_test_gpu$
_test_gpu.py$
_test_lib$
//tensorflow/cc/saved_model:saved_model_test_files
//tensorflow/cc/saved_model:saved_model_half_plus_two
//tensorflow:no_tensorflow_py_deps
//tensorflow/tools/pip_package:win_pip_package_marker
//tensorflow/core:image_testdata
//tensorflow/core/kernels/cloud:bigquery_reader_ops
//tensorflow/python:extra_py_tests_deps
//tensorflow/python:mixed_precision
//tensorflow/python:tf_optimizer

  // caller of event_mgr->ThenExecute() blocks on the completion of the callback
  // (as in the case of ConstOp kernel creation on GPU, which involves copying a
  // CPU tensor to GPU).
  // Setting a larger thread pool does not help with the Swift caller, as we use
  // a different TFE context for each thread of execution (for running graph
  // functions, and their send/recvs corountines).