b2b4005150
2016-01-19 Martin Jambor <mjambor@suse.cz> Martin Liska <mliska@suse.cz> Michael Matz <matz@suse.de> libgomp/ * plugin/Makefrag.am: Add HSA plugin requirements. * plugin/configfrag.ac (HSA_RUNTIME_INCLUDE): New variable. (HSA_RUNTIME_LIB): Likewise. (HSA_RUNTIME_CPPFLAGS): Likewise. (HSA_RUNTIME_INCLUDE): New substitution. (HSA_RUNTIME_LIB): Likewise. (HSA_RUNTIME_LDFLAGS): Likewise. (hsa-runtime): New configure option. (hsa-runtime-include): Likewise. (hsa-runtime-lib): Likewise. (PLUGIN_HSA): New substitution variable. Fill HSA_RUNTIME_INCLUDE and HSA_RUNTIME_LIB according to the new configure options. (PLUGIN_HSA_CPPFLAGS): Likewise. (PLUGIN_HSA_LDFLAGS): Likewise. (PLUGIN_HSA_LIBS): Likewise. Check that we have access to HSA run-time. * libgomp-plugin.h (offload_target_type): New element OFFLOAD_TARGET_TYPE_HSA. * libgomp.h (gomp_target_task): New fields firstprivate_copies and args. (bool gomp_create_target_task): Updated. (gomp_device_descr): Extra parameter of run_func and async_run_func, new field can_run_func. * libgomp_g.h (GOMP_target_ext): Update prototype. * oacc-host.c (host_run): Added a new parameter args. * target.c (calculate_firstprivate_requirements): New function. (copy_firstprivate_data): Likewise. (gomp_target_fallback_firstprivate): Use them. (gomp_target_unshare_firstprivate): New function. (gomp_get_target_fn_addr): Allow returning NULL for shared memory devices. (GOMP_target): Do host fallback for all shared memory devices. Do not pass any args to plugins. (GOMP_target_ext): Introduce device-specific argument parameter args. Allow host fallback if device shares memory. Do not remap data if device has shared memory. (gomp_target_task_fn): Likewise. Also treat shared memory devices like host fallback for mappings. (GOMP_target_data): Treat shared memory devices like host fallback. (GOMP_target_data_ext): Likewise. (GOMP_target_update): Likewise. (GOMP_target_update_ext): Likewise. Also pass NULL as args to gomp_create_target_task. (GOMP_target_enter_exit_data): Likewise. (omp_target_alloc): Treat shared memory devices like host fallback. (omp_target_free): Likewise. (omp_target_is_present): Likewise. (omp_target_memcpy): Likewise. (omp_target_memcpy_rect): Likewise. (omp_target_associate_ptr): Likewise. (gomp_load_plugin_for_device): Also load can_run. * task.c (GOMP_PLUGIN_target_task_completion): Free firstprivate_copies. (gomp_create_target_task): Accept new argument args and store it to ttask. * plugin/plugin-hsa.c: New file. gcc/ * Makefile.in (OBJS): Add new source files. (GTFILES): Add hsa.c. * common.opt (disable_hsa): New variable. (-Whsa): New warning. * config.in (ENABLE_HSA): New. * configure.ac: Treat hsa differently from other accelerators. (OFFLOAD_TARGETS): Define ENABLE_OFFLOADING according to $enable_offloading. (ENABLE_HSA): Define ENABLE_HSA according to $enable_hsa. * doc/install.texi (Configuration): Document --with-hsa-runtime, --with-hsa-runtime-include, --with-hsa-runtime-lib and --with-hsa-kmt-lib. * doc/invoke.texi (-Whsa): Document. (hsa-gen-debug-stores): Likewise. * lto-wrapper.c (compile_images_for_offload_targets): Do not attempt to invoke offload compiler for hsa acclerator. * opts.c (common_handle_option): Determine whether HSA offloading should be performed. * params.def (PARAM_HSA_GEN_DEBUG_STORES): New parameter. * builtin-types.def (BT_FN_VOID_UINT_PTR_INT_PTR): New. (BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_INT_INT): Removed. (BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_PTR): New. * gimple-low.c (lower_stmt): Also handle GIMPLE_OMP_GRID_BODY. * gimple-pretty-print.c (dump_gimple_omp_for): Also handle GF_OMP_FOR_KIND_GRID_LOOP. (dump_gimple_omp_block): Also handle GIMPLE_OMP_GRID_BODY. (pp_gimple_stmt_1): Likewise. * gimple-walk.c (walk_gimple_stmt): Likewise. * gimple.c (gimple_build_omp_grid_body): New function. (gimple_copy): Also handle GIMPLE_OMP_GRID_BODY. * gimple.def (GIMPLE_OMP_GRID_BODY): New. * gimple.h (enum gf_mask): Added GF_OMP_PARALLEL_GRID_PHONY, GF_OMP_FOR_KIND_GRID_LOOP, GF_OMP_FOR_GRID_PHONY and