August 26, 2021

Optimize Numerical Weather Predictions on AWS Graviton2

Broadcast Date: August 26, 2021 Level: 300 The Weather Research and Forecasting (WRF) model is a numerical weather prediction (NWP) system designed to serve both atmospheric research and operational forecasting needs. With the release of Arm-based AWS Graviton2 Amazon Elastic Compute Cloud (EC2) instances, a common question has been how these instances perform on large-scale NWP workloads. In this tech talk we will demo running NWP on AWS Graviton2 and share benchmarking results from running NWP across three different instance types. Learn how you can optimize price performance when running your WRF simulations on AWS with AWS Graviton2. Learn how to effectively use Graviton-based instances for your HPC applications, including Numerical Weather Prediction (NWP) applications Understand how you can achieve higher performance in your NWP applications through the use of Elastic Fabric Adapter (EFA) Learn how different instance types can allow you to scale your workloads efficiently Developers, Data Scientists

Matt Koop, Principal Solutions Architect, AWS

Learn More To learn more about the services featured in this talk, please visit: https://aws.amazon.com/ec2/graviton/


Share with your friends: