Paper Profile


Multilevel Parallel Strategy on Monte Carlo Particle Transport for the Large-Scale Full-Core Pin-by-Pin Simulations


Documents: Full paper available in Conference Proceedings.
 
Date: Monday October 19
Time:16:15 - 16:40
 
Session:1B3: Monte Carlo I
 
Authors: BaoYin Zhang (Institute of Applied Physics and Computational Mathematics, China)
Gang Li (Institute of Applied Physics and Computational Mathematics, China)
Wei Wang (Institute of Applied Physics and Computational Mathematics, China)
Danhua Shangguan (Institute of Applied Physics and Computational Mathematics, China)
Li Deng (Institute of Applied Physics and Computational Mathematics, China)
Abstract:

This paper introduces the Strategy of multilevel hybrid parallelism of JCOGIN Infrastructure on Monte Carlo Particle Transport for the large-scale full-core pin-by-pin simulations. The particle parallelism, domain decomposition parallelism and MPI/OpenMP parallelism are designed and implemented. By the testing, JMCT presents the parallel scalability of JCOGIN, which reaches the parallel efficiency 80% on 120,000 cores for the pin-by-pin computation of the BEAVRS benchmark.

Back to Top