TF_CAPI_EXPORT extern void TFE_ContextAsyncWait(TFE_Context* ctx,
                                                TF_Status* status);

// This function will block till the operation that produces `h` has
// completed. This is only valid on local TFE_TensorHandles. The pointer
// returned will be on the device in which the TFE_TensorHandle resides (so e.g.
// for a GPU tensor this will return a pointer to GPU memory). The pointer is

  // Copy the tensor to the right device but log a warning.
  DEVICE_PLACEMENT_WARN = 1,
  // Silently copy the tensor, which has a performance cost since the operation
  // will be blocked till the copy completes. This is the default policy.
  DEVICE_PLACEMENT_SILENT = 2,
  // Placement policy which silently copies int32 tensors but not other dtypes.
  DEVICE_PLACEMENT_SILENT_FOR_INT32 = 3,
};