-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/present-2.c
new file mode 100644
index 0000000..41efa70
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/present-2.c
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <stdlib.h>
+
+int
+main (int argc, char **argv)
+{
+  int N = 8;
+  float *a, *b;
+  int i;
+
+  a = (float *) malloc (N * sizeof (float));
+  b = (float *) malloc (N * sizeof (float));
+
+  for (i = 0; i < N; i++)
+    {
+      a[i] = 4.0;
+      b[i] = 0.0;
+    }
+
+#pragma acc data copyin(a[0:N]) copyout(b[0:N])
+  {
+
+#pragma acc parallel present(a[0:N])
+    {
+      int ii;
+
+      for (ii = 0; ii < N; ii++)
+	{
+	  b[ii] = a[ii];
+	}
+    }
+
+  }
+
+  for (i = 0; i < N; i++)
+    {
+      if (a[i] != 4.0)
+	abort ();
+
+      if (b[i] != 4.0)
+	abort ();
+    }
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-1.c
new file mode 100644
index 0000000..acf9540
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-1.c
@@ -0,0 +1,174 @@
+/* { dg-do run } */
+
+/* Integer reductions.  */
+
+#include <stdlib.h>
+#include <stdbool.h>
+
+#define vl 32
+
+int
+main(void)
+{
+  const int n = 1000;
+  int i;
+  int vresult, result, array[n];
+  bool lvresult, lresult;
+
+  for (i = 0; i < n; i++)
+    array[i] = i;
+
+  result = 0;
+  vresult = 0;
+
+  /* '+' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (+:result)
+  for (i = 0; i < n; i++)
+    result += array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult += array[i];
+
+  if (result != vresult)
+    abort ();
+
+  result = 0;
+  vresult = 0;
+
+  /* '*' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (*:result)
+  for (i = 0; i < n; i++)
+    result *= array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult *= array[i];
+
+  if (result != vresult)
+    abort ();
+
+//   result = 0;
+//   vresult = 0;
+// 
+//   /* 'max' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (+:result)
+//   for (i = 0; i < n; i++)
+//       result = result > array[i] ? result : array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//       vresult = vresult > array[i] ? vresult : array[i];
+// 
+//   printf("%d != %d\n", result, vresult);
+//   if (result != vresult)
+//     abort ();
+// 
+//   result = 0;
+//   vresult = 0;
+// 
+//   /* 'min' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (+:result)
+//   for (i = 0; i < n; i++)
+//       result = result < array[i] ? result : array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//       vresult = vresult < array[i] ? vresult : array[i];
+// 
+//   printf("%d != %d\n", result, vresult);
+//   if (result != vresult)
+//     abort ();
+
+  result = 0;
+  vresult = 0;
+
+  /* '&' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (&:result)
+  for (i = 0; i < n; i++)
+    result &= array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult &= array[i];
+
+  if (result != vresult)
+    abort ();
+
+  result = 0;
+  vresult = 0;
+
+  /* '|' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (|:result)
+  for (i = 0; i < n; i++)
+    result |= array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult |= array[i];
+
+  if (result != vresult)
+    abort ();
+
+  result = 0;
+  vresult = 0;
+
+  /* '^' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (^:result)
+  for (i = 0; i < n; i++)
+    result ^= array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult ^= array[i];
+
+  if (result != vresult)
+    abort ();
+
+  result = 5;
+  vresult = 5;
+
+  lresult = false;
+  lvresult = false;
+
+  /* '&&' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (&&:lresult)
+  for (i = 0; i < n; i++)
+    lresult = lresult && (result > array[i]);
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    lvresult = lresult && (result > array[i]);
+
+  if (lresult != lvresult)
+    abort ();
+
+  result = 5;
+  vresult = 5;
+
+  lresult = false;
+  lvresult = false;
+
+  /* '||' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (||:lresult)
+  for (i = 0; i < n; i++)
+    lresult = lresult || (result > array[i]);
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    lvresult = lresult || (result > array[i]);
+
+  if (lresult != lvresult)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-2.c
new file mode 100644
index 0000000..c2ec110
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-2.c
@@ -0,0 +1,126 @@
+/* { dg-do run } */
+
+/* float reductions.  */
+
+#include <stdlib.h>
+#include <stdbool.h>
+#include <math.h>
+
+#define vl 32
+
+int
+main(void)
+{
+  const int n = 1000;
+  int i;
+  float vresult, result, array[n];
+  bool lvresult, lresult;
+
+  for (i = 0; i < n; i++)
+    array[i] = i;
+
+  result = 0;
+  vresult = 0;
+
+  /* '+' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (+:result)
+  for (i = 0; i < n; i++)
+    result += array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult += array[i];
+
+  if (result != vresult)
+    abort ();
+
+  result = 0;
+  vresult = 0;
+
+  /* '*' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (*:result)
+  for (i = 0; i < n; i++)
+    result *= array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult *= array[i];
+
+  if (fabs(result - vresult) > .0001)
+    abort ();
+//   result = 0;
+//   vresult = 0;
+// 
+//   /* 'max' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (+:result)
+//   for (i = 0; i < n; i++)
+//       result = result > array[i] ? result : array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//       vresult = vresult > array[i] ? vresult : array[i];
+// 
+//   printf("%d != %d\n", result, vresult);
+//   if (result != vresult)
+//     abort ();
+// 
+//   result = 0;
+//   vresult = 0;
+// 
+//   /* 'min' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (+:result)
+//   for (i = 0; i < n; i++)
+//       result = result < array[i] ? result : array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//       vresult = vresult < array[i] ? vresult : array[i];
+// 
+//   printf("%d != %d\n", result, vresult);
+//   if (result != vresult)
+//     abort ();
+
+  result = 5;
+  vresult = 5;
+
+  lresult = false;
+  lvresult = false;
+
+  /* '&&' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (&&:lresult)
+  for (i = 0; i < n; i++)
+    lresult = lresult && (result > array[i]);
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    lvresult = lresult && (result > array[i]);
+
+  if (lresult != lvresult)
+    abort ();
+
+  result = 5;
+  vresult = 5;
+
+  lresult = false;
+  lvresult = false;
+
+  /* '||' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (||:lresult)
+  for (i = 0; i < n; i++)
+    lresult = lresult || (result > array[i]);
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    lvresult = lresult || (result > array[i]);
+
+  if (lresult != lvresult)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-3.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-3.c
new file mode 100644
index 0000000..58b49ff
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-3.c
@@ -0,0 +1,126 @@
+/* { dg-do run } */
+
+/* double reductions.  */
+
+#include <stdlib.h>
+#include <stdbool.h>
+#include <math.h>
+
+#define vl 32
+
+int
+main(void)
+{
+  const int n = 1000;
+  int i;
+  double vresult, result, array[n];
+  bool lvresult, lresult;
+
+  for (i = 0; i < n; i++)
+    array[i] = i;
+
+  result = 0;
+  vresult = 0;
+
+  /* '+' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (+:result)
+  for (i = 0; i < n; i++)
+    result += array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult += array[i];
+
+  if (result != vresult)
+    abort ();
+
+  result = 0;
+  vresult = 0;
+
+  /* '*' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (*:result)
+  for (i = 0; i < n; i++)
+    result *= array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult *= array[i];
+
+  if (fabs(result - vresult) > .0001)
+    abort ();
+//   result = 0;
+//   vresult = 0;
+// 
+//   /* 'max' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (+:result)
+//   for (i = 0; i < n; i++)
+//       result = result > array[i] ? result : array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//       vresult = vresult > array[i] ? vresult : array[i];
+// 
+//   printf("%d != %d\n", result, vresult);
+//   if (result != vresult)
+//     abort ();
+// 
+//   result = 0;
+//   vresult = 0;
+// 
+//   /* 'min' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (+:result)
+//   for (i = 0; i < n; i++)
+//       result = result < array[i] ? result : array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//       vresult = vresult < array[i] ? vresult : array[i];
+// 
+//   printf("%d != %d\n", result, vresult);
+//   if (result != vresult)
+//     abort ();
+
+  result = 5;
+  vresult = 5;
+
+  lresult = false;
+  lvresult = false;
+
+  /* '&&' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (&&:lresult)
+  for (i = 0; i < n; i++)
+    lresult = lresult && (result > array[i]);
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    lvresult = lresult && (result > array[i]);
+
+  if (lresult != lvresult)
+    abort ();
+
+  result = 5;
+  vresult = 5;
+
+  lresult = false;
+  lvresult = false;
+
+  /* '||' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (||:lresult)
+  for (i = 0; i < n; i++)
+    lresult = lresult || (result > array[i]);
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    lvresult = lresult || (result > array[i]);
+
+  if (lresult != lvresult)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-4.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-4.c
new file mode 100644
index 0000000..c8a9a6c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-4.c
@@ -0,0 +1,129 @@
+/* { dg-do run } */
+
+/* complex reductions.  */
+
+#include <stdlib.h>
+#include <stdbool.h>
+#include <math.h>
+#include <complex.h>
+
+#define vl 32
+
+int
+main(void)
+{
+  const int n = 1000;
+  int i;
+  double complex vresult, result, array[n];
+  bool lvresult, lresult;
+
+  for (i = 0; i < n; i++)
+    array[i] = i;
+
+  result = 0;
+  vresult = 0;
+
+  /* '+' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (+:result)
+  for (i = 0; i < n; i++)
+    result += array[i];
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    vresult += array[i];
+
+  if (result != vresult)
+    abort ();
+
+  result = 0;
+  vresult = 0;
+
+  /* Needs support for complex multiplication.  */
+
+//   /* '*' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (*:result)
+//   for (i = 0; i < n; i++)
+//     result *= array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//     vresult *= array[i];
+// 
+//   if (fabs(result - vresult) > .0001)
+//     abort ();
+//   result = 0;
+//   vresult = 0;
+
+//   /* 'max' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (+:result)
+//   for (i = 0; i < n; i++)
+//       result = result > array[i] ? result : array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//       vresult = vresult > array[i] ? vresult : array[i];
+// 
+//   printf("%d != %d\n", result, vresult);
+//   if (result != vresult)
+//     abort ();
+// 
+//   result = 0;
+//   vresult = 0;
+// 
+//   /* 'min' reductions.  */
+// #pragma acc parallel vector_length (vl)
+// #pragma acc loop reduction (+:result)
+//   for (i = 0; i < n; i++)
+//       result = result < array[i] ? result : array[i];
+// 
+//   /* Verify the reduction.  */
+//   for (i = 0; i < n; i++)
+//       vresult = vresult < array[i] ? vresult : array[i];
+// 
+//   printf("%d != %d\n", result, vresult);
+//   if (result != vresult)
+//     abort ();
+
+  result = 5;
+  vresult = 5;
+
+  lresult = false;
+  lvresult = false;
+
+  /* '&&' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (&&:lresult)
+  for (i = 0; i < n; i++)
+    lresult = lresult && (creal(result) > creal(array[i]));
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    lvresult = lresult && (creal(result) > creal(array[i]));
+
+  if (lresult != lvresult)
+    abort ();
+
+  result = 5;
+  vresult = 5;
+
+  lresult = false;
+  lvresult = false;
+
+  /* '||' reductions.  */
+#pragma acc parallel vector_length (vl)
+#pragma acc loop reduction (||:lresult)
+  for (i = 0; i < n; i++)
+    lresult = lresult || (creal(result) > creal(array[i]));
+
+  /* Verify the reduction.  */
+  for (i = 0; i < n; i++)
+    lvresult = lresult || (creal(result) > creal(array[i]));
+
+  if (lresult != lvresult)
+    abort ();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-5.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-5.c
new file mode 100644
index 0000000..757b8be
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-5.c
@@ -0,0 +1,32 @@
+#include <stdio.h>
+#include <stdlib.h>
+
+int
+main (void)
+{
+  int s1 = 2, s2 = 5, v1 = 2, v2 = 5;
+  int n = 100;
+  int i;
+
+#pragma acc parallel vector_length (1000)
+#pragma acc loop reduction (+:s1, s2)
+  for (i = 0; i < n; i++)
+    {
+      s1 = s1 + 3;
+      s2 = s2 + 2;
+    }
+
+  for (i = 0; i < n; i++)
+    {
+      v1 = v1 + 3;
+      v2 = v2 + 2;
+    }
+  
+  if (s1 != v1)
+    abort ();
+  
+  if (s2 != v2)
+    abort ();
+    
+  return 0;
+}
\ No newline at end of file
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-initial-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-initial-1.c
