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
260 lines
10 KiB
C
260 lines
10 KiB
C
/* Communication between GCC and libgomp.
|
|
|
|
Copyright (C) 2014-2015 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/>. */
|
|
|
|
#ifndef GOMP_CONSTANTS_H
|
|
#define GOMP_CONSTANTS_H 1
|
|
|
|
/* Memory mapping types. */
|
|
|
|
/* One byte. */
|
|
#define GOMP_MAP_LAST (1 << 8)
|
|
|
|
#define GOMP_MAP_FLAG_TO (1 << 0)
|
|
#define GOMP_MAP_FLAG_FROM (1 << 1)
|
|
/* Special map kinds, enumerated starting here. */
|
|
#define GOMP_MAP_FLAG_SPECIAL_0 (1 << 2)
|
|
#define GOMP_MAP_FLAG_SPECIAL_1 (1 << 3)
|
|
#define GOMP_MAP_FLAG_SPECIAL_2 (1 << 4)
|
|
#define GOMP_MAP_FLAG_SPECIAL (GOMP_MAP_FLAG_SPECIAL_1 \
|
|
| GOMP_MAP_FLAG_SPECIAL_0)
|
|
/* Flag to force a specific behavior (or else, trigger a run-time error). */
|
|
#define GOMP_MAP_FLAG_FORCE (1 << 7)
|
|
|
|
enum gomp_map_kind
|
|
{
|
|
/* If not already present, allocate. */
|
|
GOMP_MAP_ALLOC = 0,
|
|
/* ..., and copy to device. */
|
|
GOMP_MAP_TO = (GOMP_MAP_ALLOC | GOMP_MAP_FLAG_TO),
|
|
/* ..., and copy from device. */
|
|
GOMP_MAP_FROM = (GOMP_MAP_ALLOC | GOMP_MAP_FLAG_FROM),
|
|
/* ..., and copy to and from device. */
|
|
GOMP_MAP_TOFROM = (GOMP_MAP_TO | GOMP_MAP_FROM),
|
|
/* The following kind is an internal only map kind, used for pointer based
|
|
array sections. OMP_CLAUSE_SIZE for these is not the pointer size,
|
|
which is implicitly POINTER_SIZE_UNITS, but the bias. */
|
|
GOMP_MAP_POINTER = (GOMP_MAP_FLAG_SPECIAL_0 | 0),
|
|
/* Also internal, behaves like GOMP_MAP_TO, but additionally any
|
|
GOMP_MAP_POINTER records consecutive after it which have addresses
|
|
falling into that range will not be ignored if GOMP_MAP_TO_PSET wasn't
|
|
mapped already. */
|
|
GOMP_MAP_TO_PSET = (GOMP_MAP_FLAG_SPECIAL_0 | 1),
|
|
/* Must already be present. */
|
|
GOMP_MAP_FORCE_PRESENT = (GOMP_MAP_FLAG_SPECIAL_0 | 2),
|
|
/* Deallocate a mapping, without copying from device. */
|
|
GOMP_MAP_FORCE_DEALLOC = (GOMP_MAP_FLAG_SPECIAL_0 | 3),
|
|
/* Is a device pointer. OMP_CLAUSE_SIZE for these is unused; is implicitly
|
|
POINTER_SIZE_UNITS. */
|
|
GOMP_MAP_FORCE_DEVICEPTR = (GOMP_MAP_FLAG_SPECIAL_1 | 0),
|
|
/* Do not map, copy bits for firstprivate instead. */
|
|
/* OpenACC device_resident. */
|
|
GOMP_MAP_DEVICE_RESIDENT = (GOMP_MAP_FLAG_SPECIAL_1 | 1),
