// TPUReplicatedInput and TPUReplicatedOutput respectively. For example, with
// two component devices, running `x = TPUReplicatedInput(inputs=[a, b])` on the
// parallel device creates a parallel tensor `x` with `a` on the first of
// `underlying_devices` and `b` on the second. Running `a_unpacked, b_unpacked =
// TPUReplicatedOutput(input=x, num_replicas=2)` un-packs the parallel tensor
// into its components.
//

  // Adds `value` to the existing value of the variable.
  void AssignAdd(TFE_Context* context, TFE_TensorHandle* value,
                 TF_Status* status);

 private:
  // Helper for running any single-argument assignment ops (Assign, AssignAdd,
  // AssignSub, ...).
  void GeneralAssignment(const char* op_name, TFE_Context* context,
                         TFE_TensorHandle* value, TF_Status* status);

TF_CAPI_EXPORT extern uint64_t TF_NowSeconds(void);

// Populates a TF_ThreadOptions struct with system-default values.
TF_CAPI_EXPORT extern void TF_DefaultThreadOptions(TF_ThreadOptions* options);

// Returns a new thread that is running work_func and is identified
// (for debugging/performance-analysis) by thread_name.
//
// The given param (which may be null) is passed to work_func when the thread