Clouds represent a key uncertainty in future climate projection. While explicit cloud resolution remains beyond our computational grasp for global climate, we can incorporate important cloud effects through a computational middle ground called the Multi-scale Modeling Framework (MMF), also known as Super Parameterization. This algorithmic approach embeds high-resolution Cloud Resolving Models (CRMs) to represent moist convective processes within each grid column in a Global Climate Model (GCM). The MMF code requires no parallel data transfers and provides a self-contained target for acceleration. This study investigates the performance of the Energy Exascale Earth System Model-MMF (E3SM-MMF) code on the OLCF Summit supercomputer at an unprecedented scale of simulation. Hundreds of kernels in the roughly 10K lines of code in the E3SM-MMF CRM were ported to GPUs with OpenACC directives. A high-resolution benchmark using 4600 nodes on Summit demonstrates the computational capability of the GPU-enabled E3SM-MMF code in a full physics climate simulation.

云是未来气候预测的关键不确定性。虽然明确的云分辨率仍然超出了我们对全球气候的计算能力，但我们可以通过称为多尺度建模框架 (MMF)（也称为超级参数化）的计算中间层来整合重要的云效应。这种算法方法嵌入了高分辨率云解析模型 (CRM)，以表示全球气候模型 (GCM) 中每个网格列内的湿对流过程。MMF 代码不需要并行数据传输，并提供一个独立的加速目标。本研究以前所未有的模拟规模调查了 OLCF Summit 超级计算机上的 Energy Exascale Earth System Model-MMF (E3SM-MMF) 代码的性能。E3SM-MMF CRM 中大约 10K 行代码中的数百个内核通过 OpenACC 指令移植到 GPU。在 Summit 上使用 4600 个节点的高分辨率基准测试展示了支持 GPU 的 E3SM-MMF 代码在完整物理气候模拟中的计算能力。