多节点系统上天气和气候侏儒的性能报告和优化实施
Performance report and optimized implementations of Weather & Climate dwarfs on multi-node systems
摘要：
本文档是为ESCAPE项目创建的可交付成果报告之一。ESCAPE是Energy-efficient Scalable Algorithms for Weather Prediction at Exascale的缩写。该项目为欧洲业务数值天气预报和未来气候模型开发世界级的极端规模计算能力。这是通过识别天气和气候侏儒来完成的，这些侏儒是计算和通信方面的关键模式（本着伯克利侏儒的精神）。然后针对不同的硬件架构（单节点和多节点）优化这些侏儒，并探索替代算法。性能可移植性是通过使用领域特定的语言来解决的。在这里，我们总结了在侏儒优化方面所做的工作，重点是CPU多节点和多GPU。我们将自己限制在由财团选择的矮配置的子集上。侏儒节点内优化和特定于能量的优化已经在D3.3中描述。为了涵盖重要的算法主题，我们选择了与动力学核心以及柱物理相关的矮星。具体来说，我们专注于制定相关的频谱代码，如ECMWF的IFS代码。本报告的主要结论是：（a）与任务3.3中的优化版dwarfs相比，基于CPU的多节点系统的性能提升高达30%（参见D3.3），（b）通过优化在多个GPU上获得高达10倍的性能增益，以保持数据驻留在GPU上并实现快速的GPU间通信机制，以及（c）以具有NVLink/NVSwitch硬件的高带宽全对全互连拓扑为特征的多GPU系统特别适合于所述算法。
英文摘要：
This document is one of the deliverable reports created for the ESCAPE project. ESCAPE stands for Energy-efficient Scalable Algorithms for Weather Prediction at Exascale. The project develops world-class, extreme-scale computing capabilities for European operational numerical weather prediction and future climate models. This is done by identifying Weather & Climate dwarfs which are key patterns in terms of computation and communication (in the spirit of the Berkeley dwarfs). These dwarfs are then optimised for different hardware architectures (single and multi-node) and alternative algorithms are explored. Performance portability is addressed through the use of domain specific languages. Here we summarize the work performed on optimizations of the dwarfs focusing on CPU multi-nodes and multi-GPUs. We limit ourselves to a subset of the dwarf configurations chosen by the consortium. Intra-node optimizations of the dwarfs and energy-specific optimizations have been described in Deliverable D3.3. To cover the important algorithmic motifs we picked dwarfs related to the dynamical core as well as column physics. Specifically, we focused on the formulation relevant to spectral codes like ECMWF's IFS code. The main findings of this report are: (a) Up-to 30% performance gain with CPU based multi-node systems compared to optimized version of dwarfs from task 3.3 (see D3.3), (b) up to 10X performance gain on multiple GPUs from optimizations to keep data resident on the GPU and enable fast inter-GPU communication mechanisms, and (c) multi-GPU systems which feature a high-bandwidth all-to-all interconnect topology with NVLink/NVSwitch hardware are particularly well suited to the algorithms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