new file mode 100644
index 0000000..81cf865
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-initial-1.c
@@ -0,0 +1,25 @@
+/* { dg-do run } */
+
+int
+main(void)
+{
+#define I 5
+#define N 11
+#define A 8
+
+  int a = A;
+  int s = I;
+
+#pragma acc parallel vector_length(N)
+  {
+    int i;
+#pragma acc loop reduction(+:s)
+    for (i = 0; i < N; ++i)
+      s += a;
+  }
+
+  if (s != I + N * A)
+    __builtin_abort();
+
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/subr.h b/libgomp/testsuite/libgomp.oacc-c-c++-common/subr.h
new file mode 100644
index 0000000..9db236c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/subr.h
@@ -0,0 +1,46 @@
+
+#if ACC_DEVICE_TYPE_nvidia
+
+#pragma acc routine nohost
+static int clock (void)
+{
+  int thetime;
+
+  asm __volatile__ ("mov.u32 %0, %%clock;" : "=r"(thetime));
+
+  return thetime;
+}
+
+#endif
+
+void
+delay (unsigned long *d_o, unsigned long delay)
+{
+  int start, ticks;
+
+  start = clock ();
+
+  ticks = 0;
+
+  while (ticks < delay)
+    ticks = clock () - start;
+
+  return;
+}
+
+void
+delay2 (unsigned long *d_o, unsigned long delay, unsigned long tid)
+{
+  int start, ticks;
+
+  start = clock ();
+
+  ticks = 0;
+
+  while (ticks < delay)
+    ticks = clock () - start;
+
+  d_o[0] = tid;
+
+  return;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/subr.ptx b/libgomp/testsuite/libgomp.oacc-c-c++-common/subr.ptx
new file mode 100644
index 0000000..6f748fc
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/subr.ptx
@@ -0,0 +1,148 @@
+// BEGIN PREAMBLE
+	.version	3.1
+	.target	sm_30
+	.address_size 64
+// END PREAMBLE
+
+// BEGIN FUNCTION DEF: clock
+.func (.param.u32 %out_retval)clock
+{
+.reg.u32 %retval;
+	.reg.u64 %hr10;
+	.reg.u32 %r22;
+	.reg.u32 %r23;
+	.reg.u32 %r24;
+	.local.align 8 .b8 %frame[8];
+	// #APP 
+// 7 "subr.c" 1
+	mov.u32 %r24, %clock;
+// 0 "" 2
+	// #NO_APP 
+		st.local.u32	[%frame], %r24;
+		ld.local.u32	%r22, [%frame];
+		mov.u32	%r23, %r22;
+		mov.u32	%retval, %r23;
+	st.param.u32	[%out_retval], %retval;
+	ret;
+	}
+// END FUNCTION DEF
+// BEGIN GLOBAL FUNCTION DEF: delay
+.visible .entry delay(.param.u64 %in_ar1, .param.u64 %in_ar2)
+{
+	.reg.u64 %ar1;
+	.reg.u64 %ar2;
+	.reg.u64 %hr10;
+	.reg.u64 %r22;
+	.reg.u32 %r23;
+	.reg.u64 %r24;
+	.reg.u64 %r25;
+	.reg.u32 %r26;
+	.reg.u32 %r27;
+	.reg.u32 %r28;
+	.reg.u32 %r29;
+	.reg.u32 %r30;
+	.reg.u64 %r31;
+	.reg.pred %r32;
+	.local.align 8 .b8 %frame[24];
+	ld.param.u64 %ar1, [%in_ar1];
+	ld.param.u64 %ar2, [%in_ar2];
+		mov.u64	%r24, %ar1;
+		st.u64	[%frame+8], %r24;
+		mov.u64	%r25, %ar2;
+		st.local.u64	[%frame+16], %r25;
+	{
+		.param.u32 %retval_in;
+	{
+		call (%retval_in), clock;
+	}
+		ld.param.u32	%r26, [%retval_in];
+}
+		st.local.u32	[%frame+4], %r26;
+		mov.u32	%r27, 0;
+		st.local.u32	[%frame], %r27;
+		bra	$L4;
+$L5:
+	{
+		.param.u32 %retval_in;
+	{
+		call (%retval_in), clock;
+	}
+		ld.param.u32	%r28, [%retval_in];
+}
+		mov.u32	%r23, %r28;
+		ld.local.u32	%r30, [%frame+4];
+		sub.u32	%r29, %r23, %r30;
+		st.local.u32	[%frame], %r29;
+$L4:
+		ld.local.s32	%r22, [%frame];
+		ld.local.u64	%r31, [%frame+16];
+		setp.lo.u64 %r32,%r22,%r31;
+	@%r32	bra	$L5;
+	ret;
+	}
+// END FUNCTION DEF
+// BEGIN GLOBAL FUNCTION DEF: delay2
+.visible .entry delay2(.param.u64 %in_ar1, .param.u64 %in_ar2, .param.u64 %in_ar3)
+{
+	.reg.u64 %ar1;
+	.reg.u64 %ar2;
+	.reg.u64 %ar3;
+	.reg.u64 %hr10;
+	.reg.u64 %r22;
+	.reg.u32 %r23;
+	.reg.u64 %r24;
+	.reg.u64 %r25;
+	.reg.u64 %r26;
+	.reg.u32 %r27;
+	.reg.u32 %r28;
+	.reg.u32 %r29;
+	.reg.u32 %r30;
+	.reg.u32 %r31;
+	.reg.u64 %r32;
+	.reg.pred %r33;
+	.reg.u64 %r34;
+	.reg.u64 %r35;
+	.local.align 8 .b8 %frame[32];
+	ld.param.u64 %ar1, [%in_ar1];
+	ld.param.u64 %ar2, [%in_ar2];
+	ld.param.u64 %ar3, [%in_ar3];
+		mov.u64	%r24, %ar1;
+		st.local.u64	[%frame+8], %r24;
+		mov.u64	%r25, %ar2;
+		st.local.u64	[%frame+16], %r25;
+		mov.u64	%r26, %ar3;
+		st.local.u64	[%frame+24], %r26;
+	{
+		.param.u32 %retval_in;
+	{
+		call (%retval_in), clock;
+	}
+		ld.param.u32	%r27, [%retval_in];
+}
+		st.local.u32	[%frame+4], %r27;
+		mov.u32	%r28, 0;
+		st.local.u32	[%frame], %r28;
+		bra	$L8;
+$L9:
+	{
+		.param.u32 %retval_in;
+	{
+		call (%retval_in), clock;
+	}
+		ld.param.u32	%r29, [%retval_in];
+}
+		mov.u32	%r23, %r29;
+		ld.local.u32	%r31, [%frame+4];
+		sub.u32	%r30, %r23, %r31;
+		st.local.u32	[%frame], %r30;
+$L8:
+		ld.local.s32	%r22, [%frame];
+		ld.local.u64	%r32, [%frame+16];
+		setp.lo.u64 %r33,%r22,%r32;
+	@%r33	bra	$L9;
+		ld.local.u64	%r34, [%frame+8];
+		ld.local.u64	%r35, [%frame+24];
+		st.u64	[%r34], %r35;
+	ret;
+	}
+// END FUNCTION DEF
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/timer.h b/libgomp/testsuite/libgomp.oacc-c-c++-common/timer.h
new file mode 100644
index 0000000..53749da
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/timer.h
@@ -0,0 +1,103 @@
+
+#include <stdio.h>
+#include <cuda.h>
+
+static int _Tnum_timers;
+static CUevent *_Tstart_events, *_Tstop_events;
+static CUstream _Tstream;
+
+void
+init_timers (int ntimers)
+{
+  int i;
+  CUresult r;
+
+  _Tnum_timers = ntimers;
+
+  _Tstart_events = (CUevent *) malloc (_Tnum_timers * sizeof (CUevent));
+  _Tstop_events = (CUevent *) malloc (_Tnum_timers * sizeof (CUevent));
+
+  r = cuStreamCreate (&_Tstream, CU_STREAM_DEFAULT);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+      abort ();
+    }
+
+  for (i = 0; i < _Tnum_timers; i++)
+    {
+      r = cuEventCreate (&_Tstart_events[i], CU_EVENT_DEFAULT);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuEventCreate failed: %d\n", r);
+	  abort ();
+	}
+
+      r = cuEventCreate (&_Tstop_events[i], CU_EVENT_DEFAULT);
+      if (r != CUDA_SUCCESS)
+	{
+	  fprintf (stderr, "cuEventCreate failed: %d\n", r);
+	  abort ();
+	}
+    }
+}
+
+void
+fini_timers (void)
+{
+  int i;
+
+  for (i = 0; i < _Tnum_timers; i++)
+    {
+      cuEventDestroy (_Tstart_events[i]);
+      cuEventDestroy (_Tstop_events[i]);
+    }
+
+  cuStreamDestroy (_Tstream);
+
+  free (_Tstart_events);
+  free (_Tstop_events);
+}
+
+void
+start_timer (int timer)
+{
+  CUresult r;
+
+  r = cuEventRecord (_Tstart_events[timer], _Tstream);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuEventRecord failed: %d\n", r);
+      abort ();
+    }
+}
+
+float
+stop_timer (int timer)
+{
+  CUresult r;
+  float etime;
+
+  r = cuEventRecord (_Tstop_events[timer], _Tstream);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuEventRecord failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuEventSynchronize (_Tstop_events[timer]);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuEventSynchronize failed: %d\n", r);
+      abort ();
+    }
+
+  r = cuEventElapsedTime (&etime, _Tstart_events[timer], _Tstop_events[timer]);
+  if (r != CUDA_SUCCESS)
+    {
+      fprintf (stderr, "cuEventElapsedTime failed: %d\n", r);
+      abort ();
+    }
+
+  return etime;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/update-1-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/update-1-2.c
new file mode 100644
index 0000000..c7e7257
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/update-1-2.c
@@ -0,0 +1,282 @@
+/* Copy of update-1.c with self exchanged with host for #pragma acc update.  */
+
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+    int N = 8;
+    float *a, *b, *c;
+    float *d_a, *d_b, *d_c;
+    int i;
+
+    a = (float *) malloc (N * sizeof (float));
+    b = (float *) malloc (N * sizeof (float));
+    c = (float *) malloc (N * sizeof (float));
+
+    d_a = (float *) acc_malloc (N * sizeof (float));
+    d_b = (float *) acc_malloc (N * sizeof (float));
+    d_c = (float *) acc_malloc (N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 0.0;
+    }
+
+    acc_map_data (a, d_a, N * sizeof (float));
+    acc_map_data (b, d_b, N * sizeof (float));
+    acc_map_data (c, d_c, N * sizeof (float));
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update self (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 1.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update self (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 1.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update self (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 6.0)
+            abort ();
+
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 7.0;
+        b[i] = 2.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update self (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 7.0)
+            abort ();
+
+        if (b[i] != 7.0)
+            abort ();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc update device (a[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update self (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 9.0)
+            abort ();
+
+        if (b[i] != 9.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+    }
+
+#pragma acc update device (a[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+    }
+
+#pragma acc update device (a[0:N >> 1])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update self (a[0:N], b[0:N])
+
+    for (i = 0; i < (N >> 1); i++)
+    {
+        if (a[i] != 6.0)
+            abort ();
+
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    for (i = (N >> 1); i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/update-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/update-1.c
new file mode 100644
index 0000000..dff139f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/update-1.c
@@ -0,0 +1,280 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+    int N = 8;
+    float *a, *b, *c;
+    float *d_a, *d_b, *d_c;
+    int i;
+
+    a = (float *) malloc (N * sizeof (float));
+    b = (float *) malloc (N * sizeof (float));
+    c = (float *) malloc (N * sizeof (float));
+
+    d_a = (float *) acc_malloc (N * sizeof (float));
+    d_b = (float *) acc_malloc (N * sizeof (float));
+    d_c = (float *) acc_malloc (N * sizeof (float));
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 3.0;
+        b[i] = 0.0;
+    }
+
+    acc_map_data (a, d_a, N * sizeof (float));
+    acc_map_data (b, d_b, N * sizeof (float));
+    acc_map_data (c, d_c, N * sizeof (float));
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 3.0)
+            abort ();
+
+        if (b[i] != 3.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 1.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+        b[i] = 1.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update self (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+        b[i] = 0.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 6.0)
+            abort ();
+
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 7.0;
+        b[i] = 2.0;
+    }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 7.0)
+            abort ();
+
+        if (b[i] != 7.0)
+            abort ();
+    }
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 9.0;
+    }
+
+#pragma acc update device (a[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        if (a[i] != 9.0)
+            abort ();
+
+        if (b[i] != 9.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 5.0;
+    }
+
+#pragma acc update device (a[0:N])
+
+    for (i = 0; i < N; i++)
+    {
+        a[i] = 6.0;
+    }
+
+#pragma acc update device (a[0:N >> 1])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+    {
+        int ii;
+
+        for (ii = 0; ii < N; ii++)
+            b[ii] = a[ii];
+    }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+    for (i = 0; i < (N >> 1); i++)
+    {
+        if (a[i] != 6.0)
+            abort ();
+
+        if (b[i] != 6.0)
+            abort ();
+    }
+
+    for (i = (N >> 1); i < N; i++)
+    {
+        if (a[i] != 5.0)
+            abort ();
+
+        if (b[i] != 5.0)
+            abort ();
+    }
+
+    if (!acc_is_present (&a[0], (N * sizeof (float))))
+      abort ();
+
+    if (!acc_is_present (&b[0], (N * sizeof (float))))
+      abort ();
+
+    return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c/c.exp b/libgomp/testsuite/libgomp.oacc-c/c.exp
new file mode 100644
index 0000000..c0c70bb
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c/c.exp
@@ -0,0 +1,71 @@
+# This whole file adapted from libgomp.c/c.exp.
+
+if [info exists lang_library_path] then {
+    unset lang_library_path
+    unset lang_link_flags
+}
+if [info exists lang_test_file] then {
+    unset lang_test_file
+}
+if [info exists lang_include_flags] then {
+    unset lang_include_flags
+}
+
+load_lib libgomp-dg.exp
+load_gcc_lib gcc-dg.exp
+
+# If a testcase doesn't have special options, use these.
+if ![info exists DEFAULT_CFLAGS] then {
+    set DEFAULT_CFLAGS "-O2"
+}
+
+# Initialize dg.
+dg-init
+
+# Turn on OpenACC.
+lappend ALWAYS_CFLAGS "additional_flags=-fopenacc"
+
+# Gather a list of all tests.
+set tests [lsort [concat \
+		      [find $srcdir/$subdir *.c] \
+		      [find $srcdir/$subdir/../libgomp.oacc-c-c++-common *.c]]]
+
+set ld_library_path $always_ld_library_path
+append ld_library_path [gcc-set-multilib-library-path $GCC_UNDER_TEST]
+set_ld_library_path_env_vars
+
+# Test OpenACC with available accelerators.
