Cox, LouisWilliams, BenjaminVickers, JamesWard, DavinHeadleand, ChristopherSheng, YunSlingsby, Aidan2025-09-092025-09-092025978-3-03868-293-6https://doi.org/10.2312/cgvc.20251224https://diglib.eg.org/handle/10.2312/cgvc20251224Entity-Component System (ECS) architectures have emerged as a powerful alternative to traditional object-oriented solutions in video games and real-time simulations. However, different ECS implementations present distinct trade-offs between iteration speed and modification costs. Despite its growing adoption, a comparative analysis on the performance characteristics of ECS implementation types has yet to be conducted. This study compares the performance of two widely-used ECS implementations: sparse-set and archetype-based. To facilitate this, an implementation of each architecture was developed in C++20 and their performance was examined in terms of iteration speed and entity modification costs. The results show sparse-set ECSes enable cheaper entity modifications but scale poorly during iteration, while archetypes excel at large-scale iteration through cache efficiency but incur higher composition change costs. These findings provide valuable and actionable guidance for developers selecting ECS architectures for their specific applications.Attribution 4.0 International LicenseCCS Concepts: Applied computing → Computer games; General and reference → Performance; Computing methodologies → Realtime simulation; Computer graphicsApplied computing → Computer gamesGeneral and reference → PerformanceComputing methodologies → Realtime simulationComputer graphics10.2312/cgvc.202512249 pages