Parachute: Rethinking Query Execution and Bidirectional Information Flow in DuckDB - with Mihail Stoian

In this episode of the DuckDB in Research series, host Jack Waudby sits down with Mihail Stoian, PhD student at the Data Systems Lab, University of Technology Nuremberg, to unpack the cutting-edge ideas behind Parachute, a new approach to robust query processing and bidirectional information passing in modern analytical databases.

We explore how Parachute bridges theory and practice, combining concepts from instance-optimal algorithms and semi-join filtering to boost performance in DuckDB, the in-process analytical SQL engine that’s reshaping how research meets real-world data systems.

Mihail discusses:

• How Parachute extends semi-join filtering for two-way information flow
• The challenges of implementing research ideas inside DuckDB
• Practical performance gains on TPC-H and CEB workloads
• The future of adaptive query processing and research-driven system design

Whether you're a database researcher, systems engineer, or curious practitioner, this deep-dive reveals how academic innovation continues to shape modern data infrastructure.

Links:

• Parachute: Single-Pass Bi-Directional Information Passing VLDB 2025 Paper
• Mihail's homepage
• Parachute's Github repo

Hosted on Acast. See acast.com/privacy for more information.