+set SAVE_ALWAYS_CFLAGS "$ALWAYS_CFLAGS"
+foreach offload_target_openacc $offload_targets_s_openacc {
+    set ALWAYS_CFLAGS "$SAVE_ALWAYS_CFLAGS"
+    set tagopt "-DACC_DEVICE_TYPE_$offload_target_openacc=1"
+
+    switch $offload_target_openacc {
+	host {
+	    set acc_mem_shared 1
+	}
+	host_nonshm {
+	    set acc_mem_shared 0
+	}
+	nvidia {
+	    # Copy ptx file (TEMPORARY)
+	    remote_download host $srcdir/libgomp.oacc-c-c++-common/subr.ptx
+
+	    # Where timer.h lives
+	    lappend ALWAYS_CFLAGS "additional_flags=-I${srcdir}/libgomp.oacc-c-c++-common"
+
+	    set acc_mem_shared 0
+	}
+	default {
+	    set acc_mem_shared 0
+	}
+    }
+    set tagopt "$tagopt -DACC_MEM_SHARED=$acc_mem_shared"
+
+    setenv ACC_DEVICE_TYPE $offload_target_openacc
+
+    dg-runtest $tests "$tagopt" $DEFAULT_CFLAGS
+}
+
+# All done.
+dg-finish
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/abort-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/abort-1.f90
new file mode 100644
index 0000000..52b030b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/abort-1.f90
@@ -0,0 +1,10 @@
+! { dg-shouldfail "" { *-*-* } { "*" } { "" } }
+
+program main
+  implicit none
+
+  !$acc parallel
+  call abort
+  !$acc end parallel
+
+end program main
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/abort-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/abort-2.f90
new file mode 100644
index 0000000..2ba2bcb
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/abort-2.f90
@@ -0,0 +1,13 @@
+program main
+  implicit none
+
+  integer :: argc
+  argc = command_argument_count ()
+
+  !$acc parallel copyin(argc)
+  if (argc .ne. 0) then
+     call abort
+  end if
+  !$acc end parallel
+
+end program main
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-1.f90
new file mode 100644
index 0000000..4488818
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-1.f90
@@ -0,0 +1,52 @@
+! { dg-additional-options "-cpp" }
+! TODO: Have to disable the acc_on_device builtin for we want to test the
+! libgomp library function?  The command line option
+! '-fno-builtin-acc_on_device' is valid for C/C++/ObjC/ObjC++ but not for
+! Fortran.
+
+use openacc
+implicit none
+
+! Host.
+
+if (.not. acc_on_device (acc_device_none)) call abort
+if (.not. acc_on_device (acc_device_host)) call abort
+if (acc_on_device (acc_device_host_nonshm)) call abort
+if (acc_on_device (acc_device_not_host)) call abort
+if (acc_on_device (acc_device_nvidia)) call abort
+
+
+! Host via offloading fallback mode.
+
+!$acc parallel if(.false.)
+if (.not. acc_on_device (acc_device_none)) call abort
+if (.not. acc_on_device (acc_device_host)) call abort
+if (acc_on_device (acc_device_host_nonshm)) call abort
+if (acc_on_device (acc_device_not_host)) call abort
+if (acc_on_device (acc_device_nvidia)) call abort
+!$acc end parallel
+
+
+#if !ACC_DEVICE_TYPE_host
+
+! Offloaded.
+
+!$acc parallel
+if (acc_on_device (acc_device_none)) call abort
+if (acc_on_device (acc_device_host)) call abort
+#if ACC_DEVICE_TYPE_host_nonshm
+if (.not. acc_on_device (acc_device_host_nonshm)) call abort
+#else
+if (acc_on_device (acc_device_host_nonshm)) call abort
+#endif
+if (.not. acc_on_device (acc_device_not_host)) call abort
+#if ACC_DEVICE_TYPE_nvidia
+if (.not. acc_on_device (acc_device_nvidia)) call abort
+#else
+if (acc_on_device (acc_device_nvidia)) call abort
+#endif
+!$acc end parallel
+
+#endif
+
+end
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-2.f b/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-2.f
new file mode 100644
index 0000000..0047a19
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-2.f
@@ -0,0 +1,52 @@
+! { dg-additional-options "-cpp" }
+! TODO: Have to disable the acc_on_device builtin for we want to test
+! the libgomp library function?  The command line option
+! '-fno-builtin-acc_on_device' is valid for C/C++/ObjC/ObjC++ but not
+! for Fortran.
+
+      USE OPENACC
+      IMPLICIT NONE
+
+!Host.
+
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+
+
+!Host via offloading fallback mode.
+
+!$ACC PARALLEL IF(.FALSE.)
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+!$ACC END PARALLEL
+
+
+#if !ACC_DEVICE_TYPE_host
+
+! Offloaded.
+
+!$ACC PARALLEL
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+#if ACC_DEVICE_TYPE_host_nonshm
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+#else
+      IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+#endif
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+#if ACC_DEVICE_TYPE_nvidia
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+#else
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+#endif
+!$ACC END PARALLEL
+
+#endif
+
+      END
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-3.f b/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-3.f
new file mode 100644
index 0000000..49d7a72
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/acc_on_device-1-3.f
@@ -0,0 +1,52 @@
+! { dg-additional-options "-cpp" }
+! TODO: Have to disable the acc_on_device builtin for we want to test
+! the libgomp library function?  The command line option
+! '-fno-builtin-acc_on_device' is valid for C/C++/ObjC/ObjC++ but not
+! for Fortran.
+
+      IMPLICIT NONE
+      INCLUDE "openacc_lib.h"
+
+!Host.
+
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+
+
+!Host via offloading fallback mode.
+
+!$ACC PARALLEL IF(.FALSE.)
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+!$ACC END PARALLEL
+
+
+#if !ACC_DEVICE_TYPE_host
+
+! Offloaded.
+
+!$ACC PARALLEL
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
+      IF (ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+#if ACC_DEVICE_TYPE_host_nonshm
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+#else
+      IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+#endif
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+#if ACC_DEVICE_TYPE_nvidia
+      IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+#else
+      IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+#endif
+!$ACC END PARALLEL
+
+#endif
+
+      END
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-1.f90
new file mode 100644
index 0000000..b6e637b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-1.f90
@@ -0,0 +1,135 @@
+! { dg-do run }
+
+program asyncwait
+  integer, parameter :: N = 64
+  real, allocatable :: a(:), b(:), c(:), d(:), e(:)
+  integer i
+
+  allocate (a(N))
+  allocate (b(N))
+  allocate (c(N))
+  allocate (d(N))
+  allocate (e(N))
+
+  a(:) = 3.0
+  b(:) = 0.0
+
+  !$acc data copy (a(1:N)) copy (b(1:N))
+
+  !$acc parallel async
+  !$acc loop
+  do i = 1, N
+     b(i) = a(i)
+  end do
+  !$acc end parallel
+
+  !$acc wait
+  !$acc end data
+
+  do i = 1, N
+     if (a(i) .ne. 3.0) call abort
+     if (b(i) .ne. 3.0) call abort
+  end do
+
+  a(:) = 2.0
+  b(:) = 0.0
+
+  !$acc data copy (a(1:N)) copy (b(1:N))
+
+  !$acc parallel async (1)
+  !$acc loop
+  do i = 1, N
+     b(i) = a(i)
+  end do
+  !$acc end parallel
+
+  !$acc wait (1)
+  !$acc end data
+
+  do i = 1, N
+     if (a(i) .ne. 2.0) call abort
+     if (b(i) .ne. 2.0) call abort
+  end do
+
+  a(:) = 3.0
+  b(:) = 0.0
+  c(:) = 0.0
+  d(:) = 0.0
+
+  !$acc data copy (a(1:N)) copy (b(1:N)) copy (c(1:N)) copy (d(1:N))
+
+  !$acc parallel async (1)
+  do i = 1, N
+     b(i) = (a(i) * a(i) * a(i)) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     c(i) = (a(i) * 4) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  !$acc loop
+  do i = 1, N
+     d(i) = ((a(i) * a(i) + a(i)) / a(i)) - a(i)
+  end do
+  !$acc end parallel
+
+  !$acc wait (1)
+  !$acc end data
+
+  do i = 1, N
+     if (a(i) .ne. 3.0) call abort
+     if (b(i) .ne. 9.0) call abort
+     if (c(i) .ne. 4.0) call abort
+     if (d(i) .ne. 1.0) call abort
+  end do
+
+  a(:) = 2.0
+  b(:) = 0.0
+  c(:) = 0.0
+  d(:) = 0.0
+  e(:) = 0.0
+
+  !$acc data copy (a(1:N), b(1:N), c(1:N), d(1:N), e(1:N))
+
+  !$acc parallel async (1)
+  do i = 1, N
+     b(i) = (a(i) * a(i) * a(i)) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  !$acc loop
+  do i = 1, N
+     c(i) = (a(i) * 4) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  !$acc loop
+  do i = 1, N
+     d(i) = ((a(i) * a(i) + a(i)) / a(i)) - a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel wait (1) async (1)
+  !$acc loop
+  do i = 1, N
+     e(i) = a(i) + b(i) + c(i) + d(i)
+  end do
+  !$acc end parallel
+
+  !$acc wait (1)
+  !$acc end data
+
+  do i = 1, N
+     if (a(i) .ne. 2.0) call abort
+     if (b(i) .ne. 4.0) call abort
+     if (c(i) .ne. 4.0) call abort
+     if (d(i) .ne. 1.0) call abort
+     if (e(i) .ne. 11.0) call abort
+  end do
+end program asyncwait
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-2.f90
new file mode 100644
index 0000000..bade52b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-2.f90
@@ -0,0 +1,40 @@
+! { dg-do run }
+
+program parallel_wait
+  integer, parameter :: N = 64
+  real, allocatable :: a(:), b(:), c(:)
+  integer i
+
+  allocate (a(N))
+  allocate (b(N))
+  allocate (c(N))
+
+  !$acc parallel async (0)
+  !$acc loop
+  do i = 1, N
+    a(i) = 1
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  !$acc loop
+  do i = 1, N
+    b(i) = 1
+  end do
+  !$acc end parallel
+
+  !$acc parallel wait (0, 1)
+  !$acc loop
+  do i = 1, N
+    c(i) = a(i) + b(i)
+  end do
+  !$acc end parallel
+
+  do i = 1, N
+    if (c(i) .ne. 2.0) call abort
+  end do
+  
+  deallocate (a)
+  deallocate (b)
+  deallocate (c)
+end program parallel_wait
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-3.f90 b/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-3.f90
new file mode 100644
index 0000000..d48dc11
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/asyncwait-3.f90
@@ -0,0 +1,42 @@
+! { dg-do run }
+
+program parallel_wait
+  integer, parameter :: N = 64
+  real, allocatable :: a(:), b(:), c(:)
+  integer i
+
+  allocate (a(N))
+  allocate (b(N))
+  allocate (c(N))
+
+  !$acc parallel async (0)
+  !$acc loop
+  do i = 1, N
+    a(i) = 1
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  !$acc loop
+  do i = 1, N
+    b(i) = 1
+  end do
+  !$acc end parallel
+
+  !$acc wait (0, 1)
+
+  !$acc parallel
+  !$acc loop
+  do i = 1, N
+    c(i) = a(i) + b(i)
+  end do
+  !$acc end parallel
+
+  do i = 1, N
+    if (c(i) .ne. 2.0) call abort
+  end do
+  
+  deallocate (a)
+  deallocate (b)
+  deallocate (c)
+end program parallel_wait
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/collapse-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/collapse-1.f90
new file mode 100644
index 0000000..4c07bc2
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/collapse-1.f90
@@ -0,0 +1,27 @@
+! { dg-do run }
+
+program collapse1
+  integer :: i, j, k, a(1:3, 4:6, 5:7)
+  logical :: l
+  l = .false.
+  a(:, :, :) = 0
+  !$acc parallel
+  !$acc loop collapse(4 - 1)
+    do i = 1, 3
+      do j = 4, 6
+        do k = 5, 7
+          a(i, j, k) = i + j + k
+        end do
+      end do
+    end do
+  !$acc loop collapse(2) reduction(.or.:l)
+    do i = 1, 3
+      do j = 4, 6
+        do k = 5, 7
+          if (a(i, j, k) .ne. (i + j + k)) l = .true.
+        end do
+      end do
+    end do
+  !$acc end parallel
+  if (l) call abort
+end program collapse1
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/collapse-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/collapse-2.f90
new file mode 100644
index 0000000..ca3b638
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/collapse-2.f90
@@ -0,0 +1,25 @@
+! { dg-do run }
+
+program collapse2
+  integer :: i, j, k, a(1:3, 4:6, 5:7)
+  logical :: l
+  l = .false.
+  a(:, :, :) = 0
+  !$acc parallel
+  !$acc loop collapse(4 - 1)
+    do 164 i = 1, 3
+      do 164 j = 4, 6
+        do 164 k = 5, 7
+          a(i, j, k) = i + j + k
+164      end do
+  !$acc loop collapse(2) reduction(.or.:l)
+firstdo: do i = 1, 3
+      do j = 4, 6
+        do k = 5, 7
+          if (a(i, j, k) .ne. (i + j + k)) l = .true.
+        end do
+      end do
+    end do firstdo
+  !$acc end parallel
+  if (l) call abort
+end program collapse2
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/collapse-3.f90 b/libgomp/testsuite/libgomp.oacc-fortran/collapse-3.f90
new file mode 100644
index 0000000..50e6100
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/collapse-3.f90
@@ -0,0 +1,28 @@
+! { dg-do run }
+
+program collapse3
+  integer :: a(3,3,3), k, kk, kkk, l, ll, lll
+  !$acc parallel
+  !$acc loop collapse(3)
+    do 115 k=1,3
+dokk: do kk=1,3
+        do kkk=1,3
+          a(k,kk,kkk) = 1
+        enddo
+      enddo dokk
+115   continue
+  !$acc end parallel
+  if (any(a(1:3,1:3,1:3).ne.1)) call abort
+
+  !$acc parallel
+  !$acc loop collapse(3)
+dol: do 120 l=1,3
+doll: do ll=1,3
+        do lll=1,3
+          a(l,ll,lll) = 2
+        enddo
+      enddo doll
+120 end do dol
+  !$acc end parallel
+  if (any(a(1:3,1:3,1:3).ne.2)) call abort
+end program collapse3
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/collapse-4.f90 b/libgomp/testsuite/libgomp.oacc-fortran/collapse-4.f90
new file mode 100644
index 0000000..41b66db
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/collapse-4.f90
@@ -0,0 +1,40 @@
+! { dg-do run }
+
+! collapse3.f90:test1
+program collapse4
+  integer :: i, j, k, a(1:7, -3:5, 12:19), b(1:7, -3:5, 12:19)
+  logical :: l, r
+  l = .false.
