An efficient communication strategy for massively parallel computation in CFD

Abstract

With the growing computing power of high-performance computers, efficient parallel algorithms are becoming increasingly important in the development of Computational Fluid Dynamics(CFD). This research presents a novel parallel strategy based on asynchronous and package communication. This strategy tries to enhance the performance of large-scale computation for realistic complex geometry. The new strategy aggregates all communications and only requires communication once at each iteration step. Convergence of the new strategy is also proved and validated. Three numerical experiments demonstrates the exceptional parallel performance of the novel strategy in simulating complex geometry. When the number of CPU cores approach 26 thousand, strong scale parallel efficiency still remains at 74% based on 10.5 billion mesh elements. With 179,200 CPU cores and 10 billion mesh elements, weak scale parallel efficiency maintains at 90%. This research demonstrates that large-scale parallel computation can be applied efficiently in numerical simulation of a complex aircraft.

Large‐scale homo‐ and heterogeneous parallel paradigm design based on CFD application PHengLEI

“…The design principle of the "DataContainer" can be found in the document. 25 The "DataContainer" also unifies intra-and inter-process communication. The data transfer between zones includes both intra-process and inter-process modes.…”

“…Furthermore, unified optimization can be performed for communication to enhance parallel efficiency. Our paradigm is based on the communication strategy of asynchronous communication (similar to the MPI's) and packaged communication 25 . Asynchronous communication means that all communications are combined into one operation after one iteration, achieving separation of communication and calculation.…”

“…This paradigm uses the data container named “DataContainer” to compress all the variables into the data container, and then communicate the compressed data only one time. The design principle of the “DataContainer” can be found in the document 25 . The “DataContainer” also unifies intra‐ and inter‐process communication.…”

“…When the computation results converge, the obtained convergence results are consistent with the traditional communication method. We have mathematically proven in the literature 25 …”