AWS Parallel Computing Service, a new managed service that simplifies the establishment and administration of high-performance computing (HPC) clusters, has been made generally available by Amazon Web Services (AWS). System administrators can construct and sustain clusters by utilizing Amazon EC2 instances, low-latency networking, and HPC-optimized storage with this service. By incorporating the widely used Slurm workload manager, the AWS Parallel Computing Service enables scientists and engineers to swiftly scale simulations for applications such as drug discovery, genomic research, and engineering design validation. The objective of the service is to accelerate innovation and reduce the operational burden of administering HPC clusters.
AWS has been a consistent leader in HPC innovation, with previous offerings such as Amazon FSx for Lustre, Elastic Fabric Adapter, and AWS Batch. Customers can now effortlessly transition on-premises workflows to the cloud without the need to re-architect them, thereby obtaining access to highly available, secure, and scalable cloud infrastructure with the AWS Parallel Computing Service tool. Currently, the service is accessible in the United States, Europe, and Asia Pacific. The service's potential to improve research efficiency and resilience in managing complex duties has already been acknowledged by major industry actors such as Marvel Fusion, Maxar Intelligence, and NREL.
