Performing gate split operation using *cuTensorNet* adopts a very similar workflow as :ref:`QR example<QRexample>` and :ref:`SVD example<SVDexample>`. 
Here, we here highlight the notable differences between the two APIs. The full code can be found in 
the `NVIDIA/cuQuantum <https://github.com/NVIDIA/cuQuantum>`_ repository (`here <https://github.com/NVIDIA/cuQuantum/blob/main/samples/cutensornet/approxTN/gate_split_example.cu>`_).

----------------------
Define tensor operands
----------------------

As with QR/SVD decomposition, we first define all the tensor operands by specifying the data type, modes partition, and the extents. 
In this process, we choose to perform fixed extent truncation to a size of 16.

.. literalinclude:: ../../../../tensor_network/samples/approxTN/gate_split_example.cu
   :language: c++
   :linenos:
   :lineno-match:
   :start-after: Sphinx: #2
   :end-before: Sphinx: #3

---------
Execution
---------

Similar to :ref:`SVD example<SVDexample>`, we can specify the SVD options in `cutensornetTensorSVDConfig_t`. 
Workspace size query can be achieved by calling `cutensornetWorkspaceComputeGateSplitSizes` with the provided `cutensornetGateSplitAlgo_t`. 
Finally, we can execute the gate split computation by calling `cutensornetGateSplit`.

.. literalinclude:: ../../../../tensor_network/samples/approxTN/gate_split_example.cu
   :language: c++
   :linenos:
   :lineno-match:
   :start-after: Sphinx: #7
   :end-before: Sphinx: #8

.. note::
   
   Like in `cutensornetTensorSVD`, since we turned on weighted truncation options in this example, the tensor descriptors for outputs A and B need to be 
   restored if we wish to perform the same computation multiple times.

After the computation, we always need to free up all resources.