gcc/libgomp/oacc-host.c
Chung-Lin Tang 1f4c5b9bb2 2019-05-13 Chung-Lin Tang <cltang@codesourcery.com>
Reviewed-by: Thomas Schwinge <thomas@codesourcery.com>

	libgomp/
	* libgomp-plugin.h (struct goacc_asyncqueue): Declare.
	(struct goacc_asyncqueue_list): Likewise.
	(goacc_aq): Likewise.
	(goacc_aq_list): Likewise.
	(GOMP_OFFLOAD_openacc_register_async_cleanup): Remove.
	(GOMP_OFFLOAD_openacc_async_test): Remove.
	(GOMP_OFFLOAD_openacc_async_test_all): Remove.
	(GOMP_OFFLOAD_openacc_async_wait): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_async): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_all): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_all_async): Remove.
	(GOMP_OFFLOAD_openacc_async_set_async): Remove.
	(GOMP_OFFLOAD_openacc_exec): Adjust declaration.
	(GOMP_OFFLOAD_openacc_cuda_get_stream): Likewise.
	(GOMP_OFFLOAD_openacc_cuda_set_stream): Likewise.
	(GOMP_OFFLOAD_openacc_async_exec): Declare.
	(GOMP_OFFLOAD_openacc_async_construct): Declare.
	(GOMP_OFFLOAD_openacc_async_destruct): Declare.
	(GOMP_OFFLOAD_openacc_async_test): Declare.
	(GOMP_OFFLOAD_openacc_async_synchronize): Declare.
	(GOMP_OFFLOAD_openacc_async_serialize): Declare.
	(GOMP_OFFLOAD_openacc_async_queue_callback): Declare.
	(GOMP_OFFLOAD_openacc_async_host2dev): Declare.
	(GOMP_OFFLOAD_openacc_async_dev2host): Declare.

	* libgomp.h (struct acc_dispatch_t): Define 'async' sub-struct.
	(gomp_acc_insert_pointer): Adjust declaration.
	(gomp_copy_host2dev): New declaration.
	(gomp_copy_dev2host): Likewise.
	(gomp_map_vars_async): Likewise.
	(gomp_unmap_tgt): Likewise.
	(gomp_unmap_vars_async): Likewise.
	(gomp_fini_device): Likewise.

	* oacc-async.c (get_goacc_thread): New function.
	(get_goacc_thread_device): New function.
	(lookup_goacc_asyncqueue): New function.
	(get_goacc_asyncqueue): New function.
	(acc_async_test): Adjust code to use new async design.
	(acc_async_test_all): Likewise.
	(acc_wait): Likewise.
	(acc_wait_async): Likewise.
	(acc_wait_all): Likewise.
	(acc_wait_all_async): Likewise.
	(goacc_async_free): New function.
	(goacc_init_asyncqueues): Likewise.
	(goacc_fini_asyncqueues): Likewise.
	* oacc-cuda.c (acc_get_cuda_stream): Adjust code to use new async
	design.
	(acc_set_cuda_stream): Likewise.
	* oacc-host.c (host_openacc_exec): Adjust parameters, remove 'async'.
	(host_openacc_register_async_cleanup): Remove.
	(host_openacc_async_exec): New function.
	(host_openacc_async_test): Adjust parameters.
	(host_openacc_async_test_all): Remove.
	(host_openacc_async_wait): Remove.
	(host_openacc_async_wait_async): Remove.
	(host_openacc_async_wait_all): Remove.
	(host_openacc_async_wait_all_async): Remove.
	(host_openacc_async_set_async): Remove.
	(host_openacc_async_synchronize): New function.
	(host_openacc_async_serialize): New function.
	(host_openacc_async_host2dev): New function.
	(host_openacc_async_dev2host): New function.
	(host_openacc_async_queue_callback): New function.
	(host_openacc_async_construct): New function.
	(host_openacc_async_destruct): New function.
	(struct gomp_device_descr host_dispatch): Remove initialization of old
	interface, add intialization of new async sub-struct.
	* oacc-init.c (acc_shutdown_1): Adjust to use gomp_fini_device.
	(goacc_attach_host_thread_to_device): Remove old async code usage.
	* oacc-int.h (goacc_init_asyncqueues): New declaration.
	(goacc_fini_asyncqueues): Likewise.
	(goacc_async_copyout_unmap_vars): Likewise.
	(goacc_async_free): Likewise.
	(get_goacc_asyncqueue): Likewise.
	(lookup_goacc_asyncqueue): Likewise.

