BLI_task.h File Reference

#include <string.h>
#include "BLI_threads.h"
#include "BLI_utildefines.h"

Go to the source code of this file.

Classes
struct	TaskParallelTLS
struct	TaskParallelSettings

Functions
Task Scheduler
Central scheduler that holds running threads ready to execute tasks. A single queue holds the task from all pools. Initialize/exit must be called before/after any task pools are created/freed, and must be called from the main threads. All other scheduler and pool functions are thread-safe.
void	BLI_task_scheduler_init (void)
void	BLI_task_scheduler_exit (void)
int	BLI_task_scheduler_num_threads (void)
Task Isolation
Task isolation helps avoid unexpected task scheduling decisions that can lead to bugs if wrong assumptions were made. Typically that happens when doing "nested threading", i.e. one thread schedules a bunch of main-tasks and those spawn new sub-tasks. What can happen is that when a main-task waits for its sub-tasks to complete on other threads, another main-task is scheduled within the already running main-task. Generally, this is good, because it leads to better performance. However, sometimes code (often unintentionally) makes the assumption that at most one main-task runs on a thread at a time. The bugs often show themselves in two ways: Deadlock, when a main-task holds a mutex while waiting for its sub-tasks to complete. Data corruption, when a main-task makes wrong assumptions about a thread-local variable. Task isolation can avoid these bugs by making sure that a main-task does not start executing another main-task while waiting for its sub-tasks. More precisely, a function that runs in an isolated region is only allowed to run sub-tasks that were spawned in the same isolated region. Unfortunately, incorrect use of task isolation can lead to deadlocks itself. This can happen when threading primitives are used that separate spawning tasks from executing them. The problem occurs when a task is spawned in one isolated region while the tasks are waited for in another isolated region. In this setup, the thread that is waiting for the spawned tasks to complete cannot run the tasks itself. On a single thread, that causes a deadlock already. When there are multiple threads, another thread will typically run the task and avoid the deadlock. However, if this situation happens on all threads at the same time, all threads will deadlock. This happened in #88598.
void	BLI_task_isolate (void(*func)(void *userdata), void *userdata)

Task Pool
Pool of tasks that will be executed by the central task scheduler. For each pool, we can wait for all tasks to be done, or cancel them before they are done. Running tasks may spawn new tasks. Pools may be nested, i.e. a thread running a task can create another task pool with smaller tasks. When other threads are busy they will continue working on their own tasks, if not they will join in, no new threads will be launched.
enum	eTaskPriority { TASK_PRIORITY_LOW , TASK_PRIORITY_HIGH }
typedef enum eTaskPriority	eTaskPriority
typedef struct TaskPool	TaskPool
typedef void(*	TaskRunFunction) (TaskPool *__restrict pool, void *taskdata)
typedef void(*	TaskFreeFunction) (TaskPool *__restrict pool, void *taskdata)
TaskPool *	BLI_task_pool_create (void *userdata, eTaskPriority priority)
TaskPool *	BLI_task_pool_create_background (void *userdata, eTaskPriority priority)
TaskPool *	BLI_task_pool_create_background_serial (void *userdata, eTaskPriority priority)
TaskPool *	BLI_task_pool_create_suspended (void *userdata, eTaskPriority priority)
TaskPool *	BLI_task_pool_create_no_threads (void *userdata)
void	BLI_task_pool_free (TaskPool *pool)
void	BLI_task_pool_push (TaskPool *pool, TaskRunFunction run, void *taskdata, bool free_taskdata, TaskFreeFunction freedata)
void	BLI_task_pool_work_and_wait (TaskPool *pool)
void	BLI_task_pool_cancel (TaskPool *pool)
bool	BLI_task_pool_current_canceled (TaskPool *pool)
void *	BLI_task_pool_user_data (TaskPool *pool)

Parallel for Routines
typedef struct TaskParallelTLS	TaskParallelTLS
typedef void(*	TaskParallelRangeFunc) (void *__restrict userdata, int iter, const TaskParallelTLS *__restrict tls)
typedef void(*	TaskParallelInitFunc) (const void *__restrict userdata, void *__restrict chunk)
typedef void(*	TaskParallelReduceFunc) (const void *__restrict userdata, void *__restrict chunk_join, void *__restrict chunk)
typedef void(*	TaskParallelFreeFunc) (const void *__restrict userdata, void *__restrict chunk)
typedef struct TaskParallelSettings	TaskParallelSettings
typedef struct MempoolIterData	MempoolIterData
typedef void(*	TaskParallelMempoolFunc) (void *userdata, MempoolIterData *iter, const TaskParallelTLS *__restrict tls)
BLI_INLINE void	BLI_parallel_range_settings_defaults (TaskParallelSettings *settings)
void	BLI_task_parallel_range (int start, int stop, void *userdata, TaskParallelRangeFunc func, const TaskParallelSettings *settings)
void	BLI_task_parallel_mempool (struct BLI_mempool *mempool, void *userdata, TaskParallelMempoolFunc func, const TaskParallelSettings *settings)
BLI_INLINE void	BLI_parallel_mempool_settings_defaults (TaskParallelSettings *settings)
int	BLI_task_parallel_thread_id (const TaskParallelTLS *tls)

Task Graph Scheduling
Task Graphs can be used to create a forest of directional trees and schedule work to any tree. The nodes in the graph can be run in separate threads. +---- [root] ----+ | | v v [node_1] +---- [node_2] ----+ | | v v [node_3] [node_4] TaskGraph *task_graph = BLI_task_graph_create(); TaskNode *root = BLI_task_graph_node_create(task_graph, root_exec, NULL, NULL); TaskNode *node_1 = BLI_task_graph_node_create(task_graph, node_exec, NULL, NULL); TaskNode *node_2 = BLI_task_graph_node_create(task_graph, node_exec, NULL, NULL); TaskNode *node_3 = BLI_task_graph_node_create(task_graph, node_exec, NULL, NULL); TaskNode *node_4 = BLI_task_graph_node_create(task_graph, node_exec, NULL, NULL); BLI_task_graph_edge_create(root, node_1); BLI_task_graph_edge_create(root, node_2); BLI_task_graph_edge_create(node_2, node_3); BLI_task_graph_edge_create(node_2, node_4); Any node can be triggered to start a chain of tasks. Normally you would trigger a root node but it is supported to start the chain of tasks anywhere in the forest or tree. When a node completes, the execution flow is forwarded via the created edges. When a child node has multiple parents the child node will be triggered once for each parent. BLI_task_graph_node_push_work(root); In this example After root is finished, node_1 and node_2 will be started. Only after node_2 is finished node_3 and node_4 will be started. After scheduling work we need to wait until all the tasks have been finished. BLI_task_graph_work_and_wait(); When finished you can clean up all the resources by freeing the task_graph. Nodes are owned by the graph and are freed task_data will only be freed if a free_func was given. BLI_task_graph_free(task_graph); Work can enter a tree on any node. Normally this would be the root_node. A task_graph can be reused, but the caller needs to make sure the task_data is reset. Task-Data Typically you want give a task data to work on. Task data can be shared with other nodes, but be careful not to free the data multiple times. Task data is freed when calling BLI_task_graph_free. MyData *task_data = MEM_callocN(sizeof(MyData), __func__); TaskNode *root = BLI_task_graph_node_create(task_graph, root_exec, task_data, MEM_freeN); TaskNode *node_1 = BLI_task_graph_node_create(task_graph, node_exec, task_data, NULL); TaskNode *node_2 = BLI_task_graph_node_create(task_graph, node_exec, task_data, NULL); TaskNode *node_3 = BLI_task_graph_node_create(task_graph, node_exec, task_data, NULL); TaskNode *node_4 = BLI_task_graph_node_create(task_graph, node_exec, task_data, NULL);
typedef void(*	TaskGraphNodeRunFunction) (void *__restrict task_data)
typedef void(*	TaskGraphNodeFreeFunction) (void *task_data)
struct TaskGraph *	BLI_task_graph_create (void)
void	BLI_task_graph_work_and_wait (struct TaskGraph *task_graph)
void	BLI_task_graph_free (struct TaskGraph *task_graph)
struct TaskNode *	BLI_task_graph_node_create (struct TaskGraph *task_graph, TaskGraphNodeRunFunction run, void *user_data, TaskGraphNodeFreeFunction free_func)
bool	BLI_task_graph_node_push_work (struct TaskNode *task_node)
void	BLI_task_graph_edge_create (struct TaskNode *from_node, struct TaskNode *to_node)

Typedef Documentation

eTaskPriority

typedef enum eTaskPriority eTaskPriority

MempoolIterData

typedef struct MempoolIterData MempoolIterData

Definition at line 200 of file BLI_task.h.

