const float X = 3.0f, Y = 7.0f;
  TF_Operation* x = Placeholder(graph_, s_, "x", TF_FLOAT);
  TF_Operation* y = Placeholder(graph_, s_, "y", TF_FLOAT);
  TF_Operation* xy = Mul(x, y, graph_, s_, "xy");
  TF_Output dxy_dx, dxy_dy;

  TF_Output outputs[1] = {{xy, 0}};
  TF_Output inputs[1] = {{x, 0}};
  TF_AddGradients(graph_, outputs, 1, inputs, 1, nullptr, s_, &dxy_dx);
  ASSERT_EQ(TF_OK, TF_GetCode(s_)) << TF_Message(s_);

        'device at: https://developer.nvidia.com/cuda-gpus. Each capability '
        'can be specified as "x.y" or "compute_xy" to include both virtual and'
        ' binary GPU code, or as "sm_xy" to only include the binary '
        'code.\nPlease note that each additional compute capability '
        'significantly increases your build time and binary size, and that '

# Select supported compute capabilities (supported graphics cards).
# This is the same as the official TensorFlow builds.
# See https://developer.nvidia.com/cuda-gpus#compute
# `compute_XY` enables PTX embedding in addition to SASS. PTX
# is forward compatible beyond the current compute capability major
# release while SASS is only forward compatible inside the current