	* oacc-mem.c (memcpy_tofrom_device): Adjust code to use new async
	design.
	(present_create_copy): Adjust code to use new async design.
	(delete_copyout): Likewise.
	(update_dev_host): Likewise.
	(gomp_acc_insert_pointer): Add async parameter, adjust code to use new
	async design.
	(gomp_acc_remove_pointer): Adjust code to use new async design.
	* oacc-parallel.c (GOACC_parallel_keyed): Adjust code to use new async
	design.
	(GOACC_enter_exit_data): Likewise.
	(goacc_wait): Likewise.
	(GOACC_update): Likewise.
	* oacc-plugin.c (GOMP_PLUGIN_async_unmap_vars): Change to assert fail
	when called, warn as obsolete in comment.

	* target.c (goacc_device_copy_async): New function.
	(gomp_copy_host2dev): Remove 'static', add goacc_asyncqueue parameter,
	add goacc_device_copy_async case.
	(gomp_copy_dev2host): Likewise.
	(gomp_map_vars_existing): Add goacc_asyncqueue parameter, adjust code.
	(gomp_map_pointer): Likewise.
	(gomp_map_fields_existing): Likewise.
	(gomp_map_vars_internal): New always_inline function, renamed from
	gomp_map_vars.
	(gomp_map_vars): Implement by calling gomp_map_vars_internal.
	(gomp_map_vars_async): Implement by calling gomp_map_vars_internal,
	passing goacc_asyncqueue argument.
	(gomp_unmap_tgt): Remove static, add attribute_hidden.
	(gomp_unref_tgt): New function.
	(gomp_unmap_vars_internal): New always_inline function, renamed from
	gomp_unmap_vars.
	(gomp_unmap_vars): Implement by calling gomp_unmap_vars_internal.
	(gomp_unmap_vars_async): Implement by calling
	gomp_unmap_vars_internal, passing goacc_asyncqueue argument.
	(gomp_fini_device): New function.
	(gomp_exit_data): Adjust gomp_copy_dev2host call.
	(gomp_load_plugin_for_device): Remove old interface, adjust to load
	new async interface.
	(gomp_target_fini): Adjust code to call gomp_fini_device.

	* plugin/plugin-nvptx.c (struct cuda_map): Remove.
	(struct ptx_stream): Remove.
	(struct nvptx_thread): Remove current_stream field.
	(cuda_map_create): Remove.
	(cuda_map_destroy): Remove.
	(map_init): Remove.
	(map_fini): Remove.
	(map_pop): Remove.
	(map_push): Remove.
	(struct goacc_asyncqueue): Define.
	(struct nvptx_callback): Define.
	(struct ptx_free_block): Define.
	(struct ptx_device): Remove null_stream, active_streams, async_streams,
	stream_lock, and next fields.
	(enum ptx_event_type): Remove.
	(struct ptx_event): Remove.
	(ptx_event_lock): Remove.
	(ptx_events): Remove.
	(init_streams_for_device): Remove.
	(fini_streams_for_device): Remove.
	(select_stream_for_async): Remove.
	(nvptx_init): Remove ptx_events and ptx_event_lock references.
	(nvptx_attach_host_thread_to_device): Remove CUDA_ERROR_NOT_PERMITTED
	case.
	(nvptx_open_device): Add free_blocks initialization, remove
	init_streams_for_device call.
	(nvptx_close_device): Remove fini_streams_for_device call, add
	free_blocks destruct code.
	(event_gc): Remove.
	(event_add): Remove.
	(nvptx_exec): Adjust parameters and code.
	(nvptx_free): Likewise.
	(nvptx_host2dev): Remove.
	(nvptx_dev2host): Remove.
	(nvptx_set_async): Remove.
	(nvptx_async_test): Remove.
	(nvptx_async_test_all): Remove.
	(nvptx_wait): Remove.
	(nvptx_wait_async): Remove.
	(nvptx_wait_all): Remove.
	(nvptx_wait_all_async): Remove.
	(nvptx_get_cuda_stream): Remove.
	(nvptx_set_cuda_stream): Remove.
	(GOMP_OFFLOAD_alloc): Adjust code.
	(GOMP_OFFLOAD_free): Likewise.
	(GOMP_OFFLOAD_openacc_register_async_cleanup): Remove.
	(GOMP_OFFLOAD_openacc_exec): Adjust parameters and code.
	(GOMP_OFFLOAD_openacc_async_test_all): Remove.
	(GOMP_OFFLOAD_openacc_async_wait): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_async): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_all): Remove.
	(GOMP_OFFLOAD_openacc_async_wait_all_async): Remove.
	(GOMP_OFFLOAD_openacc_async_set_async): Remove.
	(cuda_free_argmem): New function.
	(GOMP_OFFLOAD_openacc_async_exec): New plugin hook function.
	(GOMP_OFFLOAD_openacc_create_thread_data): Adjust code.
	(GOMP_OFFLOAD_openacc_cuda_get_stream): Adjust code.
	(GOMP_OFFLOAD_openacc_cuda_set_stream): Adjust code.
	(GOMP_OFFLOAD_openacc_async_construct): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_destruct): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_test): Remove and re-implement.
	(GOMP_OFFLOAD_openacc_async_synchronize): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_serialize): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_queue_callback): New plugin hook function.
	(cuda_callback_wrapper): New function.
	(cuda_memcpy_sanity_check): New function.
	(GOMP_OFFLOAD_host2dev): Remove and re-implement.
	(GOMP_OFFLOAD_dev2host): Remove and re-implement.
	(GOMP_OFFLOAD_openacc_async_host2dev): New plugin hook function.
	(GOMP_OFFLOAD_openacc_async_dev2host): New plugin hook function.

From-SVN: r271128
2019-05-13 13:32:00 +00:00

303 lines
7.1 KiB
C

/* OpenACC Runtime Library: acc_device_host.
Copyright (C) 2013-2019 Free Software Foundation, Inc.
Contributed by Mentor Embedded.
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/>. */
#include "libgomp.h"
#include "oacc-int.h"
#include "gomp-constants.h"
#include <stdbool.h>
#include <stddef.h>
#include <stdint.h>
static struct gomp_device_descr host_dispatch;
static const char *
host_get_name (void)
{
return host_dispatch.name;
}
static unsigned int
host_get_caps (void)
{
return host_dispatch.capabilities;
}
static int
host_get_type (void)
{
return host_dispatch.type;
}
static int
host_get_num_devices (void)
{
return 1;
}
static bool
host_init_device (int n __attribute__ ((unused)))
{
return true;
}
static bool
host_fini_device (int n __attribute__ ((unused)))
{
return true;
}
static unsigned
host_version (void)
{
return GOMP_VERSION;
}
static int
host_load_image (int n __attribute__ ((unused)),
unsigned v __attribute__ ((unused)),
const void *t __attribute__ ((unused)),
struct addr_pair **r __attribute__ ((unused)))
{
return 0;
}
static bool
host_unload_image (int n __attribute__ ((unused)),
unsigned v __attribute__ ((unused)),
const void *t __attribute__ ((unused)))
{
return true;
}
static void *
host_alloc (int n __attribute__ ((unused)), size_t s)
{
return gomp_malloc (s);
}
static bool
host_free (int n __attribute__ ((unused)), void *p)
{
free (p);
return true;
}
static bool
host_dev2host (int n __attribute__ ((unused)),
void *h __attribute__ ((unused)),
const void *d __attribute__ ((unused)),
size_t s __attribute__ ((unused)))
{
return true;
}
static bool
host_host2dev (int n __attribute__ ((unused)),
void *d __attribute__ ((unused)),
const void *h __attribute__ ((unused)),
size_t s __attribute__ ((unused)))
{
return true;
}
static void
host_run (int n __attribute__ ((unused)), void *fn_ptr, void *vars,
void **args __attribute__((unused)))
{
void (*fn)(void *) = (void (*)(void *)) fn_ptr;
fn (vars);
}
static void
host_openacc_exec (void (*fn) (void *),
size_t mapnum __attribute__ ((unused)),
void **hostaddrs,
void **devaddrs __attribute__ ((unused)),
unsigned *dims __attribute__ ((unused)),
void *targ_mem_desc __attribute__ ((unused)))
{
fn (hostaddrs);
}
static void
host_openacc_async_exec (void (*fn) (void *),
size_t mapnum __attribute__ ((unused)),
void **hostaddrs,
void **devaddrs __attribute__ ((unused)),
unsigned *dims __attribute__ ((unused)),
void *targ_mem_desc __attribute__ ((unused)),
struct goacc_asyncqueue *aq __attribute__ ((unused)))
{
fn (hostaddrs);
}
static int
host_openacc_async_test (struct goacc_asyncqueue *aq __attribute__ ((unused)))
{
return 1;
}
static bool
host_openacc_async_synchronize (struct goacc_asyncqueue *aq
__attribute__ ((unused)))
{
return true;
}
static bool
host_openacc_async_serialize (struct goacc_asyncqueue *aq1
__attribute__ ((unused)),
struct goacc_asyncqueue *aq2
