Today we have implemented our HPC Application Best Practice using AWS ParallelCluster.
AWS ParallelCluster is an open source cluster management tool that makes it easy for you to deploy and manage High Performance Computing (HPC) clusters on AWS.
ParallelCluster offer a simple graphical user interface GUI or text file to model and provision the resources needed for your HPC applications in an automated and secure manner.
It also supports multiple instance types and job submission queues, and job schedulers like AWS Batch and Slurm.
You can build your cluster using the AWS ParallelCluster CLI.
Find example ParallelCluster configuration files under the config directory.
This configuration files are not working examples as they need you to replace a few tokens (like subnet-1234567890
or sg-1234567890
) with the resources you want to use on your AWS account.
In addition, we have build a few working CloudFormantion templates that help you to create a new HPC cluster with just 1-Click.
Select your preferred AWS Region among the supported ones. You will be asked a few questions about Networking and Storage;
If you have no idea how to answer or what these services are, just leave the default values: AUTO
.
The 1-Click deployment procedure will take care of creating everything needed for your HPC Cluster to run properly.
NOTE: Please refer to aws-hpc-recipes in case you need to leverage advanced AWS ParallelCluster functionalities through interoperable CloudFormation templates designed to work together to build complete HPC environments.
After the CloudFormation stack is completed you can go to the Output
tab and click on the SystemManagerUrl
link.
This link will let you access the HeadNode via SystemManager without using any password or certificate.
(see the image below)
You will find a clone of this repository under /fsx
.