The SQLite VLDB'22 paper provides a detailed overview of SQLite architecture. I appreciate the authors' effort in analyzing the performance comparison with DuckDB. They honestly reported OLAP use cases where DuckDB is significantly faster and measured one level deeper.
https://www.vldb.org/pvldb/vol15/p3535-gaffney.pdf
https://www.vldb.org/pvldb/vol15/p3535-gaffney.pdf
Comments
I wonder if there's any new paper on optimizing data loading?
One thing to keep in mind with this paper is that they restricted DuckDB to a single CPU Core.
https://duckdb.org/2023/10/27/csv-sniffer.html
https://duckdb.org/2024/12/05/csv-files-dethroning-parquet-or-not.html