Function GetDriverExecutor

tensorflow/stream_executor/rocm/rocm_driver.cc:127–131

ROCM driver routines may require a large amount of stack (particularly hipModuleLoadDataEx, in our experience). To avoid stack overflow when using stack-limited threads (such as those spawned by a default-argument thread::ThreadPool on some platforms), we run certain routines in this pool and wait for completion.

// thread::ThreadPool on some platforms), we run certain routines in this pool
// and wait for completion.
port::ThreadPool* GetDriverExecutor() {
  static port::ThreadPool* thread_pool = new port::ThreadPool(
      port::Env::Default(), port::ThreadOptions(), "rocm_driver", 1);
  return thread_pool;
}

}  // namespace