__attribute__ ((unused)))
{
return true;
}
static bool
host_openacc_async_host2dev (int ord __attribute__ ((unused)),
void *dst __attribute__ ((unused)),
const void *src __attribute__ ((unused)),
size_t n __attribute__ ((unused)),
struct goacc_asyncqueue *aq
__attribute__ ((unused)))
{
return true;
}
static bool
host_openacc_async_dev2host (int ord __attribute__ ((unused)),
void *dst __attribute__ ((unused)),
const void *src __attribute__ ((unused)),
size_t n __attribute__ ((unused)),
struct goacc_asyncqueue *aq
__attribute__ ((unused)))
{
return true;
}
static void
host_openacc_async_queue_callback (struct goacc_asyncqueue *aq
__attribute__ ((unused)),
void (*callback_fn)(void *)
__attribute__ ((unused)),
void *userptr __attribute__ ((unused)))
{
}
static struct goacc_asyncqueue *
host_openacc_async_construct (void)
{
/* Non-NULL 0xffff... value as opaque dummy. */
return (struct goacc_asyncqueue *) -1;
}
static bool
host_openacc_async_destruct (struct goacc_asyncqueue *aq
__attribute__ ((unused)))
{
return true;
}
static void *
host_openacc_create_thread_data (int ord __attribute__ ((unused)))
{
return NULL;
}
static void
host_openacc_destroy_thread_data (void *tls_data __attribute__ ((unused)))
{
}
static struct gomp_device_descr host_dispatch =
{
.name = "host",
.capabilities = (GOMP_OFFLOAD_CAP_SHARED_MEM
| GOMP_OFFLOAD_CAP_NATIVE_EXEC
| GOMP_OFFLOAD_CAP_OPENACC_200),
.target_id = 0,
.type = OFFLOAD_TARGET_TYPE_HOST,
.get_name_func = host_get_name,
.get_caps_func = host_get_caps,
.get_type_func = host_get_type,
.get_num_devices_func = host_get_num_devices,
.init_device_func = host_init_device,
.fini_device_func = host_fini_device,
.version_func = host_version,
.load_image_func = host_load_image,
.unload_image_func = host_unload_image,
.alloc_func = host_alloc,
.free_func = host_free,
.dev2host_func = host_dev2host,
.host2dev_func = host_host2dev,
.run_func = host_run,
.mem_map = { NULL },
/* .lock initilized in goacc_host_init. */
.state = GOMP_DEVICE_UNINITIALIZED,
.openacc = {
.data_environ = NULL,
.exec_func = host_openacc_exec,
.create_thread_data_func = host_openacc_create_thread_data,
.destroy_thread_data_func = host_openacc_destroy_thread_data,
.async = {
.construct_func = host_openacc_async_construct,
.destruct_func = host_openacc_async_destruct,
.test_func = host_openacc_async_test,
.synchronize_func = host_openacc_async_synchronize,
.serialize_func = host_openacc_async_serialize,
.queue_callback_func = host_openacc_async_queue_callback,
.exec_func = host_openacc_async_exec,
.dev2host_func = host_openacc_async_dev2host,
.host2dev_func = host_openacc_async_host2dev,
},
.cuda = {
.get_current_device_func = NULL,
.get_current_context_func = NULL,
.get_stream_func = NULL,
.set_stream_func = NULL,
}
}
};
/* Initialize and register this device type. */
void
goacc_host_init (void)
{
gomp_mutex_init (&host_dispatch.lock);
goacc_register (&host_dispatch);
}