High-performance server systems and the next generation of online games

Developing a massively multiplayer online game which utilizes physically based simulation to provide realistic behaviors requires numerical integration functions with inherently high computational costs. This simulation, performed on the individual clients of a peer-to-peer networked game or for a client/server online game, presents challenges due to many factors, including limited computing resources at the client level and network latency in the propagation of a client's state to other clients. Computationally intensive simulation may adversely affect performance and result in a situation in which little processing capacity is left for other aspects of the game. In this paper, we explore how a game developer who is aware of these issues might create a game for IBM's recently announced Cell Broadband EngineTM processor; we also present an example of the development of a game in which multiple human and robotic characters interact with static and dynamic objects in a virtual environment. Although our experience suggests that porting code to the Cell Broadband Engine core with minimal use of its synergistic processing elements (SPEs) should not be expected to produce significant performance gains at this time, the potential of the Cell SPEs to improve performance is considerable. We discuss performance and design and implementation decisions, with programmability issues being especially noted.