High Performance Computing on AWS

With virtually unlimited capacity, engineers, researchers, and HPC system owners can innovate beyond the limitations of on-premises HPC infrastructure. AWS delivers an integrated suite of services that provides everything needed to quickly and easily build and manage HPC clusters in the cloud to run the most compute intensive workloads across various industry verticals.

• Video

  High Performance Computing on AWS

  AWS delivers an integrated suite of services that provide everything needed to quickly and easily build and manage your HPC clusters in the cloud.

AWS HPC Customers

• 
  Webpage

  On AWS, AstraZeneca is running 51 billion statistical tests around their genomics pipeline, and delivered genomic insights to more than 40 drug discovery projects in 2020.
• 
  Webpage

  Lyft Level 5 was able to reduce costs up to 66% with Spot Instances and significantly scale their autonomous vehicle simulations with Amazon EC2.
• 
  Webpage

  On AWS, MAXAR was able to deliver weather forecast analysis 58% faster than the NOAA weather supercomputer.
• 
  Webpage

  INEOS team UK was able to process thousands of design simulations for their America’s Cup 4X faster on AWS compared to their on-premises environment.

Sponsored Articles

• 
  Article

  The Future of Large-Scale CFD

  The need for faster, larger, more accurate design cycles, along with the performance and cost advantages of GPUs, are all driving the next generation of CFD applications forward. With so many shifts ahead, HPC and CFD users are finding the on-prem route limiting in terms of hardware diversity, flexibility, scalability, and readiness for big shifts like AI/ML into the CFD mix.

AWS HPC Blogs

• 
  Blog

  Running finite element analysis using Simcenter Nastran on AWS

  In this blog, we demonstrate the deployment, performance, and price comparisons of Simcenter Nastran for three finite element analysis (FEA) based use cases on Amazon Web Services (AWS) high performance computing (HPC) clusters.
• 
  Blog

  GROMACS price-performance optimizations on AWS

  This blog presents a study of performance and price of running GROMACS, a popular open-source MD application, across a variety of Amazon Elastic Compute Cloud (Amazon EC2) instance type.
• 
  Blog

  A VDI solution with EnginFrame and NICE DCV Session Manager built with AWS CDK

  In this blog post, we will cover how to set up a fully functional Linux and Windows virtual desktop infrastructure (VDI) that is accessible through a simple web-based user interface.
• 
  Blog

  Simplify HPC cluster usage with AWS Cloud9 and AWS ParallelCluster

  This blog covers how to configure a canonical AWS ParallelCluster set up, and how to set up an AWS Cloud9 IDE on the head node of the cluster to enable easy collaboration with your peers.

AWS HPC Products and Services

• 
  Webpage

  Elastic Fabric Adapter

  Elastic Fabric Adapter (EFA) is a network interface for Amazon EC2 instances that enables customers to run applications requiring high levels of inter-node communications at scale on AWS.
• 
  Webpage

  AWS ParallelCluster

  AWS ParallelCluster is an AWS-supported open source cluster management tool that makes it easy for you to deploy and manage High Performance Computing (HPC) clusters on AWS.
• 
  Webpage

  NICE DCV

  NICE DCV is a high-performance remote display protocol that provides customers with a secure way to deliver remote desktops and application streaming from any cloud or data center to any device, over varying network conditions.
• 
  Webpage

  AWS Batch

  AWS Batch enables HPC users to easily and efficiently run hundreds of thousands of batch computing jobs on AWS. AWS Batch dynamically provisions the optimal quantity and type of compute resources based on the volume and specific resource requirement.

AWS HPC Tech Shorts

• Video

  "NO TEARS" HPC - Research-ready HPC clusters in under 10 minutes

  Learn how to build your HPC cluster on AWS in under 10 minutes with AWS ParallelCluster and Spack.
• Video

  Run molecular dynamics simulations fast with GROMACS on AWS

  Learn tips and tricks for software stacks and EC2 instances that deliver the best possible performance to run molecular dynamics quickly.
• Video

  Containers in HPC - What they fix and what they break

  This is the first of several videos on running containers for HPC workloads. Learn how containers work in general, and how they work with AWS services like AWS Nitro and GPU-based instances.
• Video

  How to configure multiple queues and instance types in AWS ParallelCluster

  Learn about AWS ParallelCluster 2.9 and its new features built on Slurm’s power management module, which allows you to build clusters with multiple queues and instance types within those queues.

Resources

• 
  Whitepaper

  Running HPC workloads on AWS

  By selecting the right combination of cloud-based compute and storage resources, customers can meet the demands of the most challenging HPC application. Learn how you can run a wide range of industry specific workloads on AWS.
• 
  Whitepaper

  Optimizing HPC workloads with Amazon EC2 Instances

  With access to virtually unlimited capacity in the cloud, you can reduce time-to-results by selecting the right compute platform for your workload. Learn how you can best match specific Amazon EC2 instances to your HPC application requirements.
• 
  Whitepaper

  Lower time-to-results for tightly coupled HPC applications with Elastic Fabric Adapter

  Elastic Fabric Adapter is a high bandwidth, low-latency, low-jitter network interface for Amazon EC2 instances that enables customers to run applications requiring high levels of inter-node communications at scale on AWS
• 
  Whitepaper

  The Cloud steps up to tightly coupled HPC codes

  Read this report from Hyperion Research on how cloud based service providers, like AWS, are enabling tightly-coupled workloads in the cloud.