namespace parallel_device {

// Allocate a parallel device named `device_name` which forwards operations to
// `underlying_devices`, maintaining "parallel tensors" with components placed
// on each underlying device.
//
// For example if `device_name` is
//   "/job:localhost/replica:0/task:0/device:CUSTOM:0"
// and `underlying_devices` is
//   {"/job:localhost/replica:0/task:0/device:GPU:0",
//    "/job:localhost/replica:0/task:0/device:GPU:1"}

  const char* device_name = "/job:localhost/replica:0/task:0/device:CUSTOM:0";
  std::array<const char*, 2> underlying_devices{first_device, second_device};
  RegisterParallelDevice(context.get(), device_name, underlying_devices,
                         status.get());
  ASSERT_TRUE(TF_GetCode(status.get()) == TF_OK) << TF_Message(status.get());

#include "tensorflow/c/tf_status.h"
#include "tensorflow/core/lib/gtl/cleanup.h"
#include "tensorflow/core/platform/test.h"

namespace {

struct LoggingDevice {
  tensorflow::string device_name;
  tensorflow::string underlying_device;
  // Set to true whenever a TensorHandle is copied onto the device
  bool* arrived_flag;
  // Set to true whenever an operation is executed
  bool* executed_flag;