Heterogeneous CPU/GPU co-execution of CFD simulations on the POWER9 architecture: Application to airplane aerodynamics

• Published in: Future generation computer systems Vol. 107; pp. 31 - 48
• Main Authors: Borrell, R., Dosimont, D., Garcia-Gasulla, M., Houzeaux, G., Lehmkuhl, O., Mehta, V., Owen, H., Vázquez, M., Oyarzun, G.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2020
• Subjects: CFD; GPU computing; Heterogeneous computing; Load balancing; NVIDIA volta V100; POWER9; CFD; POWER9; NVIDIA volta V100; Heterogeneous computing; Load balancing; GPU computing
• ISSN: 0167-739X; 1872-7115
• DOI: 10.1016/j.future.2020.01.045

High fidelity Computational Fluid Dynamics simulations are generally associated with large computing requirements, which are progressively acute with each new generation of supercomputers. However, significant research efforts are required to unlock the computing power of leading-edge systems, currently referred to as pre-Exascale systems, based on increasingly complex architectures. In this paper, we present the approach implemented in the computational mechanics code Alya. We describe in detail the parallelization strategy implemented to fully exploit the different levels of parallelism, together with a novel co-execution method for the efficient utilization of heterogeneous CPU/GPU architectures. The latter is based on a multi-code co-execution approach with a dynamic load balancing mechanism. The assessment of the performance of all the proposed strategies has been carried out for airplane simulations on the POWER9 architecture accelerated with NVIDIA Volta V100 GPUs. •We present a global parallelization strategy to fully exploit modern architectures.•A full airplane simulation was carried out on the Accelerated POWER9 cluster.•A new load balancing strategy was developed for co-execution.•The co-execution strategy reduces in 23% the elapsed time of the assembly.