TensorHandlePtr combined_value = CreatePerDeviceValues(
      context.get(), in_components, device_name, status.get());
  ASSERT_TRUE(TF_GetCode(status.get()) == TF_OK) << TF_Message(status.get());

  // Loop to make synchronization failures more deterministic
  for (int i = 0; i < 100; ++i) {
    TensorHandlePtr multiply_result(
        Multiply(context.get(), combined_value.get(), combined_value.get(),
                 status.get()));

                                const char* attr_name, const void* proto,
                                size_t proto_len, TF_Status* status) {
  // shape.ParseFromArray takes an int as length, this function takes size_t,
  // make sure there is no information loss.
  if (proto_len > std::numeric_limits<int>::max()) {
    status->status = InvalidArgument(
        "proto_len (", proto_len,

    int64_t target_id = target_tensor_ids[i];
    if (sources_set.find(target_id) != sources_set.end()) {
      auto tensor = targets[i];
      sources_that_are_targets.insert(
          std::make_pair(target_id, TapeTensor(tensor)));
    }
  }

  TF_RETURN_IF_ERROR(GradientTape::ComputeGradient(
      vspace, target_tensor_ids, source_tensor_ids, sources_that_are_targets,

  CHECK_OK(buffer.status());

  return new PJRT_Buffer{std::move(*buffer), c_api_client->pjrt_c_client()};
}

TEST(TensorPjRtBufferUtilTest, GetPjRtCBufferFromTensorNoBuffer) {
  auto allocator = std::make_unique<AsyncValueAllocator>();
  tensorflow::Tensor tensor(allocator.get(), DT_FLOAT, {1});

  EXPECT_THAT(
      GetPjRtCBufferFromTensor(&tensor),
      StatusIs(error::INTERNAL, HasSubstr(absl::StrCat(

  TFE_TensorHandle* t = TFE_TensorHandleCopyToDevice(
      tensor, context, dev->underlying_device.c_str(), status);
  if (TF_GetCode(status) != TF_OK) return nullptr;
  auto dst = std::make_unique<LoggedTensor>(t);
  *(dev->arrived_flag) = true;
  return MakeLoggedTensorHandle(context, dev->device_name, std::move(dst),
                                status);
}

  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);

  // Add a sync point to make sure that variables have been initialized
  // before the function execution starts.
  TFE_ContextAsyncWait(ctx, status);
  EXPECT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);

  int num_retvals = 1;
  std::vector<AbstractTensorHandle*> outputs(1);
  GradientRegistry registry;
  s = RegisterGradients(&registry);
  ASSERT_EQ(errors::OK, s.code()) << s.message();
  auto tape = std::make_unique<Tape>(/*persistent=*/false);
  s = Execute(check_numerics_op.get(), ctx.get(), absl::MakeSpan(outputs),
              &num_retvals, &forward_op, tape.get(), registry);
  ASSERT_EQ(errors::OK, s.code()) << s.message();

ParallelDevice::ParallelDevice(const std::vector<std::string>& devices,
                               bool is_async, int in_flight_nodes_limit)
    : underlying_devices_(devices),
      default_cancellation_manager_(absl::make_unique<CancellationManager>()) {
  device_threads_.reserve(devices.size());
  for (int device_index = 0; device_index < devices.size(); ++device_index) {
    device_threads_.emplace_back(new DeviceThread(

  TFE_OpSetAttrString(op.get(), "container", "", 0);
  // Use the special GUID for no buffer sharing
  //
  // TODO(allenl): Should we provide a better API for this? AFAIK this is the
  // only reasonable way to make variables with no aliasing using the eager C
  // API.
  std::string no_sharing = "cd2c89b7-88b7-44c8-ad83-06c2a9158347";
  TFE_OpSetAttrString(op.get(), "shared_name", no_sharing.c_str(),

}

// Converts `ninputs` and `inputs` into `inputs_tensors` and `input_nodes` and
// does various checks while doing so. `input_nodes` will contain the same
// information as input_tensors just in a different structure to make
// following processing easier. TODO(iga): Simplify this nested structure.
Status ProcessInputs(
    const TF_Graph* fn_body, const char* fn_name, int ninputs,
    const TF_Output* inputs, std::vector<OutputTensor>* input_tensors,