/*input_tensors*/ {},
                    /*expected_shape*/ make_shape({kUnknownDim, kUnknownDim}));

  TFE_DeleteOp(matmul_op);
  // TODO(bgogul): Add some death tests where status is not OK.
}

TEST_F(ShapeInferenceTest, InfersShapesFromInputTensors) {
  // Prepare some tensors for shape.
  TF_Tensor* tensor_1X6 = Int32Tensor({1, 6});

to a banned CUDA dependency when '--define framework_shared_object=false' is set.
This means that a CUDA target was probably included via an is_static condition,
used when targeting platforms like Windows where we build statically instead
of dynamically. Here's the output from bazel query:
EOF
  cat $BATS_TEST_TMPDIR/out
  [[ ! -s $BATS_TEST_TMPDIR/out ]]
}

@test "All tensorflow.org/code links point to real files" {

  // Returns true if `Accumulate` is active somewhere above on the stack and
  // there isn't an intervening PushState. This is useful for ordering
  // ForwardAccumulators, where more deeply nested accumulators should not see
  // computations from less deeply nested accumulators.
  bool BusyAccumulating() const { return call_state_.top().accumulating; }

  // threadpool, so that we avoid the possibility of running the runner_ in the
  // threadpool of GPU event mgr, as that can trigger more callbacks to be
  // scheduled on that same threadpool, causing a deadlock in cases where the
  // caller of event_mgr->ThenExecute() blocks on the completion of the callback
  // (as in the case of ConstOp kernel creation on GPU, which involves copying a
  // CPU tensor to GPU).

        // broadcast, i.e. set as the input to each parallel operation. This
        // allows code like "tf.constant(1.)" or "tf.reduce_sum(..., axis=1)"
        // (where the value starts on the host), without allowing other implicit
        // copies/broadcasts. Other implicit copies may be supported eventually,
        // but need special handling for gradients (gradient of copy-on is not