+  r = .false.
+  a(:, :, :) = 0
+  b(:, :, :) = 0
+  !$acc parallel
+  !$acc loop collapse (3) reduction (.or.:l)
+    do i = 2, 6
+      do j = -2, 4
+        do k = 13, 18
+          l = l.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+          l = l.or.k.lt.13.or.k.gt.18
+          if (.not.l) a(i, j, k) = a(i, j, k) + 1
+        end do
+      end do
+    end do
+  !$acc end parallel
+  do i = 2, 6
+    do j = -2, 4
+      do k = 13, 18
+        r = r.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+        r = r.or.k.lt.13.or.k.gt.18
+        if (.not.l) b(i, j, k) = b(i, j, k) + 1
+      end do
+    end do
+  end do
+  if (l .neqv. r) call abort
+  do i = 2, 6
+    do j = -2, 4
+      do k = 13, 18
+         if (a(i, j, k) .ne. b(i, j, k)) call abort
+      end do
+    end do
+  end do
+end program collapse4
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/collapse-5.f90 b/libgomp/testsuite/libgomp.oacc-fortran/collapse-5.f90
new file mode 100644
index 0000000..8c20f04
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/collapse-5.f90
@@ -0,0 +1,48 @@
+! { dg-do run }
+
+! collapse3.f90:test2
+program collapse5
+  integer :: i, j, k, a(1:7, -3:5, 12:19), b(1:7, -3:5, 12:19)
+  integer :: v1, v2, v3, v4, v5, v6
+  logical :: l, r
+  l = .false.
+  r = .false.
+  a(:, :, :) = 0
+  b(:, :, :) = 0
+  v1 = 3
+  v2 = 6
+  v3 = -2
+  v4 = 4
+  v5 = 13
+  v6 = 18
+  !$acc parallel
+  !$acc loop collapse (3) reduction (.or.:l)
+    do i = v1, v2
+      do j = v3, v4
+        do k = v5, v6
+          l = l.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+          l = l.or.k.lt.13.or.k.gt.18
+          if (.not.l) a(i, j, k) = a(i, j, k) + 1
+          m = i * 100 + j * 10 + k
+        end do
+      end do
+    end do
+  !$acc end parallel
+  do i = v1, v2
+    do j = v3, v4
+      do k = v5, v6
+        r = r.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+        r = r.or.k.lt.13.or.k.gt.18
+        if (.not.l) b(i, j, k) = b(i, j, k) + 1
+      end do
+    end do
+  end do
+  if (l .neqv. r) call abort
+  do i = v1, v2
+    do j = v3, v4
+      do k = v5, v6
+         if (a(i, j, k) .ne. b(i, j, k)) call abort
+      end do
+    end do
+  end do
+end program collapse5
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/collapse-6.f90 b/libgomp/testsuite/libgomp.oacc-fortran/collapse-6.f90
new file mode 100644
index 0000000..7404b91
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/collapse-6.f90
@@ -0,0 +1,50 @@
+! { dg-do run }
+
+! collapse3.f90:test3
+program collapse6
+  integer :: i, j, k, a(1:7, -3:5, 12:19), b(1:7, -3:5, 12:19)
+  integer :: v1, v2, v3, v4, v5, v6, v7, v8, v9
+  logical :: l, r
+  l = .false.
+  r = .false.
+  a(:, :, :) = 0
+  b(:, :, :) = 0
+  v1 = 3
+  v2 = 6
+  v3 = -2
+  v4 = 4
+  v5 = 13
+  v6 = 18
+  v7 = 1
+  v8 = 1
+  v9 = 1
+  !$acc parallel
+  !$acc loop collapse (3) reduction (.or.:l)
+    do i = v1, v2, v7
+      do j = v3, v4, v8
+        do k = v5, v6, v9
+          l = l.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+          l = l.or.k.lt.13.or.k.gt.18
+          if (.not.l) a(i, j, k) = a(i, j, k) + 1
+        end do
+      end do
+    end do
+  !$acc end parallel
+  do i = v1, v2, v7
+    do j = v3, v4, v8
+      do k = v5, v6, v9
+        r = r.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+        r = r.or.k.lt.13.or.k.gt.18
+        if (.not.r) b(i, j, k) = b(i, j, k) + 1
+      end do
+    end do
+  end do
+  if (l .neqv. r) call abort
+  do i = v1, v2, v7
+    do j = v3, v4, v8
+       do k = v5, v6, v9
+         if (a(i, j, k) .ne. b(i, j, k)) call abort
+       end do
+    end do
+  end do
+end program collapse6
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/collapse-7.f90 b/libgomp/testsuite/libgomp.oacc-fortran/collapse-7.f90
new file mode 100644
index 0000000..12efd8c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/collapse-7.f90
@@ -0,0 +1,40 @@
+! { dg-do run }
+
+! collapse3.f90:test4
+program collapse7
+  integer :: i, j, k, a(1:7, -3:5, 12:19), b(1:7, -3:5, 12:19)
+  logical :: l, r
+  l = .false.
+  r = .false.
+  a(:, :, :) = 0
+  b(:, :, :) = 0
+  !$acc parallel
+  !$acc loop collapse (3) reduction (.or.:l)
+    do i = 2, 6
+      do j = -2, 4
+        do k = 13, 18
+          l = l.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+          l = l.or.k.lt.13.or.k.gt.18
+          if (.not.l) a(i, j, k) = a(i, j, k) + 1
+        end do
+      end do
+    end do
+  !$acc end parallel
+  do i = 2, 6
+    do j = -2, 4
+      do k = 13, 18
+        r = r.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+        r = r.or.k.lt.13.or.k.gt.18
+        if (.not.r) b(i, j, k) = b(i, j, k) + 1
+      end do
+    end do
+  end do
+  if (l .neqv. r) call abort
+  do i = 1, 7
+    do j = -3, 5
+      do k = 12, 19
+         if (a(i, j, k) .ne. b(i, j, k)) call abort
+      end do
+    end do
+  end do
+end program collapse7
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/collapse-8.f90 b/libgomp/testsuite/libgomp.oacc-fortran/collapse-8.f90
new file mode 100644
index 0000000..04fbcfe
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/collapse-8.f90
@@ -0,0 +1,47 @@
+! { dg-do run }
+
+! collapse3.f90:test5
+program collapse8
+  integer :: i, j, k, a(1:7, -3:5, 12:19), b(1:7, -3:5, 12:19)
+  integer :: v1, v2, v3, v4, v5, v6
+  logical :: l, r
+  l = .false.
+  r = .false.
+  a(:, :, :) = 0
+  b(:, :, :) = 0
+  v1 = 3
+  v2 = 6
+  v3 = -2
+  v4 = 4
+  v5 = 13
+  v6 = 18
+  !$acc parallel
+  !$acc loop collapse (3) reduction (.or.:l)
+    do i = v1, v2
+      do j = v3, v4
+        do k = v5, v6
+          l = l.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+          l = l.or.k.lt.13.or.k.gt.18
+          if (.not.l) a(i, j, k) = a(i, j, k) + 1
+        end do
+      end do
+    end do
+  !$acc end parallel
+  do i = v1, v2
+    do j = v3, v4
+      do k = v5, v6
+        r = r.or.i.lt.2.or.i.gt.6.or.j.lt.-2.or.j.gt.4
+        r = r.or.k.lt.13.or.k.gt.18
+        if (.not.r) b(i, j, k) = b(i, j, k) + 1
+      end do
+    end do
+  end do
+  if (l .neqv. r) call abort
+  do i = v1, v2
+    do j = v3, v4
+      do k = v5, v6
+         if (a(i, j, k) .ne. b(i, j, k)) call abort
+      end do
+    end do
+  end do
+end program collapse8
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/data-1.f90
new file mode 100644
index 0000000..5e94e2d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-1.f90
@@ -0,0 +1,45 @@
+! { dg-do run }
+
+program test
+  integer, parameter :: N = 8
+  real, allocatable :: a(:), b(:)
+
+  allocate (a(N))
+  allocate (b(N))
+
+  a(:) = 3.0
+  b(:) = 0.0
+
+  !$acc enter data copyin (a(1:N), b(1:N))
+
+  !$acc parallel
+  do i = 1, n
+    b(i) = a (i)
+  end do
+  !$acc end parallel
+
+  !$acc exit data copyout (a(1:N), b(1:N))
+
+  do i = 1, n
+    if (a(i) .ne. 3.0) call abort
+    if (b(i) .ne. 3.0) call abort
+  end do
+
+  a(:) = 5.0
+  b(:) = 1.0
+
+  !$acc enter data copyin (a(1:N), b(1:N))
+
+  !$acc parallel
+  do i = 1, n
+    b(i) = a (i)
+  end do
+  !$acc end parallel
+
+  !$acc exit data copyout (a(1:N), b(1:N))
+
+  do i = 1, n
+    if (a(i) .ne. 5.0) call abort
+    if (b(i) .ne. 5.0) call abort
+  end do
+end program test
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/data-2.f90
new file mode 100644
index 0000000..8736c2a
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-2.f90
@@ -0,0 +1,31 @@
+! { dg-do run }
+
+program test
+  integer, parameter :: N = 8
+  real, allocatable :: a(:,:), b(:,:)
+
+  allocate (a(N,N))
+  allocate (b(N,N))
+
+  a(:,:) = 3.0
+  b(:,:) = 0.0
+
+  !$acc enter data copyin (a(1:N,1:N), b(1:N,1:N))
+
+  !$acc parallel
+  do i = 1, n
+    do j = 1, n
+      b(j,i) = a (j,i)
+    end do
+  end do
+  !$acc end parallel
+
+  !$acc exit data copyout (a(1:N,1:N), b(1:N,1:N))
+
+  do i = 1, n
+    do j = 1, n
+      if (a(j,i) .ne. 3.0) call abort
+      if (b(j,i) .ne. 3.0) call abort
+    end do
+  end do
+end program test
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-3.f90 b/libgomp/testsuite/libgomp.oacc-fortran/data-3.f90
new file mode 100644
index 0000000..9868cb0
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-3.f90
@@ -0,0 +1,131 @@
+! { dg-do run }
+
+program asyncwait
+  real, allocatable :: a(:), b(:), c(:), d(:), e(:)
+  integer i, N
+
+  N = 64
+
+  allocate (a(N))
+  allocate (b(N))
+  allocate (c(N))
+  allocate (d(N))
+  allocate (e(N))
+
+  a(:) = 3.0
+  b(:) = 0.0
+
+  !$acc enter data copyin (a(1:N)) copyin (b(1:N)) copyin (N) async
+
+  !$acc parallel async wait
+  do i = 1, N
+     b(i) = a(i)
+  end do
+  !$acc end parallel
+
+  !$acc wait
+  !$acc exit data copyout (a(1:N)) copyout (b(1:N))
+
+  do i = 1, N
+     if (a(i) .ne. 3.0) call abort
+     if (b(i) .ne. 3.0) call abort
+  end do
+
+  a(:) = 2.0
+  b(:) = 0.0
+
+  !$acc enter data copyin (a(1:N)) copyin (b(1:N)) async (1)
+
+  !$acc parallel async (1) wait (1)
+  do i = 1, N
+     b(i) = a(i)
+  end do
+  !$acc end parallel
+
+  !$acc wait (1)
+  !$acc exit data copyout (a(1:N)) copyout (b(1:N))
+
+  do i = 1, N
+     if (a(i) .ne. 2.0) call abort
+     if (b(i) .ne. 2.0) call abort
+  end do
+
+  a(:) = 3.0
+  b(:) = 0.0
+  c(:) = 0.0
+  d(:) = 0.0
+
+  !$acc enter data copyin (a(1:N)) create (b(1:N)) create (c(1:N)) create (d(1:N))
+
+  !$acc parallel async (1)
+  do i = 1, N
+     b(i) = (a(i) * a(i) * a(i)) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     c(i) = (a(i) * 4) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     d(i) = ((a(i) * a(i)  + a(i)) / a(i)) - a(i)
+  end do
+  !$acc end parallel
+
+  !$acc wait (1)
+  !$acc exit data copyout (a(1:N)) copyout (b(1:N)) copyout (c(1:N)) copyout (d(1:N))
+
+  do i = 1, N
+     if (a(i) .ne. 3.0) call abort
+     if (b(i) .ne. 9.0) call abort
+     if (c(i) .ne. 4.0) call abort
+     if (d(i) .ne. 1.0) call abort
+  end do
+
+  a(:) = 2.0
+  b(:) = 0.0
+  c(:) = 0.0
+  d(:) = 0.0
+  e(:) = 0.0
+
+  !$acc enter data copyin (a(1:N)) create (b(1:N)) create (c(1:N)) create (d(1:N)) copyin (e(1:N))
+
+  !$acc parallel async (1)
+  do i = 1, N
+     b(i) = (a(i) * a(i) * a(i)) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     c(i) = (a(i) * 4) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     d(i) = ((a(i) * a(i) + a(i)) / a(i)) - a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel wait (1) async (1)
+  do i = 1, N
+     e(i) = a(i) + b(i) + c(i) + d(i)
+  end do
+  !$acc end parallel
+
+  !$acc wait (1)
+  !$acc exit data copyout (a(1:N)) copyout (b(1:N)) copyout (c(1:N)) copyout (d(1:N)) copyout (e(1:N))
+  !$acc exit data delete (N)
+
+  do i = 1, N
+     if (a(i) .ne. 2.0) call abort
+     if (b(i) .ne. 4.0) call abort
+     if (c(i) .ne. 4.0) call abort
+     if (d(i) .ne. 1.0) call abort
+     if (e(i) .ne. 11.0) call abort
+  end do
+end program asyncwait
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-4-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/data-4-2.f90
new file mode 100644
index 0000000..16a8598
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-4-2.f90
@@ -0,0 +1,138 @@
+! Copy of data-4.f90 with self exchanged with host for !acc update.
