| /oneTBB/doc/main/reference/scalable_memory_pools/ |
| H A D | memory_pool_cls.rst | 9 A class template for scalable memory allocation from memory blocks provided by an underlying alloca…
19 The memory is obtained as big chunks from an underlying allocator specified by the template
20 argument. The latter must satisfy the subset of the allocator requirements from the [allocator.requ…
65 … memory pool with an instance of underlying memory allocator of type ``Alloc`` copied from ``src``.
71 The code below provides a simple example of allocation from an extensible memory pool.
|
| /oneTBB/doc/main/tbb_userguide/ |
| H A D | Flow_Graph_Message_Passing_Protocol.rst | 9 message from its predecessor. For a graph to operate most-efficiently,
13 not reverse from push to pull, the predecessor node would have to
19 try to pull a message from a predecessor.
25 switch from pull to push mode.
|
| H A D | Flow_Graph_Reservation.rst | 12 messages from its inputs until it has a message at each input. To create
54 output edge from push to pull mode. ``broadcast_nodes`` do not buffer
120 and the arc from ``bn`` to ``jn`` reverses. Because neither bn nor jn
149 value and the arc from ``buf1`` to ``jn`` reverses. Because not all the
171 value and the arc from ``buf2`` to ``jn`` reverses. Now both inputs of
172 ``jn`` have predecessors, a task to build and forward a message from
212 colored grey.) ``jn`` receives the value 3 from ``buf1``, but it
213 remains in ``buf1`` (in case the attempt to forward a message from
216 value 4 from ``buf2``, but it remains in ``buf2``.
236 - No attempt to pull from ``bn`` is made, because the edge from ``bn``
|
| H A D | create_token_based_system.rst | 11 is retired from the graph, its token is released, and can be paired with
39 first reserve an input on each port from an upstream source. If it
51 The ``input_node`` will only generate an input when one is pulled from it
53 the input from the ``input_node`` when it knows there is also an item to
54 pull from the ``buffer_node``.
111 to be recycled and paired with another input from the ``input_node``. So
139 the token to be of any type and to inject or remove tokens from the
|
| H A D | Advanced_Example.rst | 15 float value_of_min = FLT_MAX; // FLT_MAX from <climits>
62 value_of_min(FLT_MAX), // FLT_MAX from <climits>
77 value_of_min(FLT_MAX), // FLT_MAX from <climits>
|
| H A D | Reader_Writer_Mutexes.rst | 11 *reader locks* from *writer locks.* There can be more than one reader
15 Requests for a reader lock are distinguished from requests for a writer
|
| H A D | Mapping_Nodes2Tasks.rst | 17 from the work pool.
32 As each task from n finishes, it puts its output to m, since m is a
47 used to execute tasks from the oneTBB work pool while it is waiting.
|
| H A D | Data_Flow_Graph.rst | 14 integer values from 1 to 10 and passes them to two successor nodes. One
17 the result downstream. The right-most node receives values from both of
20 will be equal to the sum of the sequence of squares and cubes from 1 to
81 node F from **Simple Data Flow Graph** above is implemented as a loop
189 This final implementation has all of the nodes and edges from the
|
| H A D | Concurrent_Queue_Classes.rst | 9 push and pop elements from the queue. The queue is unbounded and has no
34 thread safe if there were other threads also popping from the same
36 before another thread snatches the last item from ``MySerialQueue``.
100 elsewhere in your program that prevents the queue from becoming too
|
| H A D | use_limiter_node.rst | 29 at a time, and to prevent the ``input_node`` from generating all ``M`` big
75 The example above prevents the ``input_node`` from generating all ``M`` big
83 drops below the threshold, messages begin flowing from the ``input_node``
|
| H A D | destroy_graphs_outside_main_thread.rst | 12 not want to call a wait_for_all in the example from :ref:`always_use_wait_for_all`,
42 need to use some mechanism to signal from the enqueued task that the
|
| H A D | work_isolation.rst | 13 construct, a thread can obtain a task from the outer-level construct
81 // from taking tasks of the outer parallel_for.
