“Capsule: Efficient Player Isolation for Datacenters” by Du, Davari, Li and Kodirov
Conference:
Type(s):
Title:
- Capsule: Efficient Player Isolation for Datacenters
Session/Category Title:
- Interactive Techniques
Presenter(s)/Author(s):
Abstract:
We propose a new game engine module, Capsule, that allows multiple players efficiently share one engine. We implemented Capsule in O3DE, in an application agnostic way. Our experience with four applications show that Capsule increases datacenter resource utilization by accommodating up to 2.25x more players, without degrading player gaming experience.
References:
[1] Zhouheng Du, Nima Davari, Li Li, and Nodir Kodirov. 2025. Capsule: Efficient Player Isolation for Datacenters. arxiv:https://arXiv.org/abs/2506.11483https://arxiv.org/abs/2506.11483
[2] NVIDIA. 2025. NVIDIA RTX Virtual Workstation (vWS). Retrieved April 23, 2025 from https://www.nvidia.com/en-us/design-visualization/virtual-workstation/
[3] O3DE. 2025a. MultiplayerSample Project. Retrieved April 23, 2025 from https://github.com/o3de/o3de-multiplayersample
[4] O3DE. 2025b. O3DE. Retrieved April 23, 2025 from https://github.com/o3de/o3de
[5] Unity. 2025. ECS for Unity. Retrieved April 23, 2025 from https://unity.com/ecs
[6] Alexander Weinrauch, Wolfgang Tatzgern, Pascal Stadlbauer, Alexis Crickx, Jozef Hladky, Arno Coomans, Martin Winter, Joerg H. Mueller, and Markus Steinberger. 2023. Effect-based Multi-viewer Caching for Cloud-native Rendering. ACM Trans. Graph. 42, 4, Article 87 (July 2023), 16 pages.
