Machine Learning | AWS HPC Blog

Use Terraform to deploy a complete AWS Batch environment on Amazon EKS

Harness the power of AWS Batch on Amazon EKS with this new Terraform blueprint. It provides a complete template to create robust batch processing in the cloud. An easy button you shouldn’t miss.

A guide to identity management in Research and Engineering Studio on AWS

Check out this new post to learn about identity options for Research and Engineering Studio on AWS. Understanding choices for SAML IdPs and Active Directory will help you plan secure VDI access.

LLMs: the new frontier in generative agent-based simulation

How can LLMs take agent-based simulation to the next level? Check out our new post on leveraging large language models’ capabilities for more realistic modeling.

Harnessing the power of agent-based modeling for equity market simulation and strategy testing

Financial professionals: Simulate realistic market conditions with Simudyne’s agent-based modeling on AWS and Red Hat OpenShift. Learn how HKEX leverages these insights.

Recent improvement to Open MPI AllReduce and the impact to application performance

Our team engineered some Open MPI optimizations for EFA to enhance performance of HPC codes running in the cloud. By improving MPI_AllReduce they improved scaling – matching commercial MPIs. Tests show gains for apps including Code Saturne and OpenFOAM on both Arm64 and x86 instances. Check out how these tweaks can speed up your HPC workloads in the cloud.

AWS Batch enables near-real-time energy production forecasts using NVIDIA Earth-2

Using AWS Batch and NVIDIA Earth-2, we built a scalable workflow that explores millions of scenarios at a fraction of the cost of traditional methods. This innovative approach not only provides rapid energy calculations, but also shows the potential of AI-driven meteorology.