debug environment can be used along with an output stream such as std::cout in order to dump a GraphViz representation of the dependence graph in an output stream. Remember, in the cases that a dynamic (conditional ) dependence graphs such as do_while is used, you have to use this along with a real execution environment such as taskgraph_env
More...
|
|
| graphviz_env (std::string const &name) |
| |
| template<bool isResult, typename WF , typename Mapper , typename... In> |
| void | spawn_element (std::size_t tid, std::size_t result_id, WF &&wf, Mapper &&mapper, std::size_t num_succs, In &&... in) const |
| | Every spawn_element is converted to a node in the GraphViz output. The label for this node is in the format of tid(num_succs). There is also a color representation which is associated with each task. This color changes based on the location id of each task. This is useful when the load balancing of an algorithm should be checked. Remember that this shows the load of each processor during the task creation process and does not necessarily represent the execution load balance. More...
|
| |
|
template<bool isResult, typename WF , typename Mapper , typename... In> |
| void | spawn_element (std::size_t tid, std::size_t result_id, std::vector< std::size_t > const ¬ifications, WF &&wf, Mapper &&mapper, std::size_t num_succs, In &&... in) const |
| |
|
template<typename Skeleton , typename... Arg> |
| void | pre_spawn (Skeleton &&skeleton, std::size_t lid_offset, Arg &&...) |
| |
|
template<typename Skeleton , typename... Args> |
| void | post_spawn (Skeleton &&skeleton, Args &&... args) |
| |
|
void | set_num_succs (std::size_t tid, std::size_t num_succs) const |
| |
|
void | init_location_info (std::size_t num_PEs, runtime::location_id PE_id) |
| |
|
std::size_t | get_num_PEs () const |
| |
|
runtime::location_id | get_PE_id () const |
| |
|
|
static void | output_graph (graph_type *graph, std::ostream &o) |
| |
debug environment can be used along with an output stream such as std::cout in order to dump a GraphViz representation of the dependence graph in an output stream. Remember, in the cases that a dynamic (conditional ) dependence graphs such as do_while is used, you have to use this along with a real execution environment such as taskgraph_env
- See also
- do_while
-
taskgraph_env
◆ spawn_element()
template<bool isResult, typename WF , typename Mapper , typename... In>
| void stapl::skeletons::graphviz_env::spawn_element |
( |
std::size_t |
tid, |
|
|
std::size_t |
result_id, |
|
|
WF && |
wf, |
|
|
Mapper && |
mapper, |
|
|
std::size_t |
num_succs, |
|
|
In &&... |
in |
|
) |
| const |
Every spawn_element is converted to a node in the GraphViz output. The label for this node is in the format of tid(num_succs). There is also a color representation which is associated with each task. This color changes based on the location id of each task. This is useful when the load balancing of an algorithm should be checked. Remember that this shows the load of each processor during the task creation process and does not necessarily represent the execution load balance.
- Parameters
-
| tid | the unique id assigned to the node in the graph |
| result_id | result_id of this task if it has one |
| wf | the workfunction is discarded in here |
| mapper | the output to output mapper for mapping the results |
| num_succs | the exact number of successors for this element. Remember that in some cases this value is set to stapl::defer_specs (when the spawner is in SET_HOLD mode). This number is shown in parenthesis in the output graph. |
| in | the producer information for the node's input arguments that will be translated as edge in the output graph |
The documentation for this class was generated from the following file:
1.8.13