| /oneTBB/doc/main/tbb_userguide/ |
| H A D | use_limiter_node.rst | 27 the example below, an ``input_node`` will generate ``M`` big objects. But the
28 user wants to allow at most three big objects to reach the ``function_node``
30 objects at once.
76 objects at once. The ``limiter_node`` has a threshold of 3, and will
84 again. So in this example, at most four big objects exist at a time, the
|
| H A D | create_token_based_system.rst | 48 objects and a ``buffer_node`` that is pre-filled with three tokens. The
112 like in the previous sections, there will be at most four big objects in
113 the graph. There could be three big objects in the ``function_node`` and one
118 use any type for a token, including objects or pointers to arrays.
122 above to use the big objects themselves as the tokens, removing the need
124 free list of big objects using a cycle back to the ``buffer_node``.
|
| H A D | use_concurrency_limits.rst | 29 For example, you can control the number of big objects in flight in a
69 The ``function_node`` will operate on at most three big objects
76 messages from the ``input_node``. At most four big objects will exist
|
| H A D | Cancellation_and_Nested_Parallelism.rst | 13 by creating ``task`` objects that execute the snippets of code that you
14 supply to the algorithm template. By default, these ``task`` objects are
17 objects. Cancelling a ``task_group_context`` cancels all of its child
18 ``task_group_context`` objects, and transitively all its descendants.
|
| H A D | Dependence_Graph.rst | 7 In a dependence graph, the nodes invoke body objects to perform
10 execute the body objects when it is legal to do so according to the
60 To implement this as a flow graph, continue_node objects are used for
61 the nodes and continue_msg objects as the messages. A continue_node
|
| H A D | cancelling_nested_parallelism.rst | 19 objects. If you do not provide an explicit task_group_context to a flow
|
| H A D | std_invoke.rst | 6 Starting from C++17, the requirements for callable objects passed to algorithms or Flow Graph nodes…
10 …lable <https://en.cppreference.com/w/cpp/named_req/Callable>`_) that covers three types of objects:
14 * **Pointers to member objects** work as the body of the algorithm or parallel construct
115 …template that provides a syntax for invoking different types of callable objects with a set of arg…
|
| H A D | use_input_node.rst | 28 All ``input_node`` objects are constructed in the inactive state and usually
55 In general it is safest to create your ``input_node`` objects in the inactive
|
| H A D | avoiding_data_races.rst | 9 on ``function_node`` and ``multifunction_node`` objects limit the maximum number
|
| H A D | Containers.rst | 44 As with most objects in C++, the constructor or destructor of a
|
| H A D | Non-Linear_Pipelines.rst | 44 handle objects that don’t need to be acted upon by the filter other than
|
| H A D | Memory_Allocation.rst | 36 a separate cache line. Two objects allocated by
|
| H A D | Advanced_Topic_Other_Kinds_of_Iteration_Spaces.rst | 9 You can use |full_name| to define your own iteration space objects. The object
|
| H A D | Mutex_Flavors.rst | 50 among many ``spin_mutex`` objects, you can improve performance over
|
| H A D | parallel_reduce.rst | 114 shared with other objects, it should use an atomic increment.
|
| H A D | Predefined_Node_Types.rst | 31 …c output type. It executes a user body when it receives N continue_msg objects at its input. N i…
|
| H A D | Working_on_the_Assembly_Line_pipeline.rst | 107 ``TextSlice`` objects are passed between filters using pointers to avoid
|
| /oneTBB/test/tbbmalloc/ |
| H A D | test_malloc_whitebox.cpp | 938 std::list<uintptr_t> objects; member in CacheBinModel
952 while (!objects.empty() && (intptr_t)(currTime - objects.front()) > threshold) { in doCleanup()
954 cacheBinModel.lastCleanedAge = objects.front(); in doCleanup()
955 objects.pop_front(); in doCleanup()
958 … cacheBinModel.oldest.store(objects.empty() ? 0 : objects.front(), std::memory_order_relaxed); in doCleanup()
974 if ( objects.empty() ) { in get()
986 uintptr_t obj_age = objects.back(); in get()
987 objects.pop_back(); in get()
988 if (objects.empty()) cacheBinModel.oldest.store(0, std::memory_order_relaxed); in get()
1020 if (objects.empty()) in putList()
[all …]
|
| /oneTBB/examples/parallel_for/tachyon/src/ |
| H A D | grid.hpp | 74 object *objects; /* all objects contained in the grid */ member
|
| H A D | grid.cpp | 134 free_objects(g->objects); in grid_free()
374 g->nextobj = gold->objects; in engrid_cell()
375 gold->objects = (object *)g; in engrid_cell()
425 obj->nextobj = g->objects; in engrid_object()
426 g->objects = obj; in engrid_object()
|
| /oneTBB/doc/main/tbb_userguide/design_patterns/ |
| H A D | Reduction.rst | 56 Use ``oneapi::tbb::parallel_reduce`` when the objects are inexpensive to
115 good solution when ``T`` objects are expensive to construct.
|
| H A D | Non-Preemptive_Priorities.rst | 166 ``RunWorkItem`` objects are fungible. They enable the oneTBB
|
| H A D | Local_Serializer.rst | 22 between different objects.
|
| /oneTBB/examples/graph/cholesky/ |
| H A D | README.md | 8 …aph. This version uses a dependency graph made solely of `continue_node` objects. This an inspecto…
|
| /oneTBB/doc/main/reference/ |
| H A D | concurrent_lru_cache_cls.rst | 26 Once there are no ``handle`` objects holding reference to an item, it is considered unused.
|