TaskFreeFunction

typedef void(* TaskFreeFunction) (TaskPool *__restrict pool, void *taskdata)

Definition at line 58 of file BLI_task.h.

TaskGraphNodeFreeFunction

typedef void(* TaskGraphNodeFreeFunction) (void *task_data)

Definition at line 316 of file BLI_task.h.

TaskGraphNodeRunFunction

typedef void(* TaskGraphNodeRunFunction) (void *__restrict task_data)

Definition at line 315 of file BLI_task.h.

TaskParallelFreeFunc

typedef void(* TaskParallelFreeFunc) (const void *__restrict userdata, void *__restrict chunk)

Definition at line 150 of file BLI_task.h.

TaskParallelInitFunc

typedef void(* TaskParallelInitFunc) (const void *__restrict userdata, void *__restrict chunk)

Definition at line 144 of file BLI_task.h.

TaskParallelMempoolFunc

typedef void(* TaskParallelMempoolFunc) (void *userdata, MempoolIterData *iter, const TaskParallelTLS *__restrict tls)

Definition at line 202 of file BLI_task.h.

TaskParallelRangeFunc

typedef void(* TaskParallelRangeFunc) (void *__restrict userdata, int iter, const TaskParallelTLS *__restrict tls)

Definition at line 140 of file BLI_task.h.

TaskParallelReduceFunc

typedef void(* TaskParallelReduceFunc) (const void *__restrict userdata, void *__restrict chunk_join, void *__restrict chunk)

Definition at line 146 of file BLI_task.h.

TaskParallelSettings

typedef struct TaskParallelSettings TaskParallelSettings

TaskParallelTLS

typedef struct TaskParallelTLS TaskParallelTLS

Per-thread specific data passed to the callback.

TaskPool

typedef struct TaskPool TaskPool

Definition at line 56 of file BLI_task.h.

TaskRunFunction

typedef void(* TaskRunFunction) (TaskPool *__restrict pool, void *taskdata)

Definition at line 57 of file BLI_task.h.

Enumeration Type Documentation

eTaskPriority

enum eTaskPriority

Enumerator
TASK_PRIORITY_LOW
TASK_PRIORITY_HIGH

Definition at line 51 of file BLI_task.h.

Function Documentation

BLI_parallel_mempool_settings_defaults()

BLI_INLINE void BLI_parallel_mempool_settings_defaults

(

TaskParallelSettings *

settings

)

Definition at line 229 of file BLI_task.h.

References BLI_INLINE, and TaskParallelSettings::use_threading.

Referenced by blender::bke::armature_deform_editmesh(), bm_mesh_calc_tessellation__multi_threaded(), bm_mesh_loops_calc_normals__multi_threaded(), BM_mesh_normals_update_ex(), bm_mesh_verts_calc_normals(), lattice_deform_coords_impl(), TEST(), and TEST().

BLI_parallel_range_settings_defaults()

BLI_INLINE void BLI_parallel_range_settings_defaults

(

TaskParallelSettings *

settings

)

TODO(sergey): Think of a better place for this.

Definition at line 221 of file BLI_task.h.

References BLI_INLINE, TaskParallelSettings::min_iter_per_thread, and TaskParallelSettings::use_threading.

