In this paper, we report the implementation and measured performance of our extreme-scale whole planetary ring simulation code on Sunway TaihuLight and two PEZY-SC2 systems: Shoubu System B and Gyoukou. The numerical algorithm is the parallel Barnes-Hut tree algorithm, which has been used in many large-scale astrophysical particle-based simulations. Our implementation is based on our FDPS framework. However, the extremely large numbers of cores of the systems used (10 M on TaihuLight and 16 M on Gyoukou) and their relatively poor memory and network bandwidth pose new challenges. We describe the new algorithms introduced to achieve high efficiency on machines with low memory bandwidth. The measured performance is 47.9, 10.6 PF, and 1.01PF on TaihuLight, Gyoukou and Shoubu System B (efficiency 40%, 23.5% and 35.5%). The current code is developed for the simulation of planetary rings, but most of the new algorithms are useful for other simulations, and are now available in the FDPS framework.

中文翻译：

---

Barnes-hut n-body 算法在超大规模异构众核架构上的实现和性能

在本文中，我们报告了我们在 Sunway TaihuLight 和两个 PEZY-SC2 系统：Shoubu System B 和 Gyoukou 上的极尺度全行星环模拟代码的实现和测量性能。数值算法是并行的 Barnes-Hut 树算法，该算法已被用于许多大规模的基于粒子的天体物理模拟。我们的实施基于我们的 FDPS 框架。然而，所使用的系统内核数量极其庞大（太湖之光10M，Gyoukou 16M）以及相对较差的内存和网络带宽带来了新的挑战。我们描述了为在具有低内存带宽的机器上实现高效率而引入的新算法。在太湖之光、Gyoukou 和 Shoubu System B 上测得的性能分别为 47.9、10.6 PF 和 1.01PF（效率分别为 40%、23.5% 和 35.5%）。