Range(&vals, 0, num_dims_out);
    AbstractTensorHandle* sum_dims_raw = nullptr;
    TF_RETURN_IF_ERROR(TestTensorHandleWithDims<int32_t, TF_INT32>(
        ctx, vals.data(), vals_shape, 1, &sum_dims_raw));
    sum_dims.reset(sum_dims_raw);
  }

  // Reduce sum the output on all dimensions.
  TF_RETURN_IF_ERROR(ops::Sum(ctx, model_out.get(), sum_dims.get(), &outputs[0],
                              /*keep_dims=*/false, "sum_output"));

      finished_execute_.wait(l);
    }
    if (TF_GetCode(status_.get()) != TF_OK) {
      TF_SetStatus(status, TF_GetCode(status_.get()),
                   TF_Message(status_.get()));
      // Reset the member `status_` so future op executions (after recovery from
      // the bad `status`) start with an OK status.
      TF_SetStatus(status_.get(), TF_OK, "");
    }
    cancellation_manager_ = nullptr;

    ASSERT_EQ(errors::OK, s.code()) << s.message();
    ctx.reset(ctx_raw);
  }

  AbstractTensorHandlePtr x;
  {
    AbstractTensorHandle* x_raw = nullptr;
    Status s = TestScalarTensorHandle<float, TF_FLOAT>(ctx.get(), 2.0f, &x_raw);
    ASSERT_EQ(errors::OK, s.code()) << s.message();
    x.reset(x_raw);
  }

  Status s = RunModel(TestScalarShape, ctx.get(),

    ASSERT_EQ(errors::OK, s.code()) << s.message();
    x.reset(x_raw);
  }

  AbstractTensorHandlePtr y;
  {
    AbstractTensorHandle* y_raw = nullptr;
    Status s =
        TestScalarTensorHandle<float, TF_FLOAT>(ctx_.get(), 7.0f, &y_raw);
    ASSERT_EQ(errors::OK, s.code()) << s.message();
    y.reset(y_raw);
  }

  float expected_dx[1] = {7.0f};

  int num_retvals = num_replicas;
  TFE_Execute(op.get(), result_handles, &num_retvals, status);
  if (TF_GetCode(status) != TF_OK) return;
  for (int i = 0; i < num_replicas; ++i) {
    (*components)[i].reset(result_handles[i]);
  }
}

TensorHandlePtr Multiply(TFE_Context* context, TFE_TensorHandle* first,
                         TFE_TensorHandle* second, TF_Status* status) {

            opaque_plugin_resource, plugin_resource_name, delete_func);
        return tensorflow::OkStatus();
      });

  if (cc_status.ok()) {
    tf_plugin_resource_ptr.reset(tf_plugin_resource);
    *result_plugin_resource = tf_plugin_resource_ptr->GetOpaquePluginResource();
  } else {
    *result_plugin_resource = nullptr;
  }
  status->status = cc_status;
}

    var_to_data_type_map_.swap(result.second);
  } else {
    reader_.reset(new TensorSliceReader(filename));
    if (!reader_->status().ok()) {
      tsl::Set_TF_Status_from_Status(status, reader_->status());
      return;
    }
    var_to_shape_map_.reset(
        new TensorSliceReader::VarToShapeMap(reader_->GetVariableToShapeMap()));
    var_to_data_type_map_.reset(new TensorSliceReader::VarToDataTypeMap(

      status_ =
          BuildImmediateExecutionContext(std::get<1>(GetParam()), &ctx_raw);
      ASSERT_EQ(errors::OK, status_.code()) << status_.message();
      immediate_execution_ctx_.reset(ctx_raw);
    }

    // Computing numerical gradients with TensorFloat-32 is numerically
    // unstable. Some forward pass tests also fail with TensorFloat-32 due to
    // low tolerances

 public:
  explicit GraphOperation(TF_Graph* g) : TracingOperation(kGraph), g_(g) {}
  void Release() override { delete this; }
  Status Reset(const char* op, const char* raw_device_name) override {
    if (op_) {
      return errors::FailedPrecondition("Reset called on already built op.");
    }
    if (raw_device_name) {
      device_name_ = raw_device_name;
    }
    op_type_ = op;

                             ->Finalize(&output_list, &func));
      scoped_func.reset(func);
      for (auto output : output_list.outputs) {
        output->Unref();
      }
      TF_RETURN_IF_ERROR(ctx->RegisterFunction(func));
    }

    AbstractOperationPtr fn_op(ctx->CreateOperation());
    TF_RETURN_IF_ERROR(fn_op->Reset(fn_name, /*raw_device_name=*/nullptr));
    for (auto input : inputs) {