Print this page
Published in Cloud

Amazon goes EPYC

by on08 June 2020


AMD on its cloud

AMD announced its second generation EPYC  processor is powering Amazon’s Elastic Compute Cloud (EC2) C5a and are switched on in the AWS US East, AWS US West, AWS Europe and AWS Asia Pacific regions.

Amazon is running each of the EPYC processors at frequencies up to 3.3Ghz and it is the sixth instance of AWS powered by AMD EPYC processors.

AMD claims that the C5a instance delivers leadership x86 price-performance for a broad set of compute-intensive workloads including batch processing, distributed analytics, data transformations, log analytics and web applications.

It is available in eight configurations, with up to 96 virtual CPUs, the Amazon EC2 C5a instances take advantage of high core counts from the EPYC processor to offer the lowest cost per x86 virtual CPU in the Amazon EC2 portfolio.

AMD’s Data Center and Embedded Solutions Group  senior vice president and general manager  Forrest Norrod said: “The 2nd Gen AMD EPYC processors deliver the levels of performance required for our customers to confidently bring compute-focused workloads to the cloud. With the new Amazon EC2 C5a instances, we are strategically expanding our presence and capabilities with AWS. Even more importantly, together we are helping to continuously improve the end user cloud experience.”

Amazon EC2, Web Services, Vice President David Brown said AMD and AWS offer customers great flexibility and choice of compute options to help them optimise both performance and cost for a wide range of workloads.

“Since launching Amazon EC2 R5a, M5a, and T3a instances powered by 1st gen AMD EPYC processors, we’ve seen customers move many general purpose and memory optimized workloads to take advantage of the AMD EPYC processor capabilities and 10 per cent lower prices over comparable instances. With the availability of Amazon EC2 C5a instances based on EPYC processors, customers now have a new option that enables better performance and cost for a variety of compute intensive workloads”, he said.

Last modified on 08 June 2020
Rate this item
(0 votes)