GF_OMP_TEAMS_GRID_PHONY. (gimple_statement_omp_single_layout): Updated comments. (gimple_build_omp_grid_body): New function. (gimple_has_substatements): Also handle GIMPLE_OMP_GRID_BODY. (gimple_omp_for_grid_phony): New function. (gimple_omp_for_set_grid_phony): Likewise. (gimple_omp_parallel_grid_phony): Likewise. (gimple_omp_parallel_set_grid_phony): Likewise. (gimple_omp_teams_grid_phony): Likewise. (gimple_omp_teams_set_grid_phony): Likewise. (gimple_return_set_retbnd): Also handle GIMPLE_OMP_GRID_BODY. * omp-builtins.def (BUILT_IN_GOMP_OFFLOAD_REGISTER): New. (BUILT_IN_GOMP_OFFLOAD_UNREGISTER): Likewise. (BUILT_IN_GOMP_TARGET): Updated type. * omp-low.c: Include symbol-summary.h, hsa.h and params.h. (adjust_for_condition): New function. (get_omp_for_step_from_incr): Likewise. (extract_omp_for_data): Moved parts to adjust_for_condition and get_omp_for_step_from_incr. (build_outer_var_ref): Handle GIMPLE_OMP_GRID_BODY. (fixup_child_record_type): Bail out if receiver_decl is NULL. (scan_sharing_clauses): Handle OMP_CLAUSE__GRIDDIM_. (scan_omp_parallel): Do not create child functions for phony constructs. (check_omp_nesting_restrictions): Handle GIMPLE_OMP_GRID_BODY. (scan_omp_1_op): Checking assert we are not remapping to ERROR_MARK. Also also handle GIMPLE_OMP_GRID_BODY. (parallel_needs_hsa_kernel_p): New function. (expand_parallel_call): Register apprpriate parallel child functions as HSA kernels. (grid_launch_attributes_trees): New type. (grid_attr_trees): New variable. (grid_create_kernel_launch_attr_types): New function. (grid_insert_store_range_dim): Likewise. (grid_get_kernel_launch_attributes): Likewise. (get_target_argument_identifier_1): Likewise. (get_target_argument_identifier): Likewise. (get_target_argument_value): Likewise. (push_target_argument_according_to_value): Likewise. (get_target_arguments): Likewise. (expand_omp_target): Call get_target_arguments instead of looking up for teams and thread limit. (grid_expand_omp_for_loop): New function. (grid_arg_decl_map): New type. (grid_remap_kernel_arg_accesses): New function. (grid_expand_target_kernel_body): New function. (expand_omp): Call it. (lower_omp_for): Do not emit phony constructs. (lower_omp_taskreg): Do not emit phony constructs but create for them a temporary variable receiver_decl. (lower_omp_taskreg): Do not emit phony constructs. (lower_omp_teams): Likewise. (lower_omp_grid_body): New function. (lower_omp_1): Call it. (grid_reg_assignment_to_local_var_p): New function. (grid_seq_only_contains_local_assignments): Likewise. (grid_find_single_omp_among_assignments_1): Likewise. (grid_find_single_omp_among_assignments): Likewise. (grid_find_ungridifiable_statement): Likewise. (grid_target_follows_gridifiable_pattern): Likewise. (grid_remap_prebody_decls): Likewise. (grid_copy_leading_local_assignments): Likewise. (grid_process_kernel_body_copy): Likewise. (grid_attempt_target_gridification): Likewise. (grid_gridify_all_targets_stmt): Likewise. (grid_gridify_all_targets): Likewise. (execute_lower_omp): Call grid_gridify_all_targets. (make_gimple_omp_edges): Handle GIMPLE_OMP_GRID_BODY. * tree-core.h (omp_clause_code): Added OMP_CLAUSE__GRIDDIM_. (tree_omp_clause): Added union field dimension. * tree-pretty-print.c (dump_omp_clause): Handle OMP_CLAUSE__GRIDDIM_. * tree.c (omp_clause_num_ops): Added number of arguments of OMP_CLAUSE__GRIDDIM_. (omp_clause_code_name): Added name of OMP_CLAUSE__GRIDDIM_. (walk_tree_1): Handle OMP_CLAUSE__GRIDDIM_. * tree.h (OMP_CLAUSE_GRIDDIM_DIMENSION): New. (OMP_CLAUSE_SET_GRIDDIM_DIMENSION): Likewise. (OMP_CLAUSE_GRIDDIM_SIZE): Likewise. (OMP_CLAUSE_GRIDDIM_GROUP): Likewise. * passes.def: Schedule pass_ipa_hsa and pass_gen_hsail. * tree-pass.h (make_pass_gen_hsail): Declare. (make_pass_ipa_hsa): Likewise. * ipa-hsa.c: New file. * lto-section-in.c (lto_section_name): Add hsa section name. * lto-streamer.h (lto_section_type): Add hsa section. * timevar.def (TV_IPA_HSA): New. * hsa-brig-format.h: New file. * hsa-brig.c: New file. * hsa-dump.c: Likewise. * hsa-gen.c: Likewise. * hsa.c: Likewise. * hsa.h: Likewise. * toplev.c (compile_file): Call