Proceedings of BigHPC2024: Special Track on Big Data and High-Performance Computing, co-located with the 3ʳᵈ Italian Conference on Big Data and Data Science, ITADATA2024 — 2024
High-Performance Computation on a Rust-based distributed ABM engine
Daniele De Vinco, Andrea Tranquillo, Alessia Antelmi, Carmine Spagnuolo, Vittorio Scarano
Abstract
An agent-based model (ABM) is a computational model for simulating autonomous agents' actions and interactions to understand a system's behavior and what governs its outcomes. When the data or number of agents grow or multiple runs are necessary, agent-based simulations are generally computationally costly. Therefore, adopting different computing paradigms, such as the distributed one, is essential to manage long-running simulations. The main problem with this approach is finding a way to distribute and balance the simulation field so that the agents can move from one machine to another with the least amount of synchronization overhead. Based on our experiences, we present a Rust-based ABM engine capable of distributing models on high-performance computing resources, gaining remarkable speedup against the sequential version.
@inproceedings{Antelmi_BigHPC_24,
abstract = {An agent-based model (ABM) is a computational model for simulating autonomous agents' actions and interactions to understand a system's behavior and what governs its outcomes. When the data or number of agents grow or multiple runs are necessary, agent-based simulations are generally computationally costly. Therefore, adopting different computing paradigms, such as the distributed one, is essential to manage long-running simulations. The main problem with this approach is finding a way to distribute and balance the simulation field so that the agents can move from one machine to another with the least amount of synchronization overhead. Based on our experiences, we present a Rust-based ABM engine capable of distributing models on high-performance computing resources, gaining remarkable speedup against the sequential version.},
author = {De Vinco, Daniele and Tranquillo, Andrea and Antelmi, Alessia and Spagnuolo, Carmine and Scarano, Vittorio},
booktitle = {Proceedings of BigHPC2024: Special Track on Big Data and High-Performance Computing, co-located with the 3\textsuperscript{rd} Italian Conference on Big Data and Data Science, ITADATA2024},
editor = {Alessia Antelmi and Emanuele Carlini and Patrizio Dazzi},
keywords = {icsc, analytics},
publisher = {CEUR-WS.org},
series = {{CEUR} Workshop Proceedings},
title = {High-Performance Computation on a Rust-based distributed ABM engine},
url = {https://ceur-ws.org/Vol-3785/paper124.pdf},
volume = {3785},
year = {2024},
bdsk-url-1 = {https://ceur-ws.org/Vol-3785/paper124.pdf}}