Since the debut of the first “Beowulf” cluster in 1994, HPC has been a race between technologists wanting to squeeze as much performance as possible out of the hardware and economies of scale that have pushed mass production prices to affordable levels. The first HPC cluster was an artful combination of off-the-shelf computers networked with Ethernet and novel software techniques to enable distributed processing and set the pattern for a generation. While HPC looks very different today than it did almost 30 years ago, the purpose of HPC systems is the same – to help researchers, scientists and engineers find answers to some of the world’s biggest questions.
AWS provides everything today’s HPC users need to run their most demanding HPC applications. Whether you’re sequencing the human genome or designing a next-generation sports car, on AWS you have access to powerful storage, networking, compute, and HPC specialty software to cost-effectively run virtually any application in the cloud.
Join us on February 9th for a quick look at the latest and greatest AWS HPC products and services launched over the past year. We know that with so many developments in the HPC market, it’s often difficult to keep track of all the announcements AWS is making around HPC.
This event is designed to save you time and keep you up to date on all the exciting HPC tools AWS has introduced over the past year.
Hear directly from the AWS HPC engineers and product managers who developed these exciting new offerings. At this event we will be covering the latest computing offerings from Amazon EC2 such as the upcoming Graviton3 and the AMD EPYC 3approx Generation-based Hpc6a instance that offers the best price/performance for compute-intensive, tightly coupled HPC workloads on Amazon EC2. Tune in to learn about the latest features in AWS’s custom, high-performance network interface, the Elastic Fabric Adapter, and the latest in AWS’s high-performance storage solution, Amazon FSx for Luster. Beyond compute, networking and storage, hear from engineers and product managers working on HPC services such as ParallelCluster, AWS Batch, NICE DCV and our new hybrid workflow management capability (i.e. AWS HPC Cloud Connector) powered by NICE EnginFrame is available. See agenda below and on the registration page.
Computing power, network and storage (8:30am – 9:15am PST)
- Learn about the latest Amazon EC2 instances, such as B. Amazon EC2 Hpc6a, which offers up to 65% better price performance over comparable compute-optimized x86-based EC2 instances. Also learn more about the AWS developed Graviton processors like C6g and C6gn as well as the upcoming Graviton3 processors.
- Elastic Fabric Adapter (EFA) is AWS’s custom network interface that provides up to 400 GBP/S of network. Learn how the latest features like dual-slot EFA and features like GPU-Direct help scale your workloads to tens of thousands of cores.
- Amazon FSx for Luster offers fully managed shared storage with the scalability and performance of the popular Luster file system. Learn about the latest enhancements to Amazon FSx for Luster and Amazon FSx for OpenZFS based on the AWS Graviton processor family.
Cluster management and batch processing (9:15am – 9:30am PST)
- ParallelCluster helps you manage your entire HPC environment, from user permissions to storage and compute power. Learn about the new flexible ParallelCluster API, improved configuration file formatting, simplified network configuration options, and other new features that make managing your HPC environment on AWS easier than ever.
- AWS Batch enables developers, scientists, and engineers to easily and efficiently run hundreds of thousands of batch computing jobs on AWS. Learn how the latest features like AWS Batch Fair-Share can help your business scale batch processing more efficiently.
Hybrid HPC and remote visualization (9:30am – 10:00am PST)
- With EnginFrame, users can access an HPC portal to manage their HPC infrastructure on-premises and AWS. Join us as we show how EnginFrame’s easy-to-use interface can help you run your HPC workloads in the cloud.
- With NICE DCV, customers can run graphics-intensive applications remotely on EC2 instances and stream their user interface to simpler client machines, eliminating the need for expensive dedicated workstations. Learn more about the latest release of NICE DCV and how you can save money by streaming pixels instead of data.
breakout rooms (10:00 – 10:30 PST)
Ask AWS solution architects and engineers questions about the services covered during the event or about running line-of-business applications on AWS. Available breakout room topics will be listed here before and during the event.
We look forward to seeing you on February 9thth at 8:30am PST for this free event. to register Here.
Reminder: You can learn a lot from AWS HPC engineers by subscribing to them HPC Tech Short YouTube channeland following the AWS HPC Blog Channel.