+
+! { dg-do run }
+
+program asyncwait
+  real, allocatable :: a(:), b(:), c(:), d(:), e(:)
+  integer i, N
+
+  N = 64
+
+  allocate (a(N))
+  allocate (b(N))
+  allocate (c(N))
+  allocate (d(N))
+  allocate (e(N))
+
+  a(:) = 3.0
+  b(:) = 0.0
+
+  !$acc enter data copyin (a(1:N)) copyin (b(1:N)) copyin (N) async
+
+  !$acc parallel async wait
+  !$acc loop
+  do i = 1, N
+     b(i) = a(i)
+  end do
+  !$acc end parallel
+
+  !$acc update self (a(1:N), b(1:N)) async wait
+  !$acc wait
+
+  do i = 1, N
+     if (a(i) .ne. 3.0) call abort
+     if (b(i) .ne. 3.0) call abort
+  end do
+
+  a(:) = 2.0
+  b(:) = 0.0
+
+  !$acc update device (a(1:N), b(1:N)) async (1)
+
+  !$acc parallel async (1) wait (1)
+  !$acc loop
+  do i = 1, N
+     b(i) = a(i)
+  end do
+  !$acc end parallel
+
+  !$acc update host (a(1:N), b(1:N)) async (1) wait (1)
+  !$acc wait (1)
+
+  do i = 1, N
+     if (a(i) .ne. 2.0) call abort
+     if (b(i) .ne. 2.0) call abort
+  end do
+
+  a(:) = 3.0
+  b(:) = 0.0
+  c(:) = 0.0
+  d(:) = 0.0
+
+  !$acc enter data copyin (c(1:N), d(1:N)) async (1)
+  !$acc update device (a(1:N), b(1:N)) async (1)
+
+  !$acc parallel async (1)
+  do i = 1, N
+     b(i) = (a(i) * a(i) * a(i)) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     c(i) = (a(i) * 4) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     d(i) = ((a(i) * a(i)  + a(i)) / a(i)) - a(i)
+  end do
+  !$acc end parallel
+
+  !$acc update self (a(1:N), b(1:N), c(1:N), d(1:N)) async (1) wait (1)
+
+  !$acc wait (1)
+
+  do i = 1, N
+     if (a(i) .ne. 3.0) call abort
+     if (b(i) .ne. 9.0) call abort
+     if (c(i) .ne. 4.0) call abort
+     if (d(i) .ne. 1.0) call abort
+  end do
+
+  a(:) = 2.0
+  b(:) = 0.0
+  c(:) = 0.0
+  d(:) = 0.0
+  e(:) = 0.0
+
+  !$acc enter data copyin (e(1:N)) async (1)
+  !$acc update device (a(1:N), b(1:N), c(1:N), d(1:N)) async (1)
+
+  !$acc parallel async (1)
+  do i = 1, N
+     b(i) = (a(i) * a(i) * a(i)) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     c(i) = (a(i) * 4) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     d(i) = ((a(i) * a(i) + a(i)) / a(i)) - a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel wait (1) async (1)
+  do i = 1, N
+     e(i) = a(i) + b(i) + c(i) + d(i)
+  end do
+  !$acc end parallel
+
+  !$acc update self (a(1:N), b(1:N), c(1:N), d(1:N), e(1:N)) async (1) wait (1)
+  !$acc wait (1)
+  !$acc exit data delete (N, a(1:N), b(1:N), c(1:N), d(1:N), e(1:N))
+
+  do i = 1, N
+     if (a(i) .ne. 2.0) call abort
+     if (b(i) .ne. 4.0) call abort
+     if (c(i) .ne. 4.0) call abort
+     if (d(i) .ne. 1.0) call abort
+     if (e(i) .ne. 11.0) call abort
+  end do
+end program asyncwait
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-4.f90 b/libgomp/testsuite/libgomp.oacc-fortran/data-4.f90
new file mode 100644
index 0000000..f6886b0
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-4.f90
@@ -0,0 +1,136 @@
+! { dg-do run }
+
+program asyncwait
+  real, allocatable :: a(:), b(:), c(:), d(:), e(:)
+  integer i, N
+
+  N = 64
+
+  allocate (a(N))
+  allocate (b(N))
+  allocate (c(N))
+  allocate (d(N))
+  allocate (e(N))
+
+  a(:) = 3.0
+  b(:) = 0.0
+
+  !$acc enter data copyin (a(1:N)) copyin (b(1:N)) copyin (N) async
+
+  !$acc parallel async wait
+  !$acc loop
+  do i = 1, N
+     b(i) = a(i)
+  end do
+  !$acc end parallel
+
+  !$acc update host (a(1:N), b(1:N)) async wait
+  !$acc wait
+
+  do i = 1, N
+     if (a(i) .ne. 3.0) call abort
+     if (b(i) .ne. 3.0) call abort
+  end do
+
+  a(:) = 2.0
+  b(:) = 0.0
+
+  !$acc update device (a(1:N), b(1:N)) async (1)
+
+  !$acc parallel async (1) wait (1)
+  !$acc loop
+  do i = 1, N
+     b(i) = a(i)
+  end do
+  !$acc end parallel
+
+  !$acc update self (a(1:N), b(1:N)) async (1) wait (1)
+  !$acc wait (1)
+
+  do i = 1, N
+     if (a(i) .ne. 2.0) call abort
+     if (b(i) .ne. 2.0) call abort
+  end do
+
+  a(:) = 3.0
+  b(:) = 0.0
+  c(:) = 0.0
+  d(:) = 0.0
+
+  !$acc enter data copyin (c(1:N), d(1:N)) async (1)
+  !$acc update device (a(1:N), b(1:N)) async (1)
+
+  !$acc parallel async (1)
+  do i = 1, N
+     b(i) = (a(i) * a(i) * a(i)) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     c(i) = (a(i) * 4) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     d(i) = ((a(i) * a(i)  + a(i)) / a(i)) - a(i)
+  end do
+  !$acc end parallel
+
+  !$acc update host (a(1:N), b(1:N), c(1:N), d(1:N)) async (1) wait (1)
+
+  !$acc wait (1)
+
+  do i = 1, N
+     if (a(i) .ne. 3.0) call abort
+     if (b(i) .ne. 9.0) call abort
+     if (c(i) .ne. 4.0) call abort
+     if (d(i) .ne. 1.0) call abort
+  end do
+
+  a(:) = 2.0
+  b(:) = 0.0
+  c(:) = 0.0
+  d(:) = 0.0
+  e(:) = 0.0
+
+  !$acc enter data copyin (e(1:N)) async (1)
+  !$acc update device (a(1:N), b(1:N), c(1:N), d(1:N)) async (1)
+
+  !$acc parallel async (1)
+  do i = 1, N
+     b(i) = (a(i) * a(i) * a(i)) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     c(i) = (a(i) * 4) / a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel async (1)
+  do i = 1, N
+     d(i) = ((a(i) * a(i) + a(i)) / a(i)) - a(i)
+  end do
+  !$acc end parallel
+
+  !$acc parallel wait (1) async (1)
+  do i = 1, N
+     e(i) = a(i) + b(i) + c(i) + d(i)
+  end do
+  !$acc end parallel
+
+  !$acc update host (a(1:N), b(1:N), c(1:N), d(1:N), e(1:N)) async (1) wait (1)
+  !$acc wait (1)
+  !$acc exit data delete (N, a(1:N), b(1:N), c(1:N), d(1:N), e(1:N))
+
+  do i = 1, N
+     if (a(i) .ne. 2.0) call abort
+     if (b(i) .ne. 4.0) call abort
+     if (c(i) .ne. 4.0) call abort
+     if (d(i) .ne. 1.0) call abort
+     if (e(i) .ne. 11.0) call abort
+  end do
+end program asyncwait
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-already-1.f b/libgomp/testsuite/libgomp.oacc-fortran/data-already-1.f
new file mode 100644
index 0000000..ac220ab
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-already-1.f
@@ -0,0 +1,17 @@
+! { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } }
+
+      IMPLICIT NONE
+      INCLUDE "openacc_lib.h"
+
+      INTEGER I
+
+      CALL ACC_COPYIN (I)
+
+!$ACC DATA COPY (I)
+      I = 0
+!$ACC END DATA
+
+      END
+
+! { dg-shouldfail "" }
+! { dg-output "Trying to map into device .* object when .* is already mapped" }
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-already-2.f b/libgomp/testsuite/libgomp.oacc-fortran/data-already-2.f
new file mode 100644
index 0000000..2c5254b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-already-2.f
@@ -0,0 +1,16 @@
+! { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } }
+
+      IMPLICIT NONE
+
+      INTEGER I
+
+!$ACC DATA PRESENT_OR_COPY (I)
+!$ACC DATA COPYOUT (I)
+      I = 0
+!$ACC END DATA
+!$ACC END DATA
+
+      END
+
+! { dg-shouldfail "" }
+! { dg-output "Trying to map into device .* object when .* is already mapped" }
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-already-3.f b/libgomp/testsuite/libgomp.oacc-fortran/data-already-3.f
new file mode 100644
index 0000000..c41de28
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-already-3.f
@@ -0,0 +1,15 @@
+! { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } }
+
+      IMPLICIT NONE
+      INCLUDE "openacc_lib.h"
+
+      INTEGER I
+
+!$ACC DATA PRESENT_OR_COPY (I)
+      CALL ACC_COPYIN (I)
+!$ACC END DATA
+
+      END
+
+! { dg-shouldfail "" }
+! { dg-output "already mapped to" }
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-already-4.f b/libgomp/testsuite/libgomp.oacc-fortran/data-already-4.f
new file mode 100644
index 0000000..f54bf58
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-already-4.f
@@ -0,0 +1,14 @@
+! { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } }
+
+      IMPLICIT NONE
+      INCLUDE "openacc_lib.h"
+
+      INTEGER I
+
+      CALL ACC_PRESENT_OR_COPYIN (I)
+      CALL ACC_COPYIN (I)
+
+      END
+
+! { dg-shouldfail "" }
+! { dg-output "already mapped to" }
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-already-5.f b/libgomp/testsuite/libgomp.oacc-fortran/data-already-5.f
new file mode 100644
index 0000000..9a3e94f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-already-5.f
@@ -0,0 +1,14 @@
+! { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } }
+
+      IMPLICIT NONE
+      INCLUDE "openacc_lib.h"
+
+      INTEGER I
+
+!$ACC ENTER DATA CREATE (I)
+      CALL ACC_COPYIN (I)
+
+      END
+
+! { dg-shouldfail "" }
+! { dg-output "already mapped to" }
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-already-6.f b/libgomp/testsuite/libgomp.oacc-fortran/data-already-6.f
new file mode 100644
index 0000000..eaf5d98
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-already-6.f
@@ -0,0 +1,14 @@
+! { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } }
+
+      IMPLICIT NONE
+      INCLUDE "openacc_lib.h"
+
+      INTEGER I
+
+      CALL ACC_PRESENT_OR_COPYIN (I)
+!$ACC ENTER DATA CREATE (I)
+
+      END
+
+! { dg-shouldfail "" }
+! { dg-output "already mapped to" }
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-already-7.f b/libgomp/testsuite/libgomp.oacc-fortran/data-already-7.f
new file mode 100644
index 0000000..d96bf0b
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-already-7.f
@@ -0,0 +1,14 @@
+! { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } }
+
+      IMPLICIT NONE
+      INCLUDE "openacc_lib.h"
+
+      INTEGER I
+
+!$ACC ENTER DATA CREATE (I)
+      CALL ACC_CREATE (I)
+
+      END
+
+! { dg-shouldfail "" }
+! { dg-output "already mapped to" }
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/data-already-8.f b/libgomp/testsuite/libgomp.oacc-fortran/data-already-8.f
new file mode 100644
index 0000000..16da048
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/data-already-8.f
@@ -0,0 +1,16 @@
+! { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } }
+
+      IMPLICIT NONE
+
+      INTEGER I
+
+!$ACC DATA CREATE (I)
+!$ACC PARALLEL COPYIN (I)
+      I = 0
+!$ACC END PARALLEL
+!$ACC END DATA
+
+      END
+
+! { dg-shouldfail "" }
+! { dg-output "Trying to map into device .* object when .* is already mapped" }
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/fortran.exp b/libgomp/testsuite/libgomp.oacc-fortran/fortran.exp
new file mode 100644
index 0000000..a8f62e8
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/fortran.exp
@@ -0,0 +1,98 @@
+# This whole file adapted from libgomp.fortran/fortran.exp.
+
+load_lib libgomp-dg.exp
+load_gcc_lib gcc-dg.exp
+load_gcc_lib gfortran-dg.exp
+
+global shlib_ext
+global ALWAYS_CFLAGS
+
+set shlib_ext [get_shlib_extension]
+set lang_library_path	"../libgfortran/.libs"
+set lang_link_flags	"-lgfortran"
+if [info exists lang_include_flags] then {
+    unset lang_include_flags
+}
+set lang_test_file_found 0
+set quadmath_library_path "../libquadmath/.libs"
+
+
+# Initialize dg.
+dg-init
+
+# Turn on OpenACC.
+lappend ALWAYS_CFLAGS "additional_flags=-fopenacc"
+
+if { $blddir != "" } {
+    set lang_source_re {^.*\.[fF](|90|95|03|08)$}
+    set lang_include_flags "-fintrinsic-modules-path=${blddir}"
+    # Look for a static libgfortran first.
+    if [file exists "${blddir}/${lang_library_path}/libgfortran.a"] {
+        set lang_test_file "${lang_library_path}/libgfortran.a"
+        set lang_test_file_found 1
+	# We may have a shared only build, so look for a shared libgfortran.
+    } elseif [file exists "${blddir}/${lang_library_path}/libgfortran.${shlib_ext}"] {
+        set lang_test_file "${lang_library_path}/libgfortran.${shlib_ext}"
+        set lang_test_file_found 1
+    } else {
+        puts "No libgfortran library found, will not execute fortran tests"
+    }
+} elseif [info exists GFORTRAN_UNDER_TEST] {
+    set lang_test_file_found 1
+    # Needs to exist for libgomp.exp.
+    set lang_test_file ""
+} else {
+    puts "GFORTRAN_UNDER_TEST not defined, will not execute fortran tests"
+}
+
+if { $lang_test_file_found } {
+    # Gather a list of all tests.
+    set tests [lsort [find $srcdir/$subdir *.\[fF\]{,90,95,03,08}]]
+
+    if { $blddir != "" } {
+	if { [file exists "${blddir}/${quadmath_library_path}/libquadmath.a"]
+	     || [file exists "${blddir}/${quadmath_library_path}/libquadmath.${shlib_ext}"] } {
+	    lappend ALWAYS_CFLAGS "ldflags=-L${blddir}/${quadmath_library_path}/"
+	    # Allow for spec subsitution.
+	    lappend ALWAYS_CFLAGS "additional_flags=-B${blddir}/${quadmath_library_path}/"
+	    set ld_library_path "$always_ld_library_path:${blddir}/${lang_library_path}:${blddir}/${quadmath_library_path}"
+	} else {
+	    set ld_library_path "$always_ld_library_path:${blddir}/${lang_library_path}"
+	}
+    } else {
+        set ld_library_path "$always_ld_library_path"
+    }
+    append ld_library_path [gcc-set-multilib-library-path $GCC_UNDER_TEST]
+    set_ld_library_path_env_vars
+
+    # Test OpenACC with available accelerators.
+    foreach offload_target_openacc $offload_targets_s_openacc {
+	set tagopt "-DACC_DEVICE_TYPE_$offload_target_openacc=1"
+
+	switch $offload_target_openacc {
+	    host {
+		set acc_mem_shared 1
+	    }
+	    host_nonshm {
+		set acc_mem_shared 0
+	    }
+	    nvidia {
+		set acc_mem_shared 0
+	    }
+	    default {
+		set acc_mem_shared 0
+	    }
+	}
+	set tagopt "$tagopt -DACC_MEM_SHARED=$acc_mem_shared"
+
+	setenv ACC_DEVICE_TYPE $offload_target_openacc
+
+	# For Fortran we're doing torture testing, as Fortran has far more tests
+	# with arrays etc. that testing just -O0 or -O2 is insufficient, that is
+	# typically not the case for C/C++.
+	gfortran-dg-runtest $tests "$tagopt" ""
+    }
+}
+
+# All done.
+dg-finish
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/lib-1.f90
new file mode 100644
index 0000000..51dc452
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-1.f90
@@ -0,0 +1,13 @@
+use openacc
+
+if (acc_get_num_devices (acc_device_host) .ne. 1) call abort
+call acc_set_device_type (acc_device_host)
+if (acc_get_device_type () .ne. acc_device_host) call abort
+call acc_set_device_num (0, acc_device_host)
+if (acc_get_device_num (acc_device_host) .ne. 0) call abort
+call acc_shutdown (acc_device_host)
+
+call acc_init (acc_device_host)
+call acc_shutdown (acc_device_host)
+
+end
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-10.f90 b/libgomp/testsuite/libgomp.oacc-fortran/lib-10.f90
new file mode 100644
index 0000000..a54d6a7
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-10.f90
@@ -0,0 +1,82 @@
+! { dg-do run }
+
+program main
+  implicit none
+  include "openacc_lib.h"
+
+  integer, target :: a_3d_i(10, 10, 10)
+  complex a_3d_c(10, 10, 10)
+  real a_3d_r(10, 10, 10)
+
+  integer i, j, k
+  complex c
+  real r
+  integer, parameter :: i_size = sizeof (i)
+  integer, parameter :: c_size = sizeof (c)
+  integer, parameter :: r_size = sizeof (r)
+
+  if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+  call acc_init (acc_device_nvidia)
+
+  call set3d (.FALSE., a_3d_i, a_3d_c, a_3d_r)
+
+  call acc_copyin (a_3d_i)
+  call acc_copyin (a_3d_c)
+  call acc_copyin (a_3d_r)
+
+  if (acc_is_present (a_3d_i) .neqv. .TRUE.) call abort
+  if (acc_is_present (a_3d_c) .neqv. .TRUE.) call abort
+  if (acc_is_present (a_3d_r) .neqv. .TRUE.) call abort
+
+  do i = 1, 10
+    do j = 1, 10
+      do k = 1, 10
+        if (acc_is_present (a_3d_i(i, j, k), i_size) .neqv. .TRUE.) call abort
+        if (acc_is_present (a_3d_c(i, j, k), i_size) .neqv. .TRUE.) call abort
+        if (acc_is_present (a_3d_r(i, j, k), i_size) .neqv. .TRUE.) call abort
+      end do
+    end do
+  end do
+
+  call acc_shutdown (acc_device_nvidia)
+
+contains
+
+  subroutine set3d (clear, a_i, a_c, a_r)
+  logical clear
+  integer, dimension (:,:,:), intent (inout) :: a_i
+  complex, dimension (:,:,:), intent (inout) :: a_c
+  real, dimension (:,:,:), intent (inout) :: a_r
+
+  integer i, j, k
+  integer lb1, ub1, lb2, ub2, lb3, ub3
+
+  lb1 = lbound (a_i, 1)
+  ub1 = ubound (a_i, 1)
+
+  lb2 = lbound (a_i, 2)
+  ub2 = ubound (a_i, 2)
+
+  lb3 = lbound (a_i, 3)
+  ub3 = ubound (a_i, 3)
+
+  do i = lb1, ub1
+    do j = lb2, ub2
+      do k = lb3, ub3
+        if (clear) then
+          a_i(i, j, k) = 0
+          a_c(i, j, k) = cmplx (0.0, 0.0)
+          a_r(i, j, k) = 0.0
+        else
+          a_i(i, j, k) = i
+          a_c(i, j, k) = cmplx (i, j)
+          a_r(i, j, k) = i
+        end if
+      end do
+    end do
+  end do
+
+  end subroutine
+
+end program
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-2.f b/libgomp/testsuite/libgomp.oacc-fortran/lib-2.f
new file mode 100644
index 0000000..a9d70b2
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-2.f
@@ -0,0 +1,13 @@
+      USE OPENACC
+
+      IF (ACC_GET_NUM_DEVICES (ACC_DEVICE_HOST) .NE. 1) CALL ABORT
+      CALL ACC_SET_DEVICE_TYPE (ACC_DEVICE_HOST)
+      IF (ACC_GET_DEVICE_TYPE () .NE. ACC_DEVICE_HOST) CALL ABORT
+      CALL ACC_SET_DEVICE_NUM (0, ACC_DEVICE_HOST)
+      IF (ACC_GET_DEVICE_NUM (ACC_DEVICE_HOST) .NE. 0) CALL ABORT
+      CALL ACC_SHUTDOWN (ACC_DEVICE_HOST)
+
+      CALL ACC_INIT (ACC_DEVICE_HOST)
+      CALL ACC_SHUTDOWN (ACC_DEVICE_HOST)
+
+      END
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-3.f b/libgomp/testsuite/libgomp.oacc-fortran/lib-3.f
new file mode 100644
index 0000000..56d2cd2
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-3.f
@@ -0,0 +1,13 @@
+      INCLUDE "openacc_lib.h"
+
+      IF (ACC_GET_NUM_DEVICES (ACC_DEVICE_HOST) .NE. 1) CALL ABORT
+      CALL ACC_SET_DEVICE_TYPE (ACC_DEVICE_HOST)
+      IF (ACC_GET_DEVICE_TYPE () .NE. ACC_DEVICE_HOST) CALL ABORT
+      CALL ACC_SET_DEVICE_NUM (0, ACC_DEVICE_HOST)
+      IF (ACC_GET_DEVICE_NUM (ACC_DEVICE_HOST) .NE. 0) CALL ABORT
+      CALL ACC_SHUTDOWN (ACC_DEVICE_HOST)
+
+      CALL ACC_INIT (ACC_DEVICE_HOST)
+      CALL ACC_SHUTDOWN (ACC_DEVICE_HOST)
+
+      END
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-4.f90 b/libgomp/testsuite/libgomp.oacc-fortran/lib-4.f90
new file mode 100644
index 0000000..3a2b661
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-4.f90
@@ -0,0 +1,35 @@
+! { dg-do run }
+
+program main
+  use openacc
+  implicit none
+
+  integer n
+
+  if (acc_get_num_devices (acc_device_host) .ne. 1) call abort
+
+  if (acc_get_num_devices (acc_device_none) .ne. 0) call abort
+
+  call acc_init (acc_device_host)
+
+  if (acc_get_device_type () .ne. acc_device_host) call abort
+
+  call acc_set_device_type (acc_device_host)
+
+  if (acc_get_device_type () .ne. acc_device_host) call abort
+
+  n = 0
+
+  call acc_set_device_num (n, acc_device_host)
+
+  if (acc_get_device_num (acc_device_host) .ne. 0) call abort
+
+  if (.NOT. acc_async_test (n) ) call abort
+
+  call acc_wait (n)
+
+  call acc_wait_all ()
+
+  call acc_shutdown (acc_device_host)
+
+end program
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-5.f90 b/libgomp/testsuite/libgomp.oacc-fortran/lib-5.f90
new file mode 100644
index 0000000..e68eb89
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-5.f90
@@ -0,0 +1,31 @@
+! { dg-do run }
+
+program main
+  use openacc
+  implicit none
+
+  integer n
+
+  if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+  call acc_init (acc_device_nvidia)
+
+  n = 0
+
+  call acc_set_device_num (n, acc_device_nvidia)
+
+  if (acc_get_device_num (acc_device_nvidia) .ne. 0) call abort
+
+  if (acc_get_num_devices (acc_device_nvidia) .gt. 1) then
+
+    n = 1
+
+    call acc_set_device_num (n, acc_device_nvidia)
+
+    if (acc_get_device_num (acc_device_nvidia) .ne. 1) call abort
+
+  end if
+
+  call acc_shutdown (acc_device_nvidia)
+
+end program
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-6.f90 b/libgomp/testsuite/libgomp.oacc-fortran/lib-6.f90
new file mode 100644
index 0000000..401ad66
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-6.f90
@@ -0,0 +1,35 @@
+! { dg-do run }
+
+program main
+  implicit none
+  include "openacc_lib.h"
+
+  integer n
+
+  if (acc_get_num_devices (acc_device_host) .ne. 1) call abort
+
+  if (acc_get_num_devices (acc_device_none) .ne. 0) call abort
+
+  call acc_init (acc_device_host)
+
+  if (acc_get_device_type () .ne. acc_device_host) call abort
+
+  call acc_set_device_type (acc_device_host)
+
+  if (acc_get_device_type () .ne. acc_device_host) call abort
+
+  n = 0
+
+  call acc_set_device_num (n, acc_device_host)
+
+  if (acc_get_device_num (acc_device_host) .ne. 0) call abort
+
+  if (.NOT. acc_async_test (n) ) call abort
+
+  call acc_wait (n)
+
+  call acc_wait_all ()
+
+  call acc_shutdown (acc_device_host)
+
+end program
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-7.f90 b/libgomp/testsuite/libgomp.oacc-fortran/lib-7.f90
new file mode 100644
index 0000000..422df53
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-7.f90
@@ -0,0 +1,31 @@
+! { dg-do run }
+
+program main
+  implicit none
+  include "openacc_lib.h"
+
+  integer n
+
+  if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+  call acc_init (acc_device_nvidia)
+
+  n = 0
+
+  call acc_set_device_num (n, acc_device_nvidia)
+
+  if (acc_get_device_num (acc_device_nvidia) .ne. 0) call abort
+
+  if (acc_get_num_devices (acc_device_nvidia) .gt. 1) then
+
+    n = 1
+
+    call acc_set_device_num (n, acc_device_nvidia)
+
+    if (acc_get_device_num (acc_device_nvidia) .ne. 1) call abort
+
+  end if
+
+  call acc_shutdown (acc_device_nvidia)
+
+end program
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/lib-8.f90 b/libgomp/testsuite/libgomp.oacc-fortran/lib-8.f90
new file mode 100644
index 0000000..ad758b2
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/lib-8.f90
@@ -0,0 +1,83 @@
+! { dg-do run }
+
+program main
+  use openacc
+  use iso_c_binding
+  implicit none
+
+  integer, target :: a_3d_i(10, 10, 10)
+  complex a_3d_c(10, 10, 10)
+  real a_3d_r(10, 10, 10)
+
+  integer i, j, k
+  complex c
+  real r
+  integer, parameter :: i_size = sizeof (i)
+  integer, parameter :: c_size = sizeof (c)
+  integer, parameter :: r_size = sizeof (r)
+
+  if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+  call acc_init (acc_device_nvidia)
+
+  call set3d (.FALSE., a_3d_i, a_3d_c, a_3d_r)
+
+  call acc_copyin (a_3d_i)
+  call acc_copyin (a_3d_c)
+  call acc_copyin (a_3d_r)
+
+  if (acc_is_present (a_3d_i) .neqv. .TRUE.) call abort
+  if (acc_is_present (a_3d_c) .neqv. .TRUE.) call abort
+  if (acc_is_present (a_3d_r) .neqv. .TRUE.) call abort
+
+  do i = 1, 10
+    do j = 1, 10
+      do k = 1, 10
+        if (acc_is_present (a_3d_i(i, j, k), i_size) .neqv. .TRUE.) call abort
+        if (acc_is_present (a_3d_c(i, j, k), i_size) .neqv. .TRUE.) call abort
+        if (acc_is_present (a_3d_r(i, j, k), i_size) .neqv. .TRUE.) call abort
+      end do
+    end do
+  end do
+
+  call acc_shutdown (acc_device_nvidia)
+
+contains
+
+  subroutine set3d (clear, a_i, a_c, a_r)
+  logical clear
+  integer, dimension (:,:,:), intent (inout) :: a_i
+  complex, dimension (:,:,:), intent (inout) :: a_c
+  real, dimension (:,:,:), intent (inout) :: a_r
+
+  integer i, j, k
+  integer lb1, ub1, lb2, ub2, lb3, ub3
+
+  lb1 = lbound (a_i, 1)
+  ub1 = ubound (a_i, 1)
+
+  lb2 = lbound (a_i, 2)
+  ub2 = ubound (a_i, 2)
+
+  lb3 = lbound (a_i, 3)
+  ub3 = ubound (a_i, 3)
+
+  do i = lb1, ub1
+    do j = lb2, ub2
+      do k = lb3, ub3
+        if (clear) then
+          a_i(i, j, k) = 0
+          a_c(i, j, k) = cmplx (0.0, 0.0)
+          a_r(i, j, k) = 0.0
+        else
+          a_i(i, j, k) = i
+          a_c(i, j, k) = cmplx (i, j)
+          a_r(i, j, k) = i
+        end if
+      end do
+    end do
+  end do
+
+  end subroutine
+
+end program
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/map-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/map-1.f90
new file mode 100644
index 0000000..082dd8a
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/map-1.f90
@@ -0,0 +1,97 @@
+program map
+  integer, parameter     :: n = 20, c = 10
+  integer                :: i, a(n), b(n)
+
+  a(:) = 0
+  b(:) = 0
+
+  ! COPY
+
+  !$acc parallel copy (a)
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  do i = 1, n
+     b(i) = i
+  end do
+
+  call check (a, b, n)
+
+  ! COPYOUT
+
+  a(:) = 0
+
+  !$acc parallel copyout (a)
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  do i = 1, n
+     if (a(i) .ne. b(i)) call abort
+  end do
+  call check (a, b, n)
+
+  ! COPYIN
+
+  a(:) = 0
+
+  !$acc parallel copyout (a) copyin (b)
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPY
+
+  !$acc parallel pcopy (a)
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPYOUT
+
+  a(:) = 0
+
+  !$acc parallel pcopyout (a)
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPYIN
+
+  a(:) = 0
+
+  !$acc parallel pcopyout (a) pcopyin (b)
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+end program map
+
+subroutine check (a, b, n)
+  integer :: n, a(n), b(n)
+  integer :: i
+
+  do i = 1, n
+     if (a(i) .ne. b(i)) call abort
+  end do
+end subroutine check
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/openacc_version-1.f b/libgomp/testsuite/libgomp.oacc-fortran/openacc_version-1.f
new file mode 100644
index 0000000..db3c6b1
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/openacc_version-1.f
@@ -0,0 +1,9 @@
+! { dg-do run }
+