|
|
/* OpenACC link. */
|
|
GOMP_MAP_LINK = (GOMP_MAP_FLAG_SPECIAL_1 | 2),
|
|
/* Allocate. */
|
|
GOMP_MAP_FIRSTPRIVATE = (GOMP_MAP_FLAG_SPECIAL | 0),
|
|
/* Similarly, but store the value in the pointer rather than
|
|
pointed by the pointer. */
|
|
GOMP_MAP_FIRSTPRIVATE_INT = (GOMP_MAP_FLAG_SPECIAL | 1),
|
|
/* Pointer translate host address into device address and copy that
|
|
back to host. */
|
|
GOMP_MAP_USE_DEVICE_PTR = (GOMP_MAP_FLAG_SPECIAL | 2),
|
|
/* Allocate a zero length array section. Prefer next non-zero length
|
|
mapping over previous non-zero length mapping over zero length mapping
|
|
at the address. If not already mapped, do nothing (and pointer translate
|
|
to NULL). */
|
|
GOMP_MAP_ZERO_LEN_ARRAY_SECTION = (GOMP_MAP_FLAG_SPECIAL | 3),
|
|
/* Allocate. */
|
|
GOMP_MAP_FORCE_ALLOC = (GOMP_MAP_FLAG_FORCE | GOMP_MAP_ALLOC),
|
|
/* ..., and copy to device. */
|
|
GOMP_MAP_FORCE_TO = (GOMP_MAP_FLAG_FORCE | GOMP_MAP_TO),
|
|
/* ..., and copy from device. */
|
|
GOMP_MAP_FORCE_FROM = (GOMP_MAP_FLAG_FORCE | GOMP_MAP_FROM),
|
|
/* ..., and copy to and from device. */
|
|
GOMP_MAP_FORCE_TOFROM = (GOMP_MAP_FLAG_FORCE | GOMP_MAP_TOFROM),
|
|
/* If not already present, allocate. And unconditionally copy to
|
|
device. */
|
|
GOMP_MAP_ALWAYS_TO = (GOMP_MAP_FLAG_SPECIAL_2 | GOMP_MAP_TO),
|
|
/* If not already present, allocate. And unconditionally copy from
|
|
device. */
|
|
GOMP_MAP_ALWAYS_FROM = (GOMP_MAP_FLAG_SPECIAL_2
|
|
| GOMP_MAP_FROM),
|
|
/* If not already present, allocate. And unconditionally copy to and from
|
|
device. */
|
|
GOMP_MAP_ALWAYS_TOFROM = (GOMP_MAP_FLAG_SPECIAL_2
|
|
| GOMP_MAP_TOFROM),
|
|
/* Map a sparse struct; the address is the base of the structure, alignment
|
|
it's required alignment, and size is the number of adjacent entries
|
|
that belong to the struct. The adjacent entries should be sorted by
|
|
increasing address, so it is easy to determine lowest needed address
|
|
(address of the first adjacent entry) and highest needed address
|
|
(address of the last adjacent entry plus its size). */
|
|
GOMP_MAP_STRUCT = (GOMP_MAP_FLAG_SPECIAL_2
|
|
| GOMP_MAP_FLAG_SPECIAL | 0),
|
|
/* On a location of a pointer/reference that is assumed to be already mapped
|
|
earlier, store the translated address of the preceeding mapping.
