OpenE2K/gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
556b816b82
gcc/libgomp/omp.h.in
Jakub Jelinek 1158fe4340 openmp: Conforming device numbers and omp_{initial,invalid}_device 
OpenMP 5.2 changed once more what device numbers are allowed.
In 5.1, valid device numbers were [0, omp_get_num_devices()].
5.2 makes also -1 valid (calls it omp_initial_device), which is equivalent
in behavior to omp_get_num_devices() number but has the advantage that it
is a constant.  And it also introduces omp_invalid_device which is
also a constant with implementation defined value < -1.  That value should
act like sNaN, any time any device construct (GOMP_target*) or OpenMP runtime
API routine is asked for such a device, the program is terminated.
And if OMP_TARGET_OFFLOAD=mandatory, all non-conforming device numbers (which
is all but [-1, omp_get_num_devices()] other than omp_invalid_device)
must be treated like omp_invalid_device.

For device constructs, we have a compatibility problem, we've historically
used 2 magic negative values to mean something special.
GOMP_DEVICE_ICV (-1) means device clause wasn't present, pick the
		     omp_get_default_device () number
GOMP_DEVICE_FALLBACK (-2) means the host device (this is used e.g. for
			  #pragma omp target if (cond)
			  where if cond is false, we pass -2
But 5.2 requires that omp_initial_device is -1 (there were discussions
about it, advantage of -1 is that one can say iterate over the
[-1, omp_get_num_devices()-1] range to get all devices starting with
the host/initial one.
And also, if user passes -2, unless it is omp_invalid_device, we need to
treat it like non-conforming with OMP_TARGET_OFFLOAD=mandatory.

So, the patch does on the compiler side some number remapping,
user_device_num >= -2U ? user_device_num - 1 : user_device_num.
This remapping is done at compile time if device clause has constant
argument, otherwise at runtime, and means that for user -1 (omp_initial_device)
we pass -2 to GOMP_* in the runtime library where it treats it like host
fallback, while -2 is remapped to -3 (one of the non-conforming device numbers,
for those it doesn't matter which one is which).
omp_invalid_device is then -4.
For the OpenMP device runtime APIs, no remapping is done.

This patch doesn't deal with the initial default-device-var for
OMP_TARGET_OFFLOAD=mandatory , the spec says that the inital ICV value
for that should in that case depend on whether there are any offloading
devices or not (if not, should be omp_invalid_device), but that means
we can't determine the number of devices lazily (and let libraries have the
possibility to register their offloading data etc.).

2022-06-13  Jakub Jelinek  <jakub@redhat.com>

gcc/
	* omp-expand.cc (expand_omp_target): Remap user provided
	device clause arguments, -1 to -2 and -2 to -3, either
	at compile time if constant, or at runtime.
include/
	* gomp-constants.h (GOMP_DEVICE_INVALID): Define.
libgomp/
	* omp.h.in (omp_initial_device, omp_invalid_device): New enumerators.
	* omp_lib.f90.in (omp_initial_device, omp_invalid_device): New
	parameters.
	* omp_lib.h.in (omp_initial_device, omp_invalid_device): Likewise.
	* target.c (resolve_device): Add remapped argument, handle
	GOMP_DEVICE_ICV only if remapped is true (and clear remapped),
	for negative values, treat GOMP_DEVICE_FALLBACK as fallback only
	if remapped, otherwise treat omp_initial_device that way.  For
	omp_invalid_device, always emit gomp_fatal, even when
	OMP_TARGET_OFFLOAD isn't mandatory.
	(GOMP_target, GOMP_target_ext, GOMP_target_data, GOMP_target_data_ext,
	GOMP_target_update, GOMP_target_update_ext,
	GOMP_target_enter_exit_data): Pass true as remapped argument to
	resolve_device.
	(omp_target_alloc, omp_target_free, omp_target_is_present,
	omp_target_memcpy_check, omp_target_associate_ptr,
	omp_target_disassociate_ptr, omp_get_mapped_ptr,
	omp_target_is_accessible): Pass false as remapped argument to
	resolve_device.  Treat omp_initial_device the same as
	gomp_get_num_devices ().  Don't bypass resolve_device calls if
	device_num is negative.
	(omp_pause_resource): Treat omp_initial_device the same as
	gomp_get_num_devices ().  Call resolve_device.
