Memory Bottlenecks and Memory Contention in Multi-Core Monte Carlo Transport Codes
Argonne National Laboratory, Center for Exascale Simulation of Advanced Reactors, 9700 S Cass Ave, Argonne, IL 60439
We have extracted a kernel that executes only the most computationally expensive steps of the Monte Carlo particle transport algorithm - the calculation of macroscopic cross sections - in an effort to expose bottlenecks within multi-core, shared memory architectures.
Key words: Monte Carlo / Neutron Transport / Reactor Simulation / Cross Section / Benchmarks / High Performance Computing
© Owned by the authors, published by EDP Sciences, 2014