用机器学习跳过超新星短时步，实现银河系恒星级模拟。
The First Star-by-star $N$-body/Hydrodynamics Simulation of Our Galaxy Coupling with a Surrogate Model
- 用代理模型替代超新星的短时步模拟，提升计算可扩展性。
- 首次实现3000亿粒子模拟，突破百亿级瓶颈。
- 适合高性能计算与星系演化研究者参考。
计算天体物理学的重要目标是高分辨率模拟银河系，直至单个恒星。但超新星等小尺度、短时标现象导致计算量剧增，难以扩展。本文提出一种结合机器学习的新型N体/流体动力学积分方案，通过代理模型绕过超新星引发的短时步，显著提升可扩展性。采用该方法，使用148,900个节点（相当于7,147,200个CPU核心），实现了3000亿粒子的模拟，突破当前最先进模拟的百亿粒子极限。此分辨率首次实现银河系恒星级模拟，可解析单个恒星。性能在超过10^4个CPU核心上保持良好扩展，覆盖当前主流处理器（A64FX、X86-64）及NVIDIA CUDA GPU平台。
原文摘要 · Abstract (English)
A major goal of computational astrophysics is to simulate the Milky Way Galaxy with sufficient resolution down to individual stars. However, the scaling fails due to some small-scale, short-timescale phenomena, such as supernova explosions. We have developed a novel integration scheme of $N$-body/hydrodynamics simulations working with machine learning. This approach bypasses the short timesteps caused by supernova explosions using a surrogate model, thereby improving scalability. With this method, we reached 300 billion particles using 148,900 nodes, equivalent to 7,147,200 CPU cores, breaking through the billion-particle barrier currently faced by state-of-the-art simulations. This resolution allows us to perform the first star-by-star galaxy simulation, which resolves individual stars in the Milky Way Galaxy. The performance scales over $10^4$ CPU cores, an upper limit in the current state-of-the-art simulations using both A64FX and X86-64 processors and NVIDIA CUDA GPUs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。