Provide an example that uses the Matrix Multiplication Engine

[DemiMarie]

To quote https://threedots.ovh/blog/2022/03/open-source-drivers-according-to-habana/ (emphasis theirs):

This version of the library doesn't implement any operations itself. This means for an operation like reshape or split, the user has to resolve it themselves, or write a TPC kernel to perform it.

This means that the actual MMA machine learning accelerators will not be used, with the general-purpose TPCs being used for all operators instead.

I would like to be proven wrong on this by an example that does use the MMEs.