|
|
No refcount is bumped by this, and the store is done unconditionally. */
|
|
GOMP_MAP_ALWAYS_POINTER = (GOMP_MAP_FLAG_SPECIAL_2
|
|
| GOMP_MAP_FLAG_SPECIAL | 1),
|
|
/* Forced deallocation of zero length array section. */
|
|
GOMP_MAP_DELETE_ZERO_LEN_ARRAY_SECTION
|
|
= (GOMP_MAP_FLAG_SPECIAL_2
|
|
| GOMP_MAP_FLAG_SPECIAL | 3),
|
|
/* OpenMP 4.5 alias for forced deallocation. */
|
|
GOMP_MAP_DELETE = GOMP_MAP_FORCE_DEALLOC,
|
|
/* Decrement usage count and deallocate if zero. */
|
|
GOMP_MAP_RELEASE = (GOMP_MAP_FLAG_SPECIAL_2
|
|
| GOMP_MAP_FORCE_DEALLOC),
|
|
|
|
/* Internal to GCC, not used in libgomp. */
|
|
/* Do not map, but pointer assign a pointer instead. */
|
|
GOMP_MAP_FIRSTPRIVATE_POINTER = (GOMP_MAP_LAST | 1),
|
|
/* Do not map, but pointer assign a reference instead. */
|
|
GOMP_MAP_FIRSTPRIVATE_REFERENCE = (GOMP_MAP_LAST | 2)
|
|
};
|
|
|
|
#define GOMP_MAP_COPY_TO_P(X) \
|
|
(!((X) & GOMP_MAP_FLAG_SPECIAL) \
|
|
&& ((X) & GOMP_MAP_FLAG_TO))
|
|
|
|
#define GOMP_MAP_COPY_FROM_P(X) \
|
|
(!((X) & GOMP_MAP_FLAG_SPECIAL) \
|
|
&& ((X) & GOMP_MAP_FLAG_FROM))
|
|
|
|
#define GOMP_MAP_POINTER_P(X) \
|
|
((X) == GOMP_MAP_POINTER)
|
|
|
|
#define GOMP_MAP_ALWAYS_TO_P(X) \
|
|
(((X) == GOMP_MAP_ALWAYS_TO) || ((X) == GOMP_MAP_ALWAYS_TOFROM))
|
|
|
|
#define GOMP_MAP_ALWAYS_FROM_P(X) \
|
|
(((X) == GOMP_MAP_ALWAYS_FROM) || ((X) == GOMP_MAP_ALWAYS_TOFROM))
|
|
|
|
#define GOMP_MAP_ALWAYS_P(X) \
|
|
(GOMP_MAP_ALWAYS_TO_P (X) || ((X) == GOMP_MAP_ALWAYS_FROM))
|
|
|
|
|
|
/* Asynchronous behavior. Keep in sync with
|
|
libgomp/{openacc.h,openacc.f90,openacc_lib.h}:acc_async_t. */
|
|
|
|
#define GOMP_ASYNC_NOVAL -1
|
|
#define GOMP_ASYNC_SYNC -2
|
|
|
|
|
|
/* Device codes. Keep in sync with
|
|
libgomp/{openacc.h,openacc.f90,openacc_lib.h}:acc_device_t as well as
|
|
libgomp/libgomp-plugin.h. */
|
|
#define GOMP_DEVICE_NONE 0
|
|
#define GOMP_DEVICE_DEFAULT 1
|
|
#define GOMP_DEVICE_HOST 2
|
|
/* #define GOMP_DEVICE_HOST_NONSHM 3 removed. */
|
|
#define GOMP_DEVICE_NOT_HOST 4
|
|
#define GOMP_DEVICE_NVIDIA_PTX 5
|
|
#define GOMP_DEVICE_INTEL_MIC 6
|
|
#define GOMP_DEVICE_HSA 7
|
|
|
|
#define GOMP_DEVICE_ICV -1
|
|
#define GOMP_DEVICE_HOST_FALLBACK -2
|
|
|
|
/* GOMP_task/GOMP_taskloop* flags argument. */
|
|
#define GOMP_TASK_FLAG_UNTIED (1 << 0)
|
|
#define GOMP_TASK_FLAG_FINAL (1 << 1)
|
|
#define GOMP_TASK_FLAG_MERGEABLE (1 << 2)
|
|
#define GOMP_TASK_FLAG_DEPEND (1 << 3)
|
|
#define GOMP_TASK_FLAG_PRIORITY (1 << 4)
|
|
#define GOMP_TASK_FLAG_UP (1 << 8)
|
|
#define GOMP_TASK_FLAG_GRAINSIZE (1 << 9)
|
|
#define GOMP_TASK_FLAG_IF (1 << 10)
|
|
#define GOMP_TASK_FLAG_NOGROUP (1 << 11)
|
|
|
|