99 thread is prohibited from executing any outer level tasks or tasks
131 // from taking tasks related to the outer parallel loop.
|
| H A D | Edges.rst | 41 an edge from ``n`` to ``m``. The node ``n`` is created with unlimited concurrency,
44 Because there is an edge from ``n`` to ``m``, each value ``v``, returned by ``n``, will
|
| /oneTBB/examples/parallel_for/polygon_overlay/ |
| H A D | README.md | 8 …on, by splitting list of polygons from one map and intersecting each sub-list against the entire l…
9 …from the other map. This solution requires some redundancy (some polygons are members of more than…
11 …ch solution is that the area of the generated sub-polygons are subtracted from the original area o…
13 …re(TM) Duo processor got a speedup of about 20 percent over serial.) This results from two effects:
17 …dant polygons being compared; this effect would eventually swamp the gain from comparing smaller n…
19 Running the default release pover while varying the number of submaps from 1 to 1000, the speedup o…
|
| /oneTBB/doc/main/tbb_userguide/design_patterns/ |
| H A D | Local_Serializer.rst | 50 another item from the FIFO and put it in flight.
107 Constraints on a given functor are resolved from top to bottom in the
127 A ``SerializedWorkItem`` is derived from a ``WorkItem``, which serves
166 completely hidden from the base class, thus permitting the framework
168 ``SerializedWorkItem`` is essentially ``ConcreteWorkItem`` from the
187 Step 3 is the difference from the operation of ConcreteWorkItem::run.
204 void moveOneItemToReadyPile() { // Transfer item from queue to ReadyPile
237 - If method ``add`` increments ``count`` from 0 to 1, this indicates
242 - If method ``noteCompletion`` decrements count and it is *not* from
|
| H A D | GUI_Thread.rst | 68 distinct from the calling thread.
89 // Event posted from enqueued task when it finishes its work.
93 // Queue for transmitting results from enqueued task to GUI thread.
152 item from ResultQueue into CurrentResult. The ``try_pop`` always
199 thread can pop from ``ResultQueue`` into a temporary variable, check
|
| H A D | Fenced_Data_Transfer.rst | 30 that preserves the order of a thread's operation from its viewpoint,
87 Change the flag from ``bool`` to ``std::atomic<bool>`` for the flag
114 write. A read from ``std::atomic`` value has *acquire* semantics,
160 does not read individual values from main memory. It reads cache
|
| /oneTBB/examples/parallel_for/polygon_overlay/gui/ |
| H A D | polygon_overlay.rc | 8 // Generated from the TEXTINCLUDE 2 resource.
55 // Generated from the TEXTINCLUDE 3 resource.
|
| /oneTBB/examples/parallel_for/tachyon/gui/ |
| H A D | tachyon.rc | 8 // Generated from the TEXTINCLUDE 2 resource.
84 // Generated from the TEXTINCLUDE 3 resource.
|
| /oneTBB/examples/task_arena/fractal/gui/ |
| H A D | fractal.rc | 8 // Generated from the TEXTINCLUDE 2 resource.
84 // Generated from the TEXTINCLUDE 3 resource.
|
| /oneTBB/doc/main/reference/ |
| H A D | parallel_for_each_semantics.rst | 50 If the ``iterator`` satisfies `Input iterator` named requirements from [input.iterators] ISO C++ St…
51 `Forward iterator` named requirements from [forward.iterators] ISO C++ Standard section, ``tbb::par…
59 If the ``iterator`` satisfies `Forward iterator` named requirements from [forward.iterators] ISO C+…
|
| H A D | scalable_memory_pools.rst | 9 Memory pools allocate and free memory from a specified region or an underlying allocator using
25 - Returns a pointer to ``n`` bytes allocated from the memory pool.
|
| /oneTBB/include/oneapi/tbb/detail/ |
| H A D | _flow_graph_item_buffer_impl.h | 95 void move_item(size_t to, size_t from) { in move_item() argument
97 __TBB_ASSERT(my_item_valid(from), "Trying to move from an empty slot"); in move_item()
98 set_my_item(to, get_my_item(from)); // could have std::move semantics in move_item()
99 destroy_item(from); in move_item()
|
| /oneTBB/doc/main/intro/ |
| H A D | notation.rst | 29 …- Braces and vertical bars indicate the choice of one item from a selection of two or more …
91 from the informal declaration:
97 - Method ``x()`` is inherited from a protected base class.
|
| /oneTBB/examples/concurrent_priority_queue/shortpath/ |
| H A D | README.md | 6 …from serial `A*` in that it needs to add nodes back to the open set when the `g` estimate (shortes…
|