	* icv-device.c (omp_set_default_device): Always set to device_num
	even when it is negative.
	* libgomp.texi: Document that Conforming device numbers,
	omp_initial_device and omp_invalid_device is implemented.
	* testsuite/libgomp.c/target-41.c (main): Add test with
	omp_initial_device.
	* testsuite/libgomp.c/target-45.c: New test.
	* testsuite/libgomp.c/target-46.c: New test.
	* testsuite/libgomp.c/target-47.c: New test.
	* testsuite/libgomp.c-c++-common/target-is-accessible-1.c (main): Add
	test with omp_initial_device.  Use -5 instead of -1 for negative value
	test.
	* testsuite/libgomp.fortran/target-is-accessible-1.f90 (main):
	Likewise.  Reorder stop numbers.
2022-06-13 14:02:37 +02:00

357 lines
12 KiB
C
Raw Blame History

/* Copyright (C) 2005-2022 Free Software Foundation, Inc.
Contributed by Richard Henderson <rth@redhat.com>.
This file is part of the GNU Offloading and Multi Processing Library
(libgomp).
Libgomp is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3, or (at your option)
any later version.
Libgomp is distributed in the hope that it will be useful, but WITHOUT ANY
WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for
more details.
Under Section 7 of GPL version 3, you are granted additional
permissions described in the GCC Runtime Library Exception, version
3.1, as published by the Free Software Foundation.
You should have received a copy of the GNU General Public License and
a copy of the GCC Runtime Library Exception along with this program;
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
<http://www.gnu.org/licenses/>. */
#ifndef _OMP_H
#define _OMP_H 1
#if defined(__GNUC__) && _OPENMP >= 201811
# define __GOMP_DEPRECATED_5_0 __attribute__((__deprecated__))
#else
# define __GOMP_DEPRECATED_5_0
#endif
#if defined(__GNUC__) && _OPENMP >= 202011
# define __GOMP_DEPRECATED_5_1 __attribute__((__deprecated__))
#else
# define __GOMP_DEPRECATED_5_1
#endif
#ifndef _LIBGOMP_OMP_LOCK_DEFINED
#define _LIBGOMP_OMP_LOCK_DEFINED 1
/* These two structures get edited by the libgomp build process to
reflect the shape of the two types. Their internals are private
to the library. */
typedef struct
{
unsigned char _x[@OMP_LOCK_SIZE@]
__attribute__((__aligned__(@OMP_LOCK_ALIGN@)));
} omp_lock_t;
typedef struct
{
unsigned char _x[@OMP_NEST_LOCK_SIZE@]
__attribute__((__aligned__(@OMP_NEST_LOCK_ALIGN@)));
} omp_nest_lock_t;
#endif
typedef enum omp_sched_t
{
omp_sched_static = 1,
omp_sched_dynamic = 2,
omp_sched_guided = 3,
omp_sched_auto = 4,
omp_sched_monotonic = 0x80000000U
} omp_sched_t;
typedef enum omp_proc_bind_t
{
omp_proc_bind_false = 0,
omp_proc_bind_true = 1,
omp_proc_bind_primary = 2,
omp_proc_bind_master __GOMP_DEPRECATED_5_1
= omp_proc_bind_primary,
omp_proc_bind_close = 3,
omp_proc_bind_spread = 4
} omp_proc_bind_t;
typedef enum omp_sync_hint_t
{
omp_sync_hint_none = 0,
omp_lock_hint_none __GOMP_DEPRECATED_5_0 = omp_sync_hint_none,
omp_sync_hint_uncontended = 1,
omp_lock_hint_uncontended __GOMP_DEPRECATED_5_0 = omp_sync_hint_uncontended,
omp_sync_hint_contended = 2,
omp_lock_hint_contended __GOMP_DEPRECATED_5_0 = omp_sync_hint_contended,
omp_sync_hint_nonspeculative = 4,