Referenced by BKE_autotrack_context_step(), BKE_maskrasterize_buffer(), BKE_scopes_update(), BKE_tracking_stabilize_frame(), BLI_bvhtree_overlap_ex(), BLI_covariance_m_vn_ex(), BM_loop_interp_multires_ex(), bm_mesh_calc_tessellation_with_partial__multi_threaded(), bm_mesh_select_mode_flush_edge_to_face(), bm_mesh_select_mode_flush_vert_to_edge(), brush_add(), cloth_bvh_objcollisions_nearcheck(), cloth_bvh_selfcollisions_nearcheck(), displaceModifier_do(), dynamicPaint_applySurfaceDisplace(), dynamicPaint_brushMeshCalculateVelocity(), dynamicPaint_createUVSurface(), dynamicPaint_doBorderStep(), dynamicPaint_doEffectStep(), dynamicPaint_doStep(), dynamicPaint_doWaveStep(), dynamicPaint_generateBakeData(), dynamicPaint_Modifier_apply(), dynamicPaint_outputSurfaceImage(), dynamicPaint_paintMesh(), dynamicPaint_paintParticles(), dynamicPaint_paintSinglePoint(), dynamicPaint_prepareAdjacencyData(), dynamicPaint_prepareEffectStep(), dynamicPaint_setInitialColor(), dynamics_step(), foreach_grid_coordinate(), foreach_mouse_hit_key(), blender::bke::subdiv::foreach_subdiv_geometry(), get_vert2geom_distance(), lattice_deform_coords_impl(), lineart_build_edge_neighbor(), lineart_geometry_object_load(), lineart_main_transform_and_add_shadow(), blender::ed::sculpt_paint::load_tex(), blender::ed::sculpt_paint::load_tex_cursor(), meshdeformModifier_do(), modify_mesh(), non_recursive_bvh_div_nodes(), paint_2d_op(), PE_apply_lengths(), pe_deflect_emitter(), pe_iterate_lengths(), psys_cache_edit_paths(), recount_totsel(), shrinkwrap_calc_nearest_surface_point(), shrinkwrap_calc_nearest_vertex(), shrinkwrap_calc_normal_projection(), SimpleDeformModifier_do(), surfacedeformBind(), surfacedeformModifier_do(), surfaceGenerateGrid(), and TEST().

BLI_task_graph_create()

struct TaskGraph * BLI_task_graph_create

(

void

)

Definition at line 96 of file task_graph.cc.

Referenced by TEST(), TEST(), TEST(), TEST(), and TEST().

BLI_task_graph_edge_create()

void BLI_task_graph_edge_create	(	struct TaskNode *	from_node,
		struct TaskNode *	to_node )

Definition at line 137 of file task_graph.cc.

References BLI_task_scheduler_num_threads(), and TaskNode::successors.

Referenced by TEST(), TEST(), TEST(), TEST(), and TEST().

BLI_task_graph_free()

void BLI_task_graph_free

(

struct TaskGraph *

task_graph

)

Definition at line 101 of file task_graph.cc.

Referenced by TEST(), TEST(), TEST(), TEST(), TEST(), and ExtractionGraph::work_and_wait().

BLI_task_graph_node_create()

struct TaskNode * BLI_task_graph_node_create	(	struct TaskGraph *	task_graph,
		TaskGraphNodeRunFunction	run,
		void *	user_data,
		TaskGraphNodeFreeFunction	free_func )

Definition at line 115 of file task_graph.cc.

References free_func(), and TaskGraph::nodes.

Referenced by TEST(), TEST(), TEST(), TEST(), and TEST().

BLI_task_graph_node_push_work()

bool BLI_task_graph_node_push_work

(

struct TaskNode *

task_node

)

Definition at line 125 of file task_graph.cc.

References BLI_task_scheduler_num_threads(), and TaskNode::run_serial().

Referenced by TEST(), TEST(), TEST(), TEST(), and TEST().

BLI_task_graph_work_and_wait()

void BLI_task_graph_work_and_wait

(

struct TaskGraph *

task_graph

)

Definition at line 106 of file task_graph.cc.

References UNUSED_VARS.

Referenced by TEST(), TEST(), TEST(), TEST(), TEST(), and ExtractionGraph::work_and_wait().

BLI_task_isolate()

void BLI_task_isolate	(	void(*	func )(void *userdata),
		void *	userdata )

Definition at line 70 of file task_scheduler.cc.

Referenced by add_ibuf_for_tile(), modify_mesh(), and psys_update_particle_bvhtree().

