Understanding the efficient parallelisation of Cellular Automata on CPU and GPGPU hardware
Association for Computing Machinery (ACM)
Copyright is held by the author/owner(s). This is the final version of the article. Available via the DOI in this record.
Cellular automata, represented by a discrete set of elements are ideal candidates for parallelisation, particularly on graphics cards using GPGPU technology. This paper shows that the speedups of 50 times over CPU are possible but that the hardware is only partially responsible and the memory model is vital to exploiting the additional computational power of the GPU.
GECCO '13 Companion Proceedings of the 15th annual conference companion on Genetic and evolutionary computation, pp. 171-172