Considerations for scalable CAE on the SGI ccNUMA architecture
Stan Posey, Liao Cheng, Mark D. Kremenetsky · 2000
Recent breakthroughs in CAE technology have lead to a high degree of parallel scaling for CAE simulations in a distributed shared-memory environment. A variety of research and commercial CAE software demonstrate scalable levels that are linear beyond 256 processors on the ccNUMA system architecture developed by SGI. To achieve efficient parallelism consideration must be given to topics such as choice and performance of CAE algorithms and system software, and awareness of communication architectures. This paper examines the requirements for highly-scalable CAE simulations on industrial application examples.