I have had to work with the Denodo for the past 1+ year, a total nightmare. Data virtualization is a "good in theory" concept but "doesn't work in practice" reality. Going back to the original sources for each query doesn't work, it will always be slower than using a proper analytics data warehouse. Caching doesn't help because at that point you can just do ETL. Also Denodo itself is full of weird behaviors and bugs, my team collectively decided it's worth the most hate of all the "enterprise" tools we use. One thing Denodo is good for is as an "access layer", but then maybe PrestoDB would be worth a shot or maybe even just a sqlalchemy and python.