Erik Darling puts together a great combination for a very large dataset:
So, today we’re going to talk about partitioning in columnstore because there are important differences between partitioned columnstore tables and partitioned rowstore tables. One of the sort of superpowers that columnstore has is the ability to use metadata about which row groups have which data in them, and it can skip entire segments that do not contain relevant data.
I agree with Erik’s point that you do need around 500 million or so rows before this capability really shines, but if you do pick the right partition key, you get one of those rare and coveted performance improvements from partitioning.