/* GOMP_target{_ext,update_ext,enter_exit_data} flags argument. */
|
|
#define GOMP_TARGET_FLAG_NOWAIT (1 << 0)
|
|
#define GOMP_TARGET_FLAG_EXIT_DATA (1 << 1)
|
|
/* Internal to libgomp. */
|
|
#define GOMP_TARGET_FLAG_UPDATE (1U << 31)
|
|
|
|
/* Versions of libgomp and device-specific plugins. */
|
|
#define GOMP_VERSION 0
|
|
#define GOMP_VERSION_NVIDIA_PTX 1
|
|
#define GOMP_VERSION_INTEL_MIC 0
|
|
#define GOMP_VERSION_HSA 0
|
|
|
|
#define GOMP_VERSION_PACK(LIB, DEV) (((LIB) << 16) | (DEV))
|
|
#define GOMP_VERSION_LIB(PACK) (((PACK) >> 16) & 0xffff)
|
|
#define GOMP_VERSION_DEV(PACK) ((PACK) & 0xffff)
|
|
|
|
#define GOMP_DIM_GANG 0
|
|
#define GOMP_DIM_WORKER 1
|
|
#define GOMP_DIM_VECTOR 2
|
|
#define GOMP_DIM_MAX 3
|
|
#define GOMP_DIM_MASK(X) (1u << (X))
|
|
|
|
/* Varadic launch arguments. End of list is marked by a zero. */
|
|
#define GOMP_LAUNCH_DIM 1 /* Launch dimensions, op = mask */
|
|
#define GOMP_LAUNCH_ASYNC 2 /* Async, op = cst val if not MAX */
|
|
#define GOMP_LAUNCH_WAIT 3 /* Waits, op = num waits. */
|
|
#define GOMP_LAUNCH_CODE_SHIFT 28
|
|
#define GOMP_LAUNCH_DEVICE_SHIFT 16
|
|
#define GOMP_LAUNCH_OP_SHIFT 0
|
|
#define GOMP_LAUNCH_PACK(CODE,DEVICE,OP) \
|
|
(((CODE) << GOMP_LAUNCH_CODE_SHIFT) \
|
|
| ((DEVICE) << GOMP_LAUNCH_DEVICE_SHIFT) \
|
|
| ((OP) << GOMP_LAUNCH_OP_SHIFT))
|
|
#define GOMP_LAUNCH_CODE(X) (((X) >> GOMP_LAUNCH_CODE_SHIFT) & 0xf)
|
|
#define GOMP_LAUNCH_DEVICE(X) (((X) >> GOMP_LAUNCH_DEVICE_SHIFT) & 0xfff)
|
|
#define GOMP_LAUNCH_OP(X) (((X) >> GOMP_LAUNCH_OP_SHIFT) & 0xffff)
|
|
#define GOMP_LAUNCH_OP_MAX 0xffff
|
|
|
|
/* Bitmask to apply in order to find out the intended device of a target
|
|
argument. */
|
|
#define GOMP_TARGET_ARG_DEVICE_MASK ((1 << 7) - 1)
|
|
/* The target argument is significant for all devices. */
|
|
#define GOMP_TARGET_ARG_DEVICE_ALL 0
|
|
|
|
/* Flag set when the subsequent element in the device-specific argument
|
|
values. */
|
|
#define GOMP_TARGET_ARG_SUBSEQUENT_PARAM (1 << 7)
|
|
|
|
/* Bitmask to apply to a target argument to find out the value identifier. */
|
|
#define GOMP_TARGET_ARG_ID_MASK (((1 << 8) - 1) << 8)
|
|
/* Target argument index of NUM_TEAMS. */
|
|
#define GOMP_TARGET_ARG_NUM_TEAMS (1 << 8)
|
|
/* Target argument index of THREAD_LIMIT. */
|
|
#define GOMP_TARGET_ARG_THREAD_LIMIT (2 << 8)
|
|
|
|
/* If the value is directly embeded in target argument, it should be a 16-bit
|
|
at most and shifted by this many bits. */
|
|
#define GOMP_TARGET_ARG_VALUE_SHIFT 16
|
|
|
|
/* HSA specific data structures. */
|
|
|
|
/* Identifiers of device-specific target arguments. */
|
|
#define GOMP_TARGET_ARG_HSA_KERNEL_ATTRIBUTES (1 << 8)
|
|
|
|
#endif
|