BLI_task_parallel_mempool()

void BLI_task_parallel_mempool	(	struct BLI_mempool *	mempool,
		void *	userdata,
		TaskParallelMempoolFunc	func,
		const TaskParallelSettings *	settings )

This function allows to parallelize for loops over Mempool items.

Parameters

mempool	The iterable BLI_mempool to loop over.
userdata	Common userdata passed to all instances of func.
func	Callback function.
settings	See public API doc of TaskParallelSettings for description of all settings.

Note

There is no static scheduling here.

Definition at line 55 of file task_iterator.cc.

References BLI_mempool_iternew(), BLI_mempool_iterstep(), BLI_mempool_len(), BLI_task_pool_create(), BLI_task_pool_free(), BLI_task_pool_push(), BLI_task_pool_work_and_wait(), BLI_task_scheduler_num_threads(), TaskParallelSettings::func_free, TaskParallelSettings::func_init, TaskParallelSettings::func_reduce, i, MALLOCA, MALLOCA_FREE, mempool_iter_threadsafe_create(), mempool_iter_threadsafe_destroy(), parallel_mempool_func(), state, task_pool, TASK_PRIORITY_HIGH, ParallelMempoolTaskData::tls, UNLIKELY, TaskParallelSettings::use_threading, TaskParallelSettings::userdata_chunk, TaskParallelTLS::userdata_chunk, and TaskParallelSettings::userdata_chunk_size.

Referenced by blender::bke::armature_deform_editmesh(), lattice_deform_coords_impl(), TEST(), and TEST().

BLI_task_parallel_range()

void BLI_task_parallel_range	(	int	start,
		int	stop,
		void *	userdata,
		TaskParallelRangeFunc	func,
		const TaskParallelSettings *	settings )

Definition at line 99 of file task_range.cc.

References BLI_task_scheduler_num_threads(), TaskParallelSettings::func_free, TaskParallelSettings::func_reduce, i, TaskParallelSettings::min_iter_per_thread, parallel_reduce(), blender::lazy_threading::send_hint(), TaskParallelSettings::use_threading, TaskParallelSettings::userdata_chunk, TaskParallelTLS::userdata_chunk, and TaskParallelSettings::userdata_chunk_size.

Referenced by BKE_autotrack_context_step(), BKE_maskrasterize_buffer(), BKE_scopes_update(), BKE_tracking_stabilize_frame(), BLI_bvhtree_overlap_ex(), BLI_covariance_m_vn_ex(), BM_loop_interp_multires_ex(), bm_mesh_calc_tessellation_with_partial__multi_threaded(), brush_add(), cloth_bvh_objcollisions_nearcheck(), cloth_bvh_selfcollisions_nearcheck(), displaceModifier_do(), dynamicPaint_applySurfaceDisplace(), dynamicPaint_brushMeshCalculateVelocity(), dynamicPaint_createUVSurface(), dynamicPaint_doBorderStep(), dynamicPaint_doEffectStep(), dynamicPaint_doStep(), dynamicPaint_doWaveStep(), dynamicPaint_generateBakeData(), dynamicPaint_Modifier_apply(), dynamicPaint_outputSurfaceImage(), dynamicPaint_paintMesh(), dynamicPaint_paintParticles(), dynamicPaint_paintSinglePoint(), dynamicPaint_prepareAdjacencyData(), dynamicPaint_prepareEffectStep(), dynamicPaint_setInitialColor(), dynamics_step(), foreach_grid_coordinate(), foreach_mouse_hit_key(), blender::bke::subdiv::foreach_subdiv_geometry(), get_vert2geom_distance(), lattice_deform_coords_impl(), lineart_build_edge_neighbor(), lineart_geometry_object_load(), lineart_main_transform_and_add_shadow(), blender::ed::sculpt_paint::load_tex(), blender::ed::sculpt_paint::load_tex_cursor(), meshdeformModifier_do(), modify_mesh(), non_recursive_bvh_div_nodes(), paint_2d_op(), PE_apply_lengths(), pe_deflect_emitter(), pe_iterate_lengths(), psys_cache_edit_paths(), shrinkwrap_calc_nearest_surface_point(), shrinkwrap_calc_nearest_vertex(), shrinkwrap_calc_normal_projection(), SimpleDeformModifier_do(), surfacedeformBind(), surfacedeformModifier_do(), surfaceGenerateGrid(), and TEST().

