Posted On: Jul 27, 2020

AWS ParallelCluster is a fully supported and maintained open source cluster management tool that makes it easy for scientists, researchers, and IT administrators to deploy and manage High Performance Computing (HPC) clusters in the AWS cloud. HPC clusters are collections of tightly coupled compute, storage, and networking resources that enable customers to run large scale scientific and engineering workloads. 

Significant feature enhancements to this latest release of ParallelCluster include:

  • Support for ARM-based instances: AWS has recently released both the M6g and the C6g instances that use the next-generation ARM-based chip designed by AWS (and Annapurna Labs, an Amazon company), utilizing 64-bit Arm Neoverse N1 cores. These instances give customers another way to optimize their price performance (up to 40% cost-performance ratio improvement relative to M5 instances) on AWS when running their HPC workloads in AWS.
  • Enhanced pcluster update functionality: The pcluster update command allows customers to modify attributes of a running ParallelCluster cluster such as the instance type of compute nodes. With the latest version of ParallelCluster we have provided an improved interface so that customers can stage and inspect the changes to be applied by an update action before execution, as well as review instructions for further actions required to perform the update safely.
  • Support for automatic backups with FSx for Lustre: You can now create point-in-time backup copy of your FSx for Lustre file system, use backups as the source for your Lustre file system, and specify a schedule for creating these file system backups. You can find more information on this backup feature here as well as information on how to configure it in ParallelCluster here.

AWS ParallelCluster is available at no additional charge, and you pay only for the AWS resources needed to run your applications. It is now available in all AWS commercial regions and GovCloud regions. Learn how to launch an HPC cluster using AWS ParallelCluster here.

For more detail you can find the complete release notes for the latest version of AWS ParallelCluster here