AWS HPC Blog
Harnessing the scale of AWS for financial simulations
Struggling with long compute times for numerical simulations in finance? See how AWS makes it simple to leverage the cloud for large-scale financial modeling. We walk through a real example using QuantLib and Monte Carlo methods.
A library of HPC Applications Best Practices on AWS
Want insights on running HPC codes efficiently on AWS? Our HPC specialists compiled their know-how into a new public GitHub repo. Get best practices, templates, scripts and more to optimize your workloads.
Job queue snapshots: see what’s at the head of your queues in AWS Batch
AWS Batch just grew a neat new feature: Job queue snapshots. This gives you the visibility you need for managing throughput in a dynamic environment – with competing priorities – and across multiple queues and workloads. Today we give you the inside scoop on how this feature works – especially when you’re using fair share scheduling.
An agent-based simulation of Amazon’s inbound supply chain
Hundreds of millions of products, the entire *first-mile* of distribution – learn how Amazon simulated their massive US supply chain, end-to-end, with help from a company called Simudyne.
Call for participation: HPC tutorial series from the HPCIC
Interested in getting hands-on experience with cutting-edge HPC tools? Check out this blog post on an upcoming virtual training series from @LLNL and @AWSCloud. Learn emerging technologies from the experts this August.
Integrating Research and Engineering Studio with AWS ParallelCluster
Researchers, engineers & scientists – learn how to leverage AWS ParallelCluster with Research & Engineering Studio for a full-featured cloud workspace. Read this post for details on this new integration.
Securing HPC on AWS: implementing STIGs in AWS ParallelCluster
Want to accelerate creating compliant Amazon EC2 images? Learn how HPC users can leverage cloud-native methods for applying STIG security standards.
Large scale training with NVIDIA NeMo Megatron on AWS ParallelCluster using P5 instances
Launching distributed GPT training? See how AWS ParallelCluster sets up a fast shared filesystem, SSH keys, host files, and more between nodes. Our guide has the details for creating a Slurm-managed cluster to train NeMo Megatron at scale.
Building an AI simulation assistant with agentic workflows
Simulations provide critical insights but running them takes specialized people, which can slow everyone down. We show how a Simulation Assistant can use LLMs and agents to start these workflows via chat so you can get results sooner.
Announcing: Seqera Containers for the bioinformatics community
Genomics community: rejoice! Seqera and AWS have teamed up to announce Seqera Containers, an open-source, no cost, reliable way to generate containers.