The GPU version of LICOM3 under HIP framework and its large-scale application

Abstract

Abstract. A high-resolution (1/20°) global ocean general circulation model with Graphics processing units (GPUs) code implementations is developed based on the LASG/IAP Climate system Ocean Model version 3 (LICOM3) under Heterogeneous-compute Interface for Portability (HIP) framework. The dynamic core and physics package of LICOM3 are both ported to the GPU, and 3-dimensional parallelization is applied. The HIP version of the LICOM3 (LICOM3-HIP) is 42 times faster than what the same number of CPU cores dose, when 384 AMD GPUs and CPU cores are used. The LICOM3-HIP has excellent scalability; it can still obtain speedup of more than four on 9216 GPUs comparing to 384 GPUs. In this phase, we successfully performed a test of 1/20° LICOM3-HIP using 6550 nodes and 26200 GPUs, and at the grand scale, the model’s time to solution can still obtain an increasing, about 2.72 simulated years per day (SYPD). The high performance was due to putting almost all of computation processes inside GPUs, and thus greatly reduces the time cost of data transfer between CPUs and GPUs. At the same time, a 14-year spin-up integration following the phase 2 of Ocean Model Intercomparison Project (OMIP-2) protocol of surface forcing has been conducted, and the preliminary results have been evaluated. We found that the model results have little differences from the CPU version. Further comparison with observations and lower-resolution LICOM3 results suggests that the 1/20° LICOM3-HIP can not only reproduce the observations, but also produce much smaller scale activities, such as submesoscale eddies and frontal scales structures.

Opportunities and Challenges in Applying Machine Learning for Access Control

“…To address these challenges, researchers and practitioners are exploring new approaches to make machine learning-based access control systems more cost-effective and scalable [86,82]. This includes developing more efficient algorithms and techniques for data processing and model training, as well as exploring new methods for sharing and reusing trained models and other resources.…”

How Does It Function? Characterizing Long-term Trends in Production Serverless Workloads

“…Workload characterization of server systems has been a popular research topic for decades [4,10,13]. Recently, there have been a few studies on characterization and analysis of cloud system production workloads, e.g., from Google's Borg clusters [32], Azure's VM workloads [9], Alibaba ML workloads [38], and Azure Serverless workloads [21,29,43], among many others. The main goal of these studies is to design better systems, where the system management is data-driven.…”

A century-long eddy-resolving simulation of global oceanic large- and mesoscale state

“…Consequently, the capability of OGCMs to reproduce the large-scale 46 and mesoscale 46 , 47 ocean dynamics, energy cascade between different scales 55 , air–sea interaction 56 , and ocean heat uptake 57 has dramatically improved. Recently, simulations using higher-resolution OGCMs are beginning to emerge 58 , 59 . The increasing horizontal resolution effectively refines the simulation performances of OGCMs 47 , 54 and makes them available to predict ocean dynamics for both large-scale circulation and mesoscale eddies 34 , 60 .…”