BLI_task_parallel_thread_id()

int BLI_task_parallel_thread_id

(

const TaskParallelTLS *

tls

)

Don't use this, store any thread specific data in tls->userdata_chunk instead. Only here for code to be removed.

Definition at line 139 of file task_range.cc.

References atomic_fetch_and_add_int32(), BLENDER_MAX_THREADS, and BLI_assert_msg.

Referenced by brush_add_count_iter(), blender::ed::sculpt_paint::calc_brush_texture_factors(), blender::ed::sculpt_paint::calc_brush_texture_factors(), and blender::ed::sculpt_paint::load_tex_task_cb_ex().

BLI_task_pool_cancel()

void BLI_task_pool_cancel

(

TaskPool *

pool

)

Cancel all tasks, keep worker threads running.

Definition at line 540 of file task_pool.cc.

References TaskPool::cancel().

Referenced by filelist_cache_previews_clear(), and blender::ed::vse::preview_startjob().

BLI_task_pool_create()

TaskPool * BLI_task_pool_create	(	void *	userdata,
		eTaskPriority	priority )

Regular task pool that immediately starts executing tasks as soon as they are pushed, either on the current or another thread.

Tasks will be executed as soon as they are added.

Definition at line 484 of file task_pool.cc.

References TASK_POOL_TBB.

Referenced by BKE_lib_override_library_main_operations_create(), BLI_task_parallel_mempool(), distribute_particles_on_dm(), do_sequence_proxy(), lineart_main_add_triangles(), lineart_main_load_geometries(), lineart_main_occlusion_begin(), blender::ed::vse::preview_startjob(), psys_cache_child_paths(), screen_opengl_render_init(), and start_prefetch_threads().

BLI_task_pool_create_background()

TaskPool * BLI_task_pool_create_background	(	void *	userdata,
		eTaskPriority	priority )

Background: always run tasks in a background thread, never immediately execute them. For running background jobs.

Definition at line 489 of file task_pool.cc.

References TASK_POOL_BACKGROUND.

Referenced by filelist_cache_preview_ensure_running(), blender::ed::sculpt_paint::undo::PositionUndoStorage::PositionUndoStorage(), and undomesh_from_editmesh().

BLI_task_pool_create_background_serial()

TaskPool * BLI_task_pool_create_background_serial	(	void *	userdata,
		eTaskPriority	priority )

Background Serial: run tasks one after the other in the background.

Executes one task after the other, possibly on different threads but never in parallel.

Definition at line 516 of file task_pool.cc.

References TASK_POOL_BACKGROUND_SERIAL.

Referenced by screen_opengl_render_init().

BLI_task_pool_create_no_threads()

TaskPool * BLI_task_pool_create_no_threads

(

void *

userdata

)

No threads: immediately executes tasks on the same thread. For debugging purposes.

Definition at line 511 of file task_pool.cc.

References TASK_POOL_NO_THREADS, and TASK_PRIORITY_HIGH.

BLI_task_pool_create_suspended()

TaskPool * BLI_task_pool_create_suspended	(	void *	userdata,
		eTaskPriority	priority )

Suspended: don't execute tasks until work_and_wait is called. This is slower as threads can't immediately start working. But it can be used if the data structures the threads operate on are not fully initialized until all tasks are created.

Definition at line 503 of file task_pool.cc.

References TASK_POOL_TBB_SUSPENDED.

Referenced by project_paint_op(), and TEST().

BLI_task_pool_current_canceled()

bool BLI_task_pool_current_canceled

(

TaskPool *

pool

)

For worker threads, test if current task pool canceled. this function may only be called from worker threads and pool must be the task pool that the thread is currently executing a task from.

Definition at line 545 of file task_pool.cc.

References TaskPool::current_canceled().

Referenced by blender::ed::vse::execute_read_sound_waveform_task(), and blender::gpu::VKDevice::submission_runner().