+      program main
+      implicit none
+      include "openacc_lib.h"
+
+      if (openacc_version .ne. 201306) call abort;
+
+      end program main
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/openacc_version-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/openacc_version-2.f90
new file mode 100644
index 0000000..a14ecdd
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/openacc_version-2.f90
@@ -0,0 +1,9 @@
+! { dg-do run }
+
+program main
+  use openacc
+  implicit none
+
+  if (openacc_version .ne. 201306) call abort;
+
+end program main
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/pointer-align-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/pointer-align-1.f90
new file mode 100644
index 0000000..a5e1fcb
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/pointer-align-1.f90
@@ -0,0 +1,21 @@
+! PR middle-end/63247
+
+program test
+  implicit none
+
+  integer(kind=2) a(4)
+
+  a = 10;
+
+  !$acc parallel copy(a(2:4))
+  a(2) = 52
+  a(3) = 53
+  a(4) = 54
+  !$acc end parallel
+
+  if (a(1) .ne. 10) call abort
+  if (a(2) .ne. 52) call abort
+  if (a(3) .ne. 53) call abort
+  if (a(4) .ne. 54) call abort
+
+end program test
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/pset-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/pset-1.f90
new file mode 100644
index 0000000..1a1d4c7
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/pset-1.f90
@@ -0,0 +1,229 @@
+! { dg-do run }
+
+program test
+  implicit none
+  integer, allocatable :: a1(:)
+  integer, allocatable :: b1(:)
+  integer, allocatable :: c1(:)
+  integer, allocatable :: b2(:,:)
+  integer, allocatable :: c3(:,:,:)
+
+  allocate (a1(5))
+  if (.not.allocated (a1)) call abort()
+
+  a1 = 10
+
+  !$acc parallel copy(a1(1:5))
+  a1(1) = 1
+  a1(2) = 2
+  a1(3) = 3
+  a1(4) = 4
+  a1(5) = 5
+  !$acc end parallel
+
+  if (a1(1) .ne. 1) call abort
+  if (a1(2) .ne. 2) call abort
+  if (a1(3) .ne. 3) call abort
+  if (a1(4) .ne. 4) call abort
+  if (a1(5) .ne. 5) call abort
+
+  deallocate(a1)
+
+  allocate (a1(0:4))
+  if (.not.allocated (a1)) call abort()
+
+  a1 = 10
+
+  !$acc parallel copy(a1(0:4))
+  a1(0) = 1
+  a1(1) = 2
+  a1(2) = 3
+  a1(3) = 4
+  a1(4) = 5
+  !$acc end parallel
+
+  if (a1(0) .ne. 1) call abort
+  if (a1(1) .ne. 2) call abort
+  if (a1(2) .ne. 3) call abort
+  if (a1(3) .ne. 4) call abort
+  if (a1(4) .ne. 5) call abort
+
+  deallocate(a1)
+
+  allocate (b2(5,5))
+  if (.not.allocated (b2)) call abort()
+
+  b2 = 11
+
+  !$acc parallel copy(b2(1:5,1:5))
+  b2(1,1) = 1
+  b2(2,2) = 2
+  b2(3,3) = 3
+  b2(4,4) = 4
+  b2(5,5) = 5
+  !$acc end parallel
+
+  if (b2(1,1) .ne. 1) call abort
+  if (b2(2,2) .ne. 2) call abort
+  if (b2(3,3) .ne. 3) call abort
+  if (b2(4,4) .ne. 4) call abort
+  if (b2(5,5) .ne. 5) call abort
+
+  deallocate(b2)
+
+  allocate (b2(0:4,0:4))
+  if (.not.allocated (b2)) call abort()
+
+  b2 = 11
+
+  !$acc parallel copy(b2(0:4,0:4))
+  b2(0,0) = 1
+  b2(1,1) = 2
+  b2(2,2) = 3
+  b2(3,3) = 4
+  b2(4,4) = 5
+  !$acc end parallel
+
+  if (b2(0,0) .ne. 1) call abort
+  if (b2(1,1) .ne. 2) call abort
+  if (b2(2,2) .ne. 3) call abort
+  if (b2(3,3) .ne. 4) call abort
+  if (b2(4,4) .ne. 5) call abort
+
+  deallocate(b2)
+
+  allocate (c3(5,5,5))
+  if (.not.allocated (c3)) call abort()
+
+  c3 = 12
+
+  !$acc parallel copy(c3(1:5,1:5,1:5))
+  c3(1,1,1) = 1
+  c3(2,2,2) = 2
+  c3(3,3,3) = 3
+  c3(4,4,4) = 4
+  c3(5,5,5) = 5
+  !$acc end parallel
+
+  if (c3(1,1,1) .ne. 1) call abort
+  if (c3(2,2,2) .ne. 2) call abort
+  if (c3(3,3,3) .ne. 3) call abort
+  if (c3(4,4,4) .ne. 4) call abort
+  if (c3(5,5,5) .ne. 5) call abort
+
+  deallocate(c3)
+
+  allocate (c3(0:4,0:4,0:4))
+  if (.not.allocated (c3)) call abort()
+
+  c3 = 12
+
+  !$acc parallel copy(c3(0:4,0:4,0:4))
+  c3(0,0,0) = 1
+  c3(1,1,1) = 2
+  c3(2,2,2) = 3
+  c3(3,3,3) = 4
+  c3(4,4,4) = 5
+  !$acc end parallel
+
+  if (c3(0,0,0) .ne. 1) call abort
+  if (c3(1,1,1) .ne. 2) call abort
+  if (c3(2,2,2) .ne. 3) call abort
+  if (c3(3,3,3) .ne. 4) call abort
+  if (c3(4,4,4) .ne. 5) call abort
+
+  deallocate(c3)
+
+  allocate (a1(5))
+  if (.not.allocated (a1)) call abort()
+
+  allocate (b1(5))
+  if (.not.allocated (b1)) call abort()
+
+  allocate (c1(5))
+  if (.not.allocated (c1)) call abort()
+
+  a1 = 10
+  b1 = 3
+  c1 = 7
+   
+  !$acc parallel copyin(a1(1:5)) create(c1(1:5)) copyout(b1(1:5))
+  c1(1) = a1(1)
+  c1(2) = a1(2)
+  c1(3) = a1(3)
+  c1(4) = a1(4)
+  c1(5) = a1(5)
+
+  b1(1) = c1(1)
+  b1(2) = c1(2)
+  b1(3) = c1(3)
+  b1(4) = c1(4)
+  b1(5) = c1(5)
+  !$acc end parallel
+
+  if (b1(1) .ne. 10) call abort
+  if (b1(2) .ne. 10) call abort
+  if (b1(3) .ne. 10) call abort
+  if (b1(4) .ne. 10) call abort
+  if (b1(5) .ne. 10) call abort
+
+  deallocate(a1)
+  deallocate(b1)
+  deallocate(c1)
+
+  allocate (a1(0:4))
+  if (.not.allocated (a1)) call abort()
+
+  allocate (b1(0:4))
+  if (.not.allocated (b1)) call abort()
+
+  allocate (c1(0:4))
+  if (.not.allocated (c1)) call abort()
+
+  a1 = 10
+  b1 = 3
+  c1 = 7
+   
+  !$acc parallel copyin(a1(0:4)) create(c1(0:4)) copyout(b1(0:4))
+  c1(0) = a1(0)
+  c1(1) = a1(1)
+  c1(2) = a1(2)
+  c1(3) = a1(3)
+  c1(4) = a1(4)
+
+  b1(0) = c1(0)
+  b1(1) = c1(1)
+  b1(2) = c1(2)
+  b1(3) = c1(3)
+  b1(4) = c1(4)
+  !$acc end parallel
+
+  if (b1(0) .ne. 10) call abort
+  if (b1(1) .ne. 10) call abort
+  if (b1(2) .ne. 10) call abort
+  if (b1(3) .ne. 10) call abort
+  if (b1(4) .ne. 10) call abort
+
+  deallocate(a1)
+  deallocate(b1)
+  deallocate(c1)
+
+  allocate (a1(5))
+  if (.not.allocated (a1)) call abort()
+
+  a1 = 10
+
+  !$acc parallel copy(a1(2:3))
+  a1(2) = 2
+  a1(3) = 3
+  !$acc end parallel
+
+  if (a1(1) .ne. 10) call abort
+  if (a1(2) .ne. 2) call abort
+  if (a1(3) .ne. 3) call abort
+  if (a1(4) .ne. 10) call abort
+  if (a1(5) .ne. 10) call abort
+
+  deallocate(a1)
+
+end program test
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/reduction-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/reduction-1.f90
new file mode 100644
index 0000000..89e7fe7
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/reduction-1.f90
@@ -0,0 +1,225 @@
+! { dg-do run }
+
+! Integer reductions
+
+program reduction_1
+  implicit none
+
+  integer, parameter    :: n = 10, vl = 2
+  integer               :: i, vresult, result
+  logical               :: lresult, lvresult
+  integer, dimension (n) :: array
+
+  do i = 1, n
+     array(i) = i
+  end do
+
+  result = 0
+  vresult = 0
+
+  ! '+' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(+:result)
+  do i = 1, n
+     result = result + array(i)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = vresult + array(i)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 0
+  vresult = 0
+
+  ! '*' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(*:result)
+  do i = 1, n
+     result = result * array(i)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = vresult * array(i)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 0
+  vresult = 0
+
+  ! 'max' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(max:result)
+  do i = 1, n
+     result = max (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = max (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 1
+  vresult = 1
+
+  ! 'min' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(min:result)
+  do i = 1, n
+     result = min (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = min (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 1
+  vresult = 1
+
+  ! 'iand' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(iand:result)
+  do i = 1, n
+     result = iand (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = iand (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 1
+  vresult = 1
+
+  ! 'ior' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(ior:result)
+  do i = 1, n
+     result = ior (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = ior (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 0
+  vresult = 0
+
+  ! 'ieor' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(ieor:result)
+  do i = 1, n
+     result = ieor (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = ieor (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.and.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.and.:lresult)
+  do i = 1, n
+     lresult = lresult .and. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .and. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.or.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.or.:lresult)
+  do i = 1, n
+     lresult = lresult .or. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .or. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.eqv.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.eqv.:lresult)
+  do i = 1, n
+     lresult = lresult .eqv. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .eqv. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.neqv.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.neqv.:lresult)
+  do i = 1, n
+     lresult = lresult .neqv. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .neqv. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+end program reduction_1
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/reduction-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/reduction-2.f90
new file mode 100644
index 0000000..d3659c9
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/reduction-2.f90
@@ -0,0 +1,170 @@
+! { dg-do run }
+
+! real reductions
+
+program reduction_2
+  implicit none
+
+  integer, parameter    :: n = 10, vl = 2
+  integer               :: i
+  real, parameter       :: e = .001
+  real                  :: vresult, result
+  logical               :: lresult, lvresult
+  real, dimension (n) :: array
+
+  do i = 1, n
+     array(i) = i
+  end do
+
+  result = 0
+  vresult = 0
+
+  ! '+' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(+:result)
+  do i = 1, n
+     result = result + array(i)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = vresult + array(i)
+  end do
+
+  if (abs (result - vresult) .ge. e) call abort
+
+  result = 1
+  vresult = 1
+
+  ! '*' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(*:result)
+  do i = 1, n
+     result = result * array(i)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = vresult * array(i)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 0
+  vresult = 0
+
+  ! 'max' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(max:result)
+  do i = 1, n
+     result = max (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = max (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 1
+  vresult = 1
+
+  ! 'min' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(min:result)
+  do i = 1, n
+     result = min (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = min (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 1
+  vresult = 1
+
+  ! '.and.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.and.:lresult)
+  do i = 1, n
+     lresult = lresult .and. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .and. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.or.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.or.:lresult)
+  do i = 1, n
+     lresult = lresult .or. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .or. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.eqv.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.eqv.:lresult)
+  do i = 1, n
+     lresult = lresult .eqv. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .eqv. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.neqv.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.neqv.:lresult)
+  do i = 1, n
+     lresult = lresult .neqv. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .neqv. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+end program reduction_2
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/reduction-3.f90 b/libgomp/testsuite/libgomp.oacc-fortran/reduction-3.f90
new file mode 100644
index 0000000..2b8005d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/reduction-3.f90
@@ -0,0 +1,170 @@
+! { dg-do run }
+
+! double precision reductions
+
+program reduction_3
+  implicit none
+
+  integer, parameter    :: n = 10, vl = 2
+  integer               :: i
+  double precision, parameter :: e = .001
+  double precision      :: vresult, result
+  logical               :: lresult, lvresult
+  double precision, dimension (n) :: array
+
+  do i = 1, n
+     array(i) = i
+  end do
+
+  result = 0
+  vresult = 0
+
+  ! '+' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(+:result)
+  do i = 1, n
+     result = result + array(i)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = vresult + array(i)
+  end do
+
+  if (abs (result - vresult) .ge. e) call abort
+
+  result = 1
+  vresult = 1
+
+  ! '*' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(*:result)
+  do i = 1, n
+     result = result * array(i)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = vresult * array(i)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 0
+  vresult = 0
+
+  ! 'max' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(max:result)
+  do i = 1, n
+     result = max (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = max (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 1
+  vresult = 1
+
+  ! 'min' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(min:result)
+  do i = 1, n
+     result = min (result, array(i))
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = min (vresult, array(i))
+  end do
+
+  if (result.ne.vresult) call abort
+
+  result = 1
+  vresult = 1
+
+  ! '.and.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.and.:lresult)
+  do i = 1, n
+     lresult = lresult .and. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .and. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.or.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.or.:lresult)
+  do i = 1, n
+     lresult = lresult .or. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .or. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.eqv.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.eqv.:lresult)
+  do i = 1, n
+     lresult = lresult .eqv. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .eqv. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+
+  lresult = .false.