omp_lock_hint_nonspeculative __GOMP_DEPRECATED_5_0
= omp_sync_hint_nonspeculative,
omp_sync_hint_speculative = 8,
omp_lock_hint_speculative __GOMP_DEPRECATED_5_0 = omp_sync_hint_speculative
} omp_sync_hint_t;
typedef __GOMP_DEPRECATED_5_0 omp_sync_hint_t omp_lock_hint_t;
typedef struct __attribute__((__aligned__ (sizeof (void *)))) omp_depend_t
{
char __omp_depend_t__[2 * sizeof (void *)];
} omp_depend_t;
typedef enum omp_pause_resource_t
{
omp_pause_soft = 1,
omp_pause_hard = 2
} omp_pause_resource_t;
typedef __UINTPTR_TYPE__ omp_uintptr_t;
#if __cplusplus >= 201103L
# define __GOMP_UINTPTR_T_ENUM : omp_uintptr_t
#else
# define __GOMP_UINTPTR_T_ENUM
#endif
typedef enum omp_memspace_handle_t __GOMP_UINTPTR_T_ENUM
{
omp_default_mem_space = 0,
omp_large_cap_mem_space = 1,
omp_const_mem_space = 2,
omp_high_bw_mem_space = 3,
omp_low_lat_mem_space = 4,
__omp_memspace_handle_t_max__ = __UINTPTR_MAX__
} omp_memspace_handle_t;
typedef enum omp_allocator_handle_t __GOMP_UINTPTR_T_ENUM
{
omp_null_allocator = 0,
omp_default_mem_alloc = 1,
omp_large_cap_mem_alloc = 2,
omp_const_mem_alloc = 3,
omp_high_bw_mem_alloc = 4,
omp_low_lat_mem_alloc = 5,
omp_cgroup_mem_alloc = 6,
omp_pteam_mem_alloc = 7,
omp_thread_mem_alloc = 8,
__omp_allocator_handle_t_max__ = __UINTPTR_MAX__
} omp_allocator_handle_t;
typedef enum omp_alloctrait_key_t
{
omp_atk_sync_hint = 1,
omp_atk_alignment = 2,
omp_atk_access = 3,
omp_atk_pool_size = 4,
omp_atk_fallback = 5,
omp_atk_fb_data = 6,
omp_atk_pinned = 7,
omp_atk_partition = 8
} omp_alloctrait_key_t;
typedef enum omp_alloctrait_value_t
{
omp_atv_default = (__UINTPTR_TYPE__) -1,
omp_atv_false = 0,
omp_atv_true = 1,
omp_atv_contended = 3,
omp_atv_uncontended = 4,
omp_atv_serialized = 5,
omp_atv_sequential __GOMP_DEPRECATED_5_1 = omp_atv_serialized,
omp_atv_private = 6,
omp_atv_all = 7,
omp_atv_thread = 8,
omp_atv_pteam = 9,
omp_atv_cgroup = 10,
omp_atv_default_mem_fb = 11,
omp_atv_null_fb = 12,
omp_atv_abort_fb = 13,
omp_atv_allocator_fb = 14,
omp_atv_environment = 15,
omp_atv_nearest = 16,
omp_atv_blocked = 17,
omp_atv_interleaved = 18
} omp_alloctrait_value_t;
typedef struct omp_alloctrait_t
{
omp_alloctrait_key_t key;
omp_uintptr_t value;
} omp_alloctrait_t;
typedef enum omp_event_handle_t __GOMP_UINTPTR_T_ENUM
{
__omp_event_handle_t_max__ = __UINTPTR_MAX__
} omp_event_handle_t;
enum
{
omp_initial_device = -1,
omp_invalid_device = -4
};
#ifdef __cplusplus
extern "C" {
# define __GOMP_NOTHROW throw ()
# define __GOMP_DEFAULT_NULL_ALLOCATOR = omp_null_allocator
#else
# define __GOMP_NOTHROW __attribute__((__nothrow__))
# define __GOMP_DEFAULT_NULL_ALLOCATOR
#endif
extern void omp_set_num_threads (int) __GOMP_NOTHROW;
extern int omp_get_num_threads (void) __GOMP_NOTHROW;
extern int omp_get_max_threads (void) __GOMP_NOTHROW;
extern int omp_get_thread_num (void) __GOMP_NOTHROW;
extern int omp_get_num_procs (void) __GOMP_NOTHROW;
extern int omp_in_parallel (void) __GOMP_NOTHROW;
extern void omp_set_dynamic (int) __GOMP_NOTHROW;
extern int omp_get_dynamic (void) __GOMP_NOTHROW;
extern void omp_set_nested (int) __GOMP_NOTHROW __GOMP_DEPRECATED_5_0;
