AWS Announces New Instances Powered by 2nd Gen Intel® Xeon® Scalable Processors

We’re extremely proud to collaborate with Amazon Web Services (AWS) and continue to deliver ground-breaking technology to their customers. For over a decade the engineering relationship between Intel and AWS has provided tailored solutions for the most demanding workloads. This week’s announcement of the new Amazon EC2 instances for large, in-memory applications and workloads demanding high network throughput, both powered by 2nd Generation Intel® Xeon® Scalable, is another milestone born of our close collaboration with AWS.

Double the Available Memory

The previous EC2 High Memory instances offered 6, 9 and 12 tebibytes (TiB) of memory.  The bare metal instances launched this week extend these options to an 18 and 24 TiB of memory and are powered by eight Intel® Xeon® Platinum 8280L processors. The large memory capacity is optimal for customers running demanding in-memory databases such as SAP HANA.

Each instance also has 28 Gbps of dedicated Elastic Block Store (EBS) bandwidth which enables high-speed loading of data into memory. According to Jeff Barr’s announcement on the AWS blog this week, his team loaded 9 TB of data in just 45 minutes, an effective rate of 3.4 gigabytes per second. Look here for the detailed specs and an overview of the scale-up and scale-out options that are possible when using these new instances to run SAP HANA.

Faster Machine Learning

Also announced this week is the availability of Amazon EC2 instances that utilize up to 100 Gbps of network bandwidth. The new M5n, M5dn, R5n, R5dn instances run on a custom 2nd Generation Intel® Xeon® Scalable processor  and provide support for the new Intel® Deep Learning Boost instructions and our latest Advanced Vector Extensions (AVX-512). These new instruction sets are unique to Xeon Scalable and improve performance across  different workloads. These new instances with network bandwidth ranging from 25 Gbps to 100 Gbps are designed for AI/ML, HPC, analytics and Big Data workloads, that can benefit from the improved packet rate performance.

Intel and AWS engineers collaborate on difficult technical questions every day, and it’s really rewarding when their work pays off with cloud solutions that help our end-users solve their biggest business challenges.

To learn more about these instances and all of Amazon’s Elastic Compute offerings visit Visit to learn more about Intel’s solutions for Cloud Service Providers.

Published on Categories Cloud ComputingTags , , , ,
Rebecca Weekly

About Rebecca Weekly

Hyperscale Strategy and Execution, Intel Corporation Vice President, General Manager, and Senior Principal Engineer. Rebecca leads the organization that influences every aspect of Intel’s cloud platform solutions. Together they shape Intel’s development, production, and business strategy for Hyperscale Cloud Service Providers by driving strategic collaborations with key partners to ensure platform requirements meet customer needs. Rebecca is the Open Compute Project chair and president of the board and is on Fortune’s 40 Under 40 list of most influential people in technology. In her "spare" time, she is the lead singer of the funk and soul band, Sinister Dexter, and enjoys her passion of dance and choreography. She has two amazing little boys, and loves to run (after them, and on her own). Rebecca graduated from MIT with a degree in Computer Science and Electrical Engineering.