#include <ThreadedInferenceInterface.h>
template<typename X, typename... Args>
class ThreadedInferenceInterface< X, Args >
- Author
- piantado
- Date
- 07/06/20
◆ ThreadedInferenceInterface()
template<typename X, typename... Args>
◆ next_index()
template<typename X, typename... Args>
Return the next index to operate on (in a thread-safe way).
- Returns
◆ nthreads()
template<typename X, typename... Args>
How many threads are currently run in this interface?
- Returns
◆ run()
template<typename X, typename... Args>
Set up the multiple threads and actually run, calling run_thread_generator_wrapper.
- Parameters
-
- Returns
◆ run_thread()
template<typename X, typename... Args>
◆ run_thread_generator_wrapper()
template<typename X, typename... Args>
We have to wrap run_thread in something that manages the sync with main. This really just synchronizes the output of run_thread with run below. NOTE this makes a copy of x into the local next_x, so that when the thread keeps running, it doesn't mess anything up. We may in the future block the thread and return a reference, but its not clear that's faster.
- Parameters
-
◆ unthreaded_run()
template<typename X, typename... Args>
◆ __nrunning
template<typename X, typename... Args>
◆ __nthreads
template<typename X, typename... Args>
◆ index
template<typename X, typename... Args>
◆ to_yield
template<typename X, typename... Args>
The documentation for this class was generated from the following file: