Advancing the future of data + AI.
We describe and demo MotherDuck: a new service that connects DuckDB to the cloud. MotherDuck provides the concept of hybrid query processing: the ability to execute queries partly on the client and partly in the cloud.
This thesis tackles a core challenge in MotherDuck's hybrid execution model: deciding which parts of a query should run locally vs. in the cloud. The result is a cost-based optimizer that delivers up to 17x speedups on long-running analytical queries.
This thesis introduces Accelerated Approximate Views — a new SQL-level caching mechanism for MotherDuck’s hybrid execution model. By partially materializing query results on the client, AAVs reduce latency for interactive data exploration in both native and WebAssembly environments.
