segment-wise.
        index (`IndexMap`, indices are of shape [B1, B2, ..., Bn, I1, .., Ik].):
            Index defining the segments.
        name (`str`, *optional*, defaults to 'segmented_reduce_sum'):
            Name for the operation. Currently not used

    Returns:
        output_values (`torch.Tensor`of shape [B1, B2, ..., Bn, num_segments, V1, V2, ..]): Tensor containing the
        output values. output_index (`IndexMap`): IndexMap with shape [B1, B2, ..., Bn, num_segments]. .
    rW