vectorized-execution

[SIGMOD'25] We show the data chunk compaction problem in vectorized execution, and propose practical compaction solutions.

A high-performance, distributed SQL query engine built in Rust. Powered by Apache Arrow for vectorized execution, it supports complex SQL (JOINs, CTEs, Window Functions), distributed processing, and Arrow Flight.

Relational execution engine in C++20 with iterator (Volcano), vectorized, and compiled (codegen-to-C) execution over one operator set - benchmarked on identical plans (12.7x vectorized win).

Research prototype for layered PostgreSQL representations and compact batch execution.

We integrate data chunk compaction methods into duckdb, for an end-to-end benchmark.

Lamina SQL: vectorized analytical SQL engine from scratch in Rust -- parsing, query planning, predicate pushdown, columnar execution, hash joins, benchmarked on TPC-H-shaped workloads

Vectorized executor to speed up PostgreSQL

C++17 vector-at-a-time analytical engine with null bitmaps, selection vectors, hash aggregation, joins, and scalar differential tests

Low-level systems engineering analysis of DuckDB - query execution path, vectorized execution, benchmarking, and failure analysis.

Basalt — a from-scratch hybrid OLTP/OLAP (HTAP) database engine in C++17, columnar by nature, with a browser Workbench and WASM playground; benchmarked vs SQLite, DuckDB, and MySQL

Dependency-free C++23 analytical kernels with runtime scalar, AVX2, AVX-512, and NEON dispatch.