Can we use systolic arrays in this implementation?

Congrats on your release!

I am wondering if your implementation allows me to use systolic arrays (tensor cores or xmx engines or matrix cores in diff gpu implementations)? Intel's implementation has this [extension](https://github.com/intel/llvm/blob/b209b321b5a8540263af9ba317c89a1882f06120/sycl/doc/extensions/experimental/sycl_ext_matrix/sycl_ext_oneapi_matrix.asciidoc#L69) to support these from all vendors.

I think having support for these is very important for performance of matrix multiplication and highly quantized implementations.