AWS ParallelCluster 3.3 has been released with bumper new features

Brendan Bouffler
Date : November 11, 2022
Categories : AWS ParallelCluster ,Amazon NICE DCV ,Elastic Fabric Adapter ,Life Sciences
Tags : cpus ,dcv ,ec2 ,efa ,gpus ,hpc ,high performance computing ,lustre ,mpi ,odcr ,parallel cluster ,schedulers ,storage ,autoscaling ,aws ,bioinformatics ,cloud computing ,elastic ,elastic fabric adapter ,infiniband ,instance allocation strategies ,instance diversity ,lustre ,on demand capacity reservation ,scientific computing ,shared storage ,slurm accounting ,technical computing ,tightly coupled ,virtualization ,vizualization ,techshorts

We just released version 3.3 of AWS ParallelCluster, and it has a whole bag of new features.

instance type allocation diversity in your queues;
separation of shred volumes from the cluster lifecycle
SLURM ACCOUNTING (this is pretty popular)
support for ODCRs (a 70’s progressive rock band ^H^H^H^H^H a way of reserving capacity despite ParallelCluster’s best efforts to reduce your unnecessary usage - it’s honestly needed at times).

Matt Vaughn - our WW Principal Dev Advocate for HPC (@yakshavers) came to Tech Shorts to explain it all to us.

If you have ideas for technical topics you’d like to see us cover in a future show, let us know by finding us on Twitter (@TechHpc) and DM’ing us with your idea.