Exploring Energy Management on GPUs in Game Architectures

Marcelo Zamith, Luis Valente, Mark Joselli, José Ricardo Silva Junior, Esteban Clua, Bruno Feijó

Abstract


CPUs and GPUs have been evolving rapidly over time regarding their capabilities and processing power. This has opened many new possibilities for interactive and real time systems, such as more sophisticated scene realism, more precise and complex artificial intelligence, and better physical simulations. However, these improvements come at a cost: increase of energy consumption. Energy management in interactive and real time architectures have not been receiving much attention over the years, but this issue is likely to become important in the near future due to the increasing energy demand and consumption required by top-notch game applications(especially regarding the mobile and portable consoles). In this paper we introduce the concept of intelligent energy management for games and interactive systems and address the aforementioned issue through these contributions: 1) an investigation of works related to energy management (in general); 2) implementations of feasibility tests for energy management on GPUs; and 3) a novel game architecture with energy management, using multiple GPUs.

Keywords


energy management, parallel computing, multi-thread, GPGPU, game loop models, real-time systems, multiple GPUs.

Full Text:

PDF