Visible to Intel only — GUID: GUID-E23B3A4E-021A-4EE6-ABB4-E1C1446FD46D
Package Contents
Parallelizing Simple Loops
Parallelizing Complex Loops
Parallelizing Data Flow and Dependence Graphs
Work Isolation
Exceptions and Cancellation
Floating-point Settings
Containers
Mutual Exclusion
Timing
Memory Allocation
The Task Scheduler
Design Patterns
Migrating from Threading Building Blocks (TBB)
Constrained APIs
Appendix A Costs of Time Slicing
Appendix B Mixing With Other Threading Packages
References
parallel_for_each Body semantics and requirements
parallel_sort ranges interface extension
TBB_malloc_replacement_log Function
Type-specified message keys for join_node
Scalable Memory Pools
Helper Functions for Expressing Graphs
concurrent_lru_cache
task_group extensions
The customizing mutex type for concurrent_hash_map
Visible to Intel only — GUID: GUID-E23B3A4E-021A-4EE6-ABB4-E1C1446FD46D
task_arena::constraints extensions
NOTE:
To enable this feature, set the TBB_PREVIEW_TASK_ARENA_CONSTRAINTS_EXTENSION macro to 1.
Description
These extensions allow to customize tbb::task_arena::constraints with the following properties:
On machines with Intel® Hybrid Technology set the preferred core type for threads working within the task arena.
Limit the maximum number of threads that can be scheduled to one core simultaneously.
API
Header
#include <oneapi/tbb/task_arena.h>
Synopsis
namespace oneapi {
namespace tbb {
class task_arena {
public:
struct constraints {
constraints& set_numa_id(numa_node_id id);
constraints& set_max_concurrency(int maximal_concurrency);
constraints& set_core_type(core_type_id id);
constraints& set_max_threads_per_core(int threads_number);
numa_node_id numa_id = task_arena::automatic;
int max_concurrency = task_arena::automatic;
core_type_id core_type = task_arena::automatic;
int max_threads_per_core = task_arena::automatic;
}; // struct constraints
}; // class task_arena
} // namespace tbb
} // namespace oneapi
Member Functions
constraints&set_numa_id(numa_node_idid)
Sets the numa_id field to the id.
Returns: Reference to *this.
constraints&set_max_concurrency(intmaximal_concurrency)
Sets the max_concurrency field to the maximal_concurrency.
Returns: Reference to *this.
constraints&set_core_type(core_type_idid)
Sets the core_type field to the id.
Returns: Reference to *this.
constraints&set_max_threads_per_core(intthreads_number)
Sets the max_threads_per_core field to the threads_number.
Returns: Reference to *this.
Member Objects
numa_node_idnuma_id
An integral logical index uniquely identifying a NUMA node. All threads joining the task_arena are bound to this NUMA node.
NOTE:
To obtain a valid NUMA node ID, call oneapi::tbb::info::numa_nodes().
intmax_concurrency
The maximum number of threads that can participate in work processing within the task_arena at the same time.
core_type_idcore_type
An integral logical index uniquely identifying a core type. All threads joining the task_arena are bound to this core type.
NOTE:
To obtain a valid core type node ID, call oneapi::tbb::info::core_types().
intmax_threads_per_core
The maximum number of threads that can be scheduled to one core simultaneously.
See also: