Applicability of GPGPU Computing to Real-Time AI Solutions in Games
William Blewitt, Gary Ushaw, Graham Morgan · IEEE Transactions on Computational Intelligence and AI in Games · 2013
This paper reviews developments in general purpose computing on graphics processor units (GPGPU computing) from the perspective of video-game-related artificial intelligence (AI). We present an overview of the field, beginning with early shader language solutions and continuing to discuss three accessible platforms for GPGPU development: CUDA, OpenCL, and Direct Compute. Consideration is given to the commercial and practical realities which hinder the adoption of GPGPU solutions within video game AI, and developments in GPGPU computing directly relevant to common AI practices within the video games industry are reviewed in depth.