extern int omp_get_nested (void) __GOMP_NOTHROW __GOMP_DEPRECATED_5_0;
extern void omp_init_lock (omp_lock_t *) __GOMP_NOTHROW;
extern void omp_init_lock_with_hint (omp_lock_t *, omp_sync_hint_t)
__GOMP_NOTHROW;
extern void omp_destroy_lock (omp_lock_t *) __GOMP_NOTHROW;
extern void omp_set_lock (omp_lock_t *) __GOMP_NOTHROW;
extern void omp_unset_lock (omp_lock_t *) __GOMP_NOTHROW;
extern int omp_test_lock (omp_lock_t *) __GOMP_NOTHROW;
extern void omp_init_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW;
extern void omp_init_nest_lock_with_hint (omp_nest_lock_t *, omp_sync_hint_t)
__GOMP_NOTHROW;
extern void omp_destroy_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW;
extern void omp_set_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW;
extern void omp_unset_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW;
extern int omp_test_nest_lock (omp_nest_lock_t *) __GOMP_NOTHROW;
extern double omp_get_wtime (void) __GOMP_NOTHROW;
extern double omp_get_wtick (void) __GOMP_NOTHROW;
extern void omp_set_schedule (omp_sched_t, int) __GOMP_NOTHROW;
extern void omp_get_schedule (omp_sched_t *, int *) __GOMP_NOTHROW;
extern int omp_get_thread_limit (void) __GOMP_NOTHROW;
extern void omp_set_max_active_levels (int) __GOMP_NOTHROW;
extern int omp_get_max_active_levels (void) __GOMP_NOTHROW;
extern int omp_get_supported_active_levels (void) __GOMP_NOTHROW;
extern int omp_get_level (void) __GOMP_NOTHROW;
extern int omp_get_ancestor_thread_num (int) __GOMP_NOTHROW;
extern int omp_get_team_size (int) __GOMP_NOTHROW;
extern int omp_get_active_level (void) __GOMP_NOTHROW;
extern int omp_in_final (void) __GOMP_NOTHROW;
extern int omp_get_cancellation (void) __GOMP_NOTHROW;
extern omp_proc_bind_t omp_get_proc_bind (void) __GOMP_NOTHROW;
extern int omp_get_num_places (void) __GOMP_NOTHROW;
extern int omp_get_place_num_procs (int) __GOMP_NOTHROW;
extern void omp_get_place_proc_ids (int, int *) __GOMP_NOTHROW;
extern int omp_get_place_num (void) __GOMP_NOTHROW;
extern int omp_get_partition_num_places (void) __GOMP_NOTHROW;
extern void omp_get_partition_place_nums (int *) __GOMP_NOTHROW;
extern void omp_set_default_device (int) __GOMP_NOTHROW;
extern int omp_get_default_device (void) __GOMP_NOTHROW;
extern int omp_get_num_devices (void) __GOMP_NOTHROW;
extern int omp_get_device_num (void) __GOMP_NOTHROW;
extern int omp_get_num_teams (void) __GOMP_NOTHROW;
extern int omp_get_team_num (void) __GOMP_NOTHROW;
extern int omp_is_initial_device (void) __GOMP_NOTHROW;
extern int omp_get_initial_device (void) __GOMP_NOTHROW;
extern int omp_get_max_task_priority (void) __GOMP_NOTHROW;
extern void omp_fulfill_event (omp_event_handle_t) __GOMP_NOTHROW;
extern void omp_set_num_teams (int) __GOMP_NOTHROW;
extern int omp_get_max_teams (void) __GOMP_NOTHROW;
extern void omp_set_teams_thread_limit (int) __GOMP_NOTHROW;
extern int omp_get_teams_thread_limit (void) __GOMP_NOTHROW;
extern void *omp_target_alloc (__SIZE_TYPE__, int) __GOMP_NOTHROW;
extern void omp_target_free (void *, int) __GOMP_NOTHROW;
extern int omp_target_is_present (const void *, int) __GOMP_NOTHROW;
extern int omp_target_memcpy (void *, const void *, __SIZE_TYPE__,