+  lvresult = .false.
+
+  ! '.neqv.' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(.neqv.:lresult)
+  do i = 1, n
+     lresult = lresult .neqv. (array(i) .ge. 5)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     lvresult = lvresult .neqv. (array(i) .ge. 5)
+  end do
+
+  if (result.ne.vresult) call abort
+end program reduction_3
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/reduction-4.f90 b/libgomp/testsuite/libgomp.oacc-fortran/reduction-4.f90
new file mode 100644
index 0000000..12f7a33
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/reduction-4.f90
@@ -0,0 +1,54 @@
+! { dg-do run }
+
+! complex reductions
+
+program reduction_4
+  implicit none
+
+  integer, parameter    :: n = 10, vl = 32
+  integer               :: i
+  complex               :: vresult, result
+  complex, dimension (n) :: array
+
+  do i = 1, n
+     array(i) = i
+  end do
+
+  result = 0
+  vresult = 0
+
+  ! '+' reductions
+
+  !$acc parallel vector_length(vl) num_gangs(1)
+  !$acc loop reduction(+:result)
+  do i = 1, n
+     result = result + array(i)
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vresult = vresult + array(i)
+  end do
+
+  if (result .ne. vresult) call abort
+
+  result = 1
+  vresult = 1
+
+!  ! '*' reductions
+!
+!  !$acc parallel vector_length(vl)
+!  !$acc loop reduction(*:result)
+!  do i = 1, n
+!     result = result * array(i)
+!  end do
+!  !$acc end parallel
+!
+!  ! Verify the results
+!  do i = 1, n
+!     vresult = vresult * array(i)
+!  end do
+!
+!  if (result.ne.vresult) call abort
+end program reduction_4
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/reduction-5.f90 b/libgomp/testsuite/libgomp.oacc-fortran/reduction-5.f90
new file mode 100644
index 0000000..df44a7a
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/reduction-5.f90
@@ -0,0 +1,32 @@
+! { dg-do run }
+
+! subroutine reduction
+
+program reduction
+  integer, parameter    :: n = 40, c = 10
+  integer               :: i, vsum, sum
+
+  call redsub (sum, n, c)
+
+  vsum = 0
+
+  ! Verify the results
+  do i = 1, n
+     vsum = vsum + c
+  end do
+
+  if (sum.ne.vsum) call abort ()
+end program reduction
+
+subroutine redsub(sum, n, c)
+  integer :: sum, n, c
+
+  sum = 0
+
+  !$acc parallel vector_length(n) copyin (n, c) num_gangs(1)
+  !$acc loop reduction(+:sum)
+  do i = 1, n
+     sum = sum + c
+  end do
+  !$acc end parallel
+end subroutine redsub
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/reduction-6.f90 b/libgomp/testsuite/libgomp.oacc-fortran/reduction-6.f90
new file mode 100644
index 0000000..6325431
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/reduction-6.f90
@@ -0,0 +1,30 @@
+! { dg-do run }
+
+program reduction
+  implicit none
+
+  integer, parameter    :: n = 100
+  integer               :: i, s1, s2, vs1, vs2
+
+  s1 = 0
+  s2 = 0
+  vs1 = 0
+  vs2 = 0
+
+  !$acc parallel vector_length (1000)
+  !$acc loop reduction(+:s1, s2)
+  do i = 1, n
+     s1 = s1 + 1
+     s2 = s2 + 2
+  end do
+  !$acc end parallel
+
+  ! Verify the results
+  do i = 1, n
+     vs1 = vs1 + 1
+     vs2 = vs2 + 2
+  end do
+
+  if (s1.ne.vs1) call abort ()
+  if (s2.ne.vs2) call abort ()
+end program reduction
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/routine-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/routine-1.f90
new file mode 100644
index 0000000..3390515
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/routine-1.f90
@@ -0,0 +1,32 @@
+! { dg-do run }
+! { dg-options "-fno-inline" }
+
+  interface
+    recursive function fact (x)
+      !$acc routine
+      integer, intent(in) :: x
+      integer :: fact
+    end function fact
+  end interface
+  integer, parameter :: n = 10
+  integer :: a(n), i
+  !$acc parallel
+  !$acc loop
+  do i = 1, n
+     a(i) = fact (i)
+  end do
+  !$acc end parallel
+  do i = 1, n
+     if (a(i) .ne. fact(i)) call abort
+  end do
+end
+recursive function fact (x) result (res)
+  !$acc routine
+  integer, intent(in) :: x
+  integer :: res
+  if (x < 1) then
+     res = 1
+  else
+     res = x * fact (x - 1)
+  end if
+end function fact
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/routine-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/routine-2.f90
new file mode 100644
index 0000000..3d418b6
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/routine-2.f90
@@ -0,0 +1,29 @@
+! { dg-do run }
+! { dg-options "-fno-inline" }
+
+  module m1
+    contains
+    recursive function fact (x) result (res)
+      !$acc routine
+      integer, intent(in) :: x
+      integer :: res
+      if (x < 1) then
+         res = 1
+      else
+         res = x * fact (x - 1)
+      end if
+    end function fact
+  end module m1
+  use m1
+  integer, parameter :: n = 10
+  integer :: a(n), i
+  !$acc parallel
+  !$acc loop
+  do i = 1, n
+     a(i) = fact (i)
+  end do
+  !$acc end parallel
+  do i = 1, n
+     if (a(i) .ne. fact(i)) call abort
+  end do
+end
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/routine-3.f90 b/libgomp/testsuite/libgomp.oacc-fortran/routine-3.f90
new file mode 100644
index 0000000..d233a63
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/routine-3.f90
@@ -0,0 +1,27 @@
+! { dg-do run }
+! { dg-options "-fno-inline" }
+
+  integer, parameter :: n = 10
+  integer :: a(n), i
+  integer, external :: fact
+  !$acc routine (fact)
+  !$acc parallel
+  !$acc loop
+  do i = 1, n
+     a(i) = fact (i)
+  end do
+  !$acc end parallel
+  do i = 1, n
+     if (a(i) .ne. fact(i)) call abort
+  end do
+end
+recursive function fact (x) result (res)
+  !$acc routine
+  integer, intent(in) :: x
+  integer :: res
+  if (x < 1) then
+     res = 1
+  else
+     res = x * fact (x - 1)
+  end if
+end function fact
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/routine-4.f90 b/libgomp/testsuite/libgomp.oacc-fortran/routine-4.f90
new file mode 100644
index 0000000..3e5fb09
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/routine-4.f90
@@ -0,0 +1,23 @@
+! { dg-do run }
+! { dg-options "-fno-inline" }
+
+  integer, parameter :: n = 10
+  integer :: a(n), i
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc parallel
+  !$acc loop
+  do i = 1, n
+     call incr(a(i))
+  end do
+  !$acc end parallel
+  do i = 1, n
+     if (a(i) .ne. (i + 1)) call abort
+  end do
+end
+subroutine incr (x)
+  !$acc routine
+  integer, intent(inout) :: x
+  x = x + 1
+end subroutine incr
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/subarrays-1.f90 b/libgomp/testsuite/libgomp.oacc-fortran/subarrays-1.f90
new file mode 100644
index 0000000..b39414f
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/subarrays-1.f90
@@ -0,0 +1,97 @@
+program subarrays
+  integer, parameter     :: n = 20, c = 10
+  integer                :: i, a(n), b(n)
+
+  a(:) = 0
+  b(:) = 0
+
+  ! COPY
+
+  !$acc parallel copy (a(1:n))
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  do i = 1, n
+     b(i) = i
+  end do
+
+  call check (a, b, n)
+
+  ! COPYOUT
+
+  a(:) = 0
+
+  !$acc parallel copyout (a(1:n))
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  do i = 1, n
+     if (a(i) .ne. b(i)) call abort
+  end do
+  call check (a, b, n)
+
+  ! COPYIN
+
+  a(:) = 0
+
+  !$acc parallel copyout (a(1:n)) copyin (b(1:n))
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPY
+
+  !$acc parallel pcopy (a(1:n))
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPYOUT
+
+  a(:) = 0
+
+  !$acc parallel pcopyout (a(1:n))
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPYIN
+
+  a(:) = 0
+
+  !$acc parallel pcopyout (a(1:n)) pcopyin (b(1:n))
+  !$acc loop
+  do i = 1, n
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+end program subarrays
+
+subroutine check (a, b, n)
+  integer :: n, a(n), b(n)
+  integer :: i
+
+  do i = 1, n
+     if (a(i) .ne. b(i)) call abort
+  end do
+end subroutine check
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/subarrays-2.f90 b/libgomp/testsuite/libgomp.oacc-fortran/subarrays-2.f90
new file mode 100644
index 0000000..81799f6
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/subarrays-2.f90
@@ -0,0 +1,100 @@
+program subarrays
+  integer, parameter     :: n = 20, c = 10, low = 5, high = 10
+  integer                :: i, a(n), b(n)
+
+  a(:) = 0
+  b(:) = 0
+
+  ! COPY
+
+  !$acc parallel copy (a(low:high))
+  !$acc loop
+  do i = low, high
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  do i = low, high
+     b(i) = i
+  end do
+
+  call check (a, b, n)
+
+  ! COPYOUT
+
+  a(:) = 0
+
+  !$acc parallel copyout (a(low:high))
+  !$acc loop
+  do i = low, high
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  do i = low, high
+     if (a(i) .ne. b(i)) call abort
+  end do
+  call check (a, b, n)
+
+  ! COPYIN
+
+  a(:) = 0
+
+  !$acc parallel copyout (a(low:high)) copyin (b(low:high))
+  !$acc loop
+  do i = low, high
+     a(i) = b(i)
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPY
+
+  a(:) = 0
+  
+  !$acc parallel pcopy (a(low:high))
+  !$acc loop
+  do i = low, high
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPYOUT
+
+  a(:) = 0
+
+  !$acc parallel pcopyout (a(low:high))
+  !$acc loop
+  do i = low, high
+     a(i) = i
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+
+  ! PRESENT_OR_COPYIN
+
+  a(:) = 0
+
+  !$acc parallel pcopyout (a(low:high)) &
+  !$acc & pcopyin (b(low:high))
+  !$acc loop
+  do i = low, high
+     a(i) = b(i)
+  end do
+  !$acc end parallel
+
+  call check (a, b, n)
+end program subarrays
+
+subroutine check (a, b, n)
+  integer :: n, a(n), b(n)
+  integer :: i
+
+  do i = 1, n
+     if (a(i) .ne. b(i)) call abort
+  end do
+end subroutine check