BLI_task_pool_free()

void BLI_task_pool_free

(

TaskPool *

pool

)

Definition at line 521 of file task_pool.cc.

Referenced by BKE_lib_override_library_main_operations_create(), BLI_task_parallel_mempool(), blender::deg::deg_evaluate_on_refresh(), distribute_particles_on_dm(), do_sequence_proxy(), filelist_cache_previews_free(), lineart_main_add_triangles(), lineart_main_load_geometries(), lineart_main_occlusion_begin(), blender::ed::vse::preview_startjob(), project_paint_op(), psys_cache_child_paths(), screen_opengl_render_end(), start_prefetch_threads(), TEST(), um_arraystore_free(), blender::fn::lazy_function::Executor::~Executor(), and blender::ed::sculpt_paint::undo::PositionUndoStorage::~PositionUndoStorage().

BLI_task_pool_push()

void BLI_task_pool_push	(	TaskPool *	pool,
		TaskRunFunction	run,
		void *	taskdata,
		bool	free_taskdata,
		TaskFreeFunction	freedata )

Definition at line 526 of file task_pool.cc.

References TaskPool::task_push().

Referenced by BKE_lib_override_library_main_operations_create(), BLI_task_parallel_mempool(), distribute_particles_on_dm(), do_sequence_proxy(), filelist_cache_previews_push(), lineart_main_add_triangles(), lineart_main_load_geometries(), lineart_main_occlusion_begin(), blender::ed::sculpt_paint::undo::PositionUndoStorage::PositionUndoStorage(), blender::ed::vse::preview_startjob(), project_paint_op(), psys_cache_child_paths(), schedule_write_result(), start_prefetch_threads(), TEST(), and undomesh_from_editmesh().

BLI_task_pool_user_data()

void * BLI_task_pool_user_data

(

TaskPool *

pool

)

Optional userdata pointer to pass along to run function.

Definition at line 550 of file task_pool.cc.

References TaskPool::userdata.

Referenced by filelist_cache_preview_runf(), lib_override_library_operations_create_cb(), parallel_mempool_func(), prefetch_task_func(), proxy_task_func(), blender::gpu::VKDevice::submission_runner(), and write_result().

BLI_task_pool_work_and_wait()

void BLI_task_pool_work_and_wait

(

TaskPool *

pool

)

Work and wait until all tasks are done.

Definition at line 535 of file task_pool.cc.

References TaskPool::work_and_wait().

Referenced by BKE_lib_override_library_main_operations_create(), BLI_task_parallel_mempool(), distribute_particles_on_dm(), do_sequence_proxy(), blender::ed::sculpt_paint::undo::PositionUndoStorage::ensure_compression_complete(), blender::fn::lazy_function::Executor::execute(), lineart_main_add_triangles(), lineart_main_load_geometries(), lineart_main_occlusion_begin(), blender::ed::vse::preview_startjob(), project_paint_op(), psys_cache_child_paths(), screen_opengl_render_end(), start_prefetch_threads(), TEST(), undomesh_free_data(), undomesh_from_editmesh(), undomesh_to_editmesh(), and blender::ed::sculpt_paint::undo::PositionUndoStorage::~PositionUndoStorage().

BLI_task_scheduler_exit()

void BLI_task_scheduler_exit

(

void

)

Definition at line 58 of file task_scheduler.cc.

Referenced by WM_exit_ex().

BLI_task_scheduler_init()

void BLI_task_scheduler_init

(

void

)

Definition at line 34 of file task_scheduler.cc.

References BLI_system_num_threads_override_get(), BLI_system_thread_count(), task_scheduler_num_threads, and threads_override_num.

Referenced by main(), and blender::fn::lazy_function::tests::TEST().

BLI_task_scheduler_num_threads()

int BLI_task_scheduler_num_threads

(

void

)

Definition at line 65 of file task_scheduler.cc.

References task_scheduler_num_threads.

Referenced by BLI_task_graph_edge_create(), BLI_task_graph_node_push_work(), BLI_task_parallel_mempool(), BLI_task_parallel_range(), do_sequence_proxy(), blender::threading::detail::memory_bandwidth_bound_task_impl(), start_prefetch_threads(), and TaskPool::TaskPool().