On supporting compilation in spatial query engines: (vision paper)

Abstract

Today's 'Big' spatial computing and analytics are largely processed in-memory. Still, evaluation in prominent spatial query engines is neither fully optimized for modern-class platforms nor taking full advantage of compilation (i.e., generating low-level query code). Query compilation has been rapidly rising inside in-memory relational database management systems (RDBMSs) achieving remarkable speedups; how can we bring similar benefits to spatial query engines? In this research, we bring in proven Programming Languages (PL) approaches e.g., partial evaluation, generative programming, etc. and leverage the power of modern hardware to extend query compilation inside spatial query engines. We envision a fully compiled spatial query engine that is efficient and feasible to implement in a high-level language. We describe LB2-Spatial; a prototype for a fully compiled spatial query engine that employs generative and multi-stage programming to realize query compilation. Furthermore, we discuss challenges, and conduct a preliminary experiment to highlight potential gains of compilation. Finally, we sketch potential avenues for supporting spatial query compilation in Postgres/ PostGIS; a traditional RDBMS and Spark/ Spark SQL; a main-memory cluster computing framework.