Avoid LDGSTS routing by changing default copy to be universalcopy

[ZelboK]

https://github.com/NVIDIA/cutlass/issues/1672

This PR changes the default copy to be UniversalCopy so the LDGSTS instruction is avoided, and downstream users will need to specify the copy type if they want to use it which is more intuitive.

Note: I imagine since all of the tests and examples that are configured to use DefaultCopy will need to now transition over to AutoVectorizingCopyWithAssumedAlignment<128> as that was the previous copy type. This way we can preserve behavior across benchmarks and tests. Before I make a bunch of changes across files though I'd like to get feedback now incase I'm missing anything.