float data[], int64_t dims[],
                                                  int num_dims);

// Get a Matrix TensorHandle with given float values and dimensions
TFE_TensorHandle* TestTensorHandleWithDimsFloat(TFE_Context* ctx, float data[],
                                                int64_t dims[], int num_dims);

absl::Status SetAttrString(AbstractOperation*, const char* attr_name,
                           const char* data, size_t length, ForwardOperation*);
absl::Status SetAttrInt(AbstractOperation*, const char* attr_name,
                        int64_t value, ForwardOperation*);
absl::Status SetAttrFloat(AbstractOperation*, const char* attr_name,
                          float value, ForwardOperation*);

    TF_DeleteShapeAndTypeList(output_shapes);
  }

  absl::optional<std::vector<int64_t>> make_shape(
      std::vector<int64_t>&& dims) const {
    return absl::make_optional(dims);
  }

  absl::optional<std::vector<int64_t>> unknown_shape() const {
    return absl::nullopt;
  }

  static constexpr int64_t kUnknownDim =
      shape_inference::InferenceContext::kUnknownDim;
  TF_Status* status_;

}

// Checks whether the stride array matches the layout of compact, row-majored
// data.
bool IsValidStrideCompactRowMajorData(int64_t* shape_arr, int64_t* stride_arr,
                                      int ndim) {
  bool valid = true;
  int64_t expected_stride = 1;
  for (int i = ndim - 1; i >= 0; --i) {
    // Empty tensors are always compact regardless of strides.
    if (shape_arr[i] == 0) return true;

TFE_MonitoringNewCounterReader(const char* name);

// Reads the value of a counter that was created with 0 labels.
TF_CAPI_EXPORT extern int64_t TFE_MonitoringReadCounter0(
    TFE_MonitoringCounterReader*);

// Reads the value of specific cell of a counter that was created with 1 label.
TF_CAPI_EXPORT extern int64_t TFE_MonitoringReadCounter1(
    TFE_MonitoringCounterReader*, const char* label_value);

#ifdef __cplusplus
} /* end extern "C" */

  return num_dims;
}

int64_t TFE_TensorHandleNumElements(TFE_TensorHandle* h, TF_Status* status) {
  if (h == nullptr) {
    status->status = tensorflow::errors::InvalidArgument("Invalid handle");
    return -1;
  }

  int64_t num_elements = -1;
  status->status = tensorflow::unwrap(h)->NumElements(&num_elements);
  return num_elements;
}

int64_t TFE_TensorHandleDim(TFE_TensorHandle* h, int dim_index,

// Fills data with values [start,end) with given step size.
void Range(vector<int32_t>* data, int32_t start, int32_t end,
           int32_t step = 1) {
  for (int32_t i = start; i < end; i += step) {
    (*data)[i] = i;
  }
}

// Fills out_dims with the dimensions of the given tensor.
void GetDims(const TF_Tensor* t, int64_t* out_dims) {
  int num_dims = TF_NumDims(t);
  for (int i = 0; i < num_dims; i++) {

  }
}

void TestEncodeDecode(int line, const std::vector<string>& data) {
  const int64_t n = data.size();
  absl::Status status;
  for (const std::vector<int64_t>& dims :
       std::vector<std::vector<int64_t>>{{n}, {1, n}, {n, 1}, {n / 2, 2}}) {
    // Create C++ Tensor
    Tensor src(tensorflow::DT_STRING, TensorShape(dims));
    for (int64_t i = 0; i < src.NumElements(); ++i) {
      src.flat<tstring>()(i) = data[i];
    }

 private:
  ParallelTensor(const ParallelDevice& device,
                 std::vector<TensorHandlePtr> tensors,
                 absl::Span<const int64_t> shape, const TF_DataType dtype)
      : device_(device),
        tensors_(std::move(tensors)),
        shape_(std::vector<int64_t>(shape.begin(), shape.end())),
        dtype_(dtype) {}
  ParallelTensor(const ParallelDevice& device,

                                                  TF_Status* status);
TF_CAPI_EXPORT extern int64_t TFE_TensorHandleNumElements(TFE_TensorHandle* h,
                                                          TF_Status* status);
// This function will block till the operation that produces `h` has completed.
TF_CAPI_EXPORT extern int64_t TFE_TensorHandleDim(TFE_TensorHandle* h,
                                                  int dim_index,