A cyclic-track decomposition method for 3D MOC neutron transport simulation

Abstract

The method of characteristics (MOC) is a promising numerical technique for solving the neutron transport equation. This method has been parallelized to accommodate its high computing power and memory requirements. Angle decomposition is widely used by parallel MOC codes to distribute MOC tracks over CPU cores, but it may lead to load imbalance. Based on modular ray tracing, we present a cyclic-track decomposition method along with a load balancing strategy to address the limitations of angle decomposition for parallel MOC on 3D axially extruded geometries. It has been implemented as the top-level decomposition in the ANT-MOC code to demonstrate its effectiveness and to show its potential as an alternative to domain decomposition. We evaluated the cyclic-track decomposition method using a generalized performance model and some neutron transport benchmarks. Our evaluation showed that the cyclic-track decomposition method generated a more balanced load distribution than the angle decomposition method, and ANT-MOC with the new strategy for load balancing achieved a good performance of over 40% parallel efficiency as it scales from 10,240 to 98,304 cores on the ORISE supercomputer.