hsa_output_brig. * hsa-regalloc.c: New file. gcc/fortran/ * types.def (BT_FN_VOID_UINT_PTR_INT_PTR): New. (BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_INT_INT): Removed. (BT_FN_VOID_INT_OMPFN_SIZE_PTR_PTR_PTR_UINT_PTR_PTR): New. gcc/lto/ * lto-partition.c: Include "hsa.h" (add_symbol_to_partition_1): Put hsa implementations into the same partition as host implementations. liboffloadmic/ * plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_async_run): New unused parameter. (GOMP_OFFLOAD_run): Likewise. include/ * gomp-constants.h (GOMP_DEVICE_HSA): New macro. (GOMP_VERSION_HSA): Likewise. (GOMP_TARGET_ARG_DEVICE_MASK): Likewise. (GOMP_TARGET_ARG_DEVICE_ALL): Likewise. (GOMP_TARGET_ARG_SUBSEQUENT_PARAM): Likewise. (GOMP_TARGET_ARG_ID_MASK): Likewise. (GOMP_TARGET_ARG_NUM_TEAMS): Likewise. (GOMP_TARGET_ARG_THREAD_LIMIT): Likewise. (GOMP_TARGET_ARG_VALUE_SHIFT): Likewise. (GOMP_TARGET_ARG_HSA_KERNEL_ATTRIBUTES): Likewise. From-SVN: r232549
262 lines
5.9 KiB
C
262 lines
5.9 KiB
C
/* OpenACC Runtime Library: acc_device_host.
|
|
|
|
Copyright (C) 2013-2016 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 void
|
|
host_init_device (int n __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
static void
|
|
host_fini_device (int n __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
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 void
|
|
host_unload_image (int n __attribute__ ((unused)),
|
|
unsigned v __attribute__ ((unused)),
|
|
const void *t __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
static void *
|
|
host_alloc (int n __attribute__ ((unused)), size_t s)
|
|
{
|
|
return gomp_malloc (s);
|
|
}
|
|
|
|
static void
|
|
host_free (int n __attribute__ ((unused)), void *p)
|
|
{
|
|
free (p);
|
|
}
|
|
|
|
static void *
|
|
host_dev2host (int n __attribute__ ((unused)),
|
|
void *h __attribute__ ((unused)),
|
|
const void *d __attribute__ ((unused)),
|
|
size_t s __attribute__ ((unused)))
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static void *
|
|
host_host2dev (int n __attribute__ ((unused)),
|
|
void *d __attribute__ ((unused)),
|
|
const void *h __attribute__ ((unused)),
|
|
size_t s __attribute__ ((unused)))
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
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)),
|
|
int async __attribute__ ((unused)),
|
|
unsigned *dims __attribute ((unused)),
|
|
void *targ_mem_desc __attribute__ ((unused)))
|
|
{
|
|
fn (hostaddrs);
|
|
}
|
|
|
|
static void
|
|
host_openacc_register_async_cleanup (void *targ_mem_desc __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
static int
|
|
host_openacc_async_test (int async __attribute__ ((unused)))
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static int
|
|
host_openacc_async_test_all (void)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static void
|
|
host_openacc_async_wait (int async __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
static void
|
|
host_openacc_async_wait_async (int async1 __attribute__ ((unused)),
|
|
int async2 __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
static void
|
|
host_openacc_async_wait_all (void)
|
|
{
|
|
}
|
|
|
|
static void
|
|
host_openacc_async_wait_all_async (int async __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
static void
|
|
host_openacc_async_set_async (int async __attribute__ ((unused)))
|
|
{
|
|
}
|
|
|
|
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,
|
|
|
|
.register_async_cleanup_func = host_openacc_register_async_cleanup,
|
|
|
|
.async_test_func = host_openacc_async_test,
|
|
.async_test_all_func = host_openacc_async_test_all,
|
|
.async_wait_func = host_openacc_async_wait,
|
|
.async_wait_async_func = host_openacc_async_wait_async,
|
|
.async_wait_all_func = host_openacc_async_wait_all,
|
|
.async_wait_all_async_func = host_openacc_async_wait_all_async,
|
|
.async_set_async_func = host_openacc_async_set_async,
|
|
|
|
.create_thread_data_func = host_openacc_create_thread_data,
|
|
.destroy_thread_data_func = host_openacc_destroy_thread_data,
|
|
|
|
.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);
|
|
}
|