Speeding up Python-based Lagrangian Fluid-Flow Particle Simulations via Dynamic Collection Data Structures
Year: 2021
Type: preprint
Abstract: Array-like collection data structures are widely established in Python's scientific computing-ecosystem for high-performance computations. The structure maps well to regular, gridded lattice structures that are common to computational problems in physics and geosciences. High performance is, however, only guaranteed for static computations with a fixed computational domain. We show that for dynamic computations within an actively changing computational domain, the array-like collections provided by NumPy and its derivatives are a bottleneck for large computations. In response, we describe the integration of naturally-dynamic collection data structures (e.g. double-linked lists) into NumPy simulations and \textit{ctypes}-based C-bindings. Our benchmarks verify and quantify the performance increase attributed to the change of the collection data structure. Our application scenario, a Lagrangian (oceanic) fluid-flow particle simulation within the \textit{Parcels} framework, demonstrates the speed-up yield in a realistic setting and demonstrates the novel capabilities that are facilitated by optimised collection data structures.
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3158147124