}

  // Takes a description of a single operation being executed on the
  // ParallelDevice, and in turn runs one operation per component device with
  // its corresponding inputs from the input ParallelTensors. Wraps the
  // resulting per-device and per-output TFE_TensorHandles into one
  // ParallelTensor per output of the original operation.
  //
  // Attributes are forwarded to executed operations unmodified.
  //

        - Documentation Bug
        - Others
    validations:
      required: true
  - type: markdown
    attributes:
      value: |
        Please make sure that this is a bug. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub.

  - type: dropdown
    id: tf-nightly

//    "/job:localhost/replica:0/task:0/device:GPU:1"}
// Then executing an operation on CUSTOM:0 will execute it on GPU:0 and GPU:1.
//
// Implicit copies onto `device_name` are allowed, replicating the value once
// per device in `underlying_devices`. Implicit copies off of the device throw
// an error.
//
// All component tensors must have the same dtype. Currently they must also have

  // or consider other ways of packing/unpacking parallel tensors.
  if (operation_name == std::string("TPUReplicatedInput")) {
    // Special-cased operation for packing per-device tensors into one parallel
    // tensor.
    if (inputs.size() != parallel_device.num_underlying_devices()) {
      std::string message(absl::StrCat(
          "The parallel device ", parallel_device_name, " expected ",

  const char task1_name[] = "/job:localhost/replica:0/task:1/device:CPU:0";
  const char task2_name[] = "/job:localhost/replica:0/task:2/device:CPU:0";

  // Create one variable per task.
  TFE_TensorHandle* h0 = TestVariable(ctx, 1.0, task1_name);
  TFE_TensorHandle* h1 = TestVariable(ctx, 2.0, task2_name);
  TFE_TensorHandle* h2 = TestVariable(ctx, 3.0, task0_name);

TF_CAPI_EXPORT extern void TF_AddInputList(TF_OperationDescription* desc,
                                           const TF_Output* inputs,
                                           int num_inputs);

// Call once per control input to `desc`.
TF_CAPI_EXPORT extern void TF_AddControlInput(TF_OperationDescription* desc,
                                              TF_Operation* input);