votess: A multi-target, GPU-capable, parallel Voronoi tessellator

TL;DR

Votess is a portable, GPU-capable library that efficiently computes 3D Voronoi tessellations using a cell-by-cell algorithm optimized for data parallel architectures, improving performance over traditional methods.

Contribution

It introduces a parallel Voronoi tessellation library leveraging SYCL for portability and demonstrates significant performance gains over existing single-threaded solutions.

Findings

Achieves high performance on heterogeneous platforms.

Simplifies Voronoi computation with cell-by-cell approach.

Suitable for real-time, performance-critical applications.

Abstract

votess is a library for computing parallel 3D Voronoi tessellations on heterogeneous platforms, from CPUs and GPUs, to future accelerator architectures. To do so, it leverages the SYCL abstraction layer to achieve portability and performance across these architectures. The core library is an implementation of a Voronoi cell-by-cell computation algorithm, producing the geometry of the cells and their neighbor connectivity information, rather than a full combinatorial mesh data structure. This simplifies the Voronoi tessellation and makes it more suitable to data parallel architectures than alternatives such as sequential insertion or the Bowyer-Watson algorithm. The library demonstrates significant performance improvements over established single-threaded programs and serves as a foundational tool for performance-critical applications, such as on-the-fly computations in hydrodynamical codes.