Meaning of 'matching location' in description of tensor.backward

What does matching location mean in the below description of tensor.backkward?

`backward` ( gradient=None , retain_graph=None , create_graph=False )[SOURCE]

Computes the gradient of current tensor w.r.t. graph leaves.

The graph is differentiated using the chain rule. If the tensor is non-scalar (i.e. its data has more than one element) and requires gradient, the function additionally requires specifying `gradient` . It should be a tensor of matching type and location, that contains the gradient of the differentiated function w.r.t. `self` .

Kind regards,
Jens