__SIZE_TYPE__, __SIZE_TYPE__, int, int)
__GOMP_NOTHROW;
extern int omp_target_memcpy_async (void *, const void *, __SIZE_TYPE__,
__SIZE_TYPE__, __SIZE_TYPE__, int, int,
int, omp_depend_t *)
__GOMP_NOTHROW;
extern int omp_target_memcpy_rect (void *, const void *, __SIZE_TYPE__, int,
const __SIZE_TYPE__ *,
const __SIZE_TYPE__ *,
const __SIZE_TYPE__ *,
const __SIZE_TYPE__ *,
const __SIZE_TYPE__ *, int, int)
__GOMP_NOTHROW;
extern int omp_target_memcpy_rect_async (void *, const void *, __SIZE_TYPE__,
int, const __SIZE_TYPE__ *,
const __SIZE_TYPE__ *,
const __SIZE_TYPE__ *,
const __SIZE_TYPE__ *,
const __SIZE_TYPE__ *, int, int, int,
omp_depend_t *)
__GOMP_NOTHROW;
extern int omp_target_associate_ptr (const void *, const void *, __SIZE_TYPE__,
__SIZE_TYPE__, int) __GOMP_NOTHROW;
extern int omp_target_disassociate_ptr (const void *, int) __GOMP_NOTHROW;
extern void *omp_get_mapped_ptr (const void *, int) __GOMP_NOTHROW;
extern int omp_target_is_accessible (const void *, __SIZE_TYPE__, int)
__GOMP_NOTHROW;
extern void omp_set_affinity_format (const char *) __GOMP_NOTHROW;
extern __SIZE_TYPE__ omp_get_affinity_format (char *, __SIZE_TYPE__)
__GOMP_NOTHROW;
extern void omp_display_affinity (const char *) __GOMP_NOTHROW;
extern __SIZE_TYPE__ omp_capture_affinity (char *, __SIZE_TYPE__, const char *)
__GOMP_NOTHROW;
extern int omp_pause_resource (omp_pause_resource_t, int) __GOMP_NOTHROW;
extern int omp_pause_resource_all (omp_pause_resource_t) __GOMP_NOTHROW;
extern omp_allocator_handle_t omp_init_allocator (omp_memspace_handle_t,
int,
const omp_alloctrait_t [])
__GOMP_NOTHROW;
extern void omp_destroy_allocator (omp_allocator_handle_t) __GOMP_NOTHROW;
extern void omp_set_default_allocator (omp_allocator_handle_t) __GOMP_NOTHROW;
extern omp_allocator_handle_t omp_get_default_allocator (void) __GOMP_NOTHROW;
extern void omp_free (void *,
omp_allocator_handle_t __GOMP_DEFAULT_NULL_ALLOCATOR)
__GOMP_NOTHROW;
extern void *omp_alloc (__SIZE_TYPE__,
omp_allocator_handle_t __GOMP_DEFAULT_NULL_ALLOCATOR)
__GOMP_NOTHROW __attribute__((__malloc__, __malloc__ (omp_free),
__alloc_size__ (1)));
extern void *omp_aligned_alloc (__SIZE_TYPE__, __SIZE_TYPE__,
omp_allocator_handle_t
__GOMP_DEFAULT_NULL_ALLOCATOR)
__GOMP_NOTHROW __attribute__((__malloc__, __malloc__ (omp_free),
__alloc_size__ (2), __alloc_align__ (1)));
extern void *omp_calloc (__SIZE_TYPE__, __SIZE_TYPE__,
omp_allocator_handle_t __GOMP_DEFAULT_NULL_ALLOCATOR)
__GOMP_NOTHROW __attribute__((__malloc__, __malloc__ (omp_free),
__alloc_size__ (1, 2)));
extern void *omp_aligned_calloc (__SIZE_TYPE__, __SIZE_TYPE__, __SIZE_TYPE__,
omp_allocator_handle_t
__GOMP_DEFAULT_NULL_ALLOCATOR)
__GOMP_NOTHROW __attribute__((__malloc__, __malloc__ (omp_free),
__alloc_size__ (2, 3), __alloc_align__ (1)));
extern void *omp_realloc (void *, __SIZE_TYPE__,
omp_allocator_handle_t __GOMP_DEFAULT_NULL_ALLOCATOR,
omp_allocator_handle_t __GOMP_DEFAULT_NULL_ALLOCATOR)
__GOMP_NOTHROW __attribute__((__malloc__ (omp_free), __alloc_size__ (2)));
extern void omp_display_env (int) __GOMP_NOTHROW;
#ifdef __cplusplus
}
#endif
#endif /* _OMP_H */
Reference in New Issue View Git Blame Copy Permalink