AMD Announces GA of New AWS EC2 Hpc6a Instances

HPC ClustersAMD (NASDAQ: AMD) today GA of Amazon Web Services (AWS) EC2 Hpc6a instances based on the AMD EPYC CPU, built for high performance computing (HPC) workloads in the cloud.

AWS pre-announced Hpc6a last November. The instances deliver 100 Gbps networking with 96 third-generation AMD EPYC processor (Milan) cores with 384 GB RAM, according to the company. The instances work through the Elastic Fabric Adapter (EFA) EC2 network device, designed to improve throughput and scaling of tightly coupled workloads, and AWS ParallelCluster, an open-source cluster management tool.

According to AWS, the new instances deliver up to 65 percent better price-performance compared to similar Amazon EC2 instances. “Hpc6a will help customers run their most compute-intensive HPC workloads, like genomics, computational fluid dynamics, weather forecasting, financial risk modeling, EDA for semiconductor design, computer-aided engineering, and seismic imaging,” the company said.

“AWS enables you to increase the speed of research and reduce time-to-results by running HPC in the cloud and scaling to tens of thousands of parallel tasks that wouldn’t be practical in most on-premises environments,” the company said in a blog.

In its announcement, AMD said “Throughout the HPC industry, there has been a growing preference for AMD, as showcased by AMD EPYC processors powering 73 supercomputers on the latest Top500 list and holding 70 HPC world records.”

AMD said EPYC-powered instances are now available in US East (Ohio) and AWS GovCloud (US-West), with availability in additional AWS regions planned soon. AWS customers can visit the Amazon EC2 Hpc6a instances page to get started.

“Our processors power all levels of HPC, from exascale systems in research laboratories to flexible HPC cloud computing instances like the new Amazon EC2 Hpc6a instances. AMD EPYC processors provide a powerful solution for Amazon EC2 customers that need access to impressive HPC performance and cloud scalability for their workloads,” said Dan McNamara, SVP/GM, Server Business, AMD. “Our work with AWS exemplifies our commitment to powering cutting edge technology in the HPC industry and helping customers find answers to the world’s most pressing questions.”

“Amazon EC2 Hpc6a instances, powered by 3rd Gen AMD EPYC processors, allow organizations the flexibility to run HPC workloads requiring an abundance of compute power, fast memory and storage, and high levels of inter-instance communication without the upfront cost of building and maintaining HPC infrastructure on-premises,” said David Brown, vice president, Amazon EC2, AWS. “We’re excited to continue our collaboration with AMD and add another crucial AMD EPYC instance to the Amazon EC2 portfolio.”