Title

Low-Latency Query Compilation

Authors

Henning Funke, Jan Mühlig, and Jens Teubner

Published

The VLDB Journal, vol. 31(6), pages 1171–1184, 2022

Abstract

Query compilation is a processing technique that achieves very high processing speeds but has the disadvantage of introducing additional compilation latencies. These latencies cause an overhead that is relatively high for short-running and high-complexity queries. In this work, we present Flounder IR and ReSQL, our new approach to query compilation. Instead of using a general purpose intermediate representation (e.g., LLVM IR) during compilation, ReSQL uses Flounder IR, which is specifically designed for database processing. Flounder IR is lightweight and close to machine assembly. This simplifies the translation from IR to machine code, which otherwise is a costly translation step. Despite simple translation, compiled queries still benefit from the high processing speeds of the query compilation technique. We analyze the performance of our approach with micro-benchmarks and with ReSQL, which employs a full translation stack from SQL to machine code. We show reductions in compilation times up to two orders of magnitude over LLVM and show improvements in overall execution time for TPC-H queries up to 5.5 × over state-of-the-art systems.

Download

PDF via Springer Link (open access)

DOI

10.1007/s00778-022-00741-5 (Springer Link)

May 2022

publication in The VLDB Journal (PDF, via Springer Link)

March 2022

accepted for publication in The VLDB Journal

December 2021

revision submission to The VLDB Journal

• submission
• revision letter
• review (accept)

May 2021

submission to The VLDB Journal

• submission to The VLDB Journal
• reviews (minor revision)

December 2020

invitation to submit to The VLDB Journal (special Edition “Best of DaMoN 2020”); follow-up to publication “Efficient Generation of Machine Code for Query Compilers”.