Amazon Web Services (AWS) today announced the availability of new Amazon Elastic Compute Cloud (Amazon EC2) instances based on 4th generation Intel Xeon Scalable processors customized. This announcement is the latest among a large number of 4th generation Xeon-based instances that offer one of the most competitive cost of operation (TCO) in the industry and the tightest integration of accelerators in any CPU to support workloads such as artificial intelligence , database, networking and business applications.
Intel Xeon, the fourth generation processors for cloud users
“Intel has worked closely with AWS to bring 4th generation Xeon processors to cloud users, many of whom have been able to benefit first – publicly and privately – from their performance and value. Today we are happy to offer the same value to cloud users around the world”. he claimed Lisa Spelman, Intel corporate vice president e general manager, Xeon Products and Solutions Group.
Because it is important? The new Amazon EC2 M7i-flex and M7i instances make fourth-generation Xeon acceleration engines mass-available through AWS global presence. Integrated accelerators such as Intel Advanced Matrix Extensions (Intel AMX) offer an important alternative for those users who have a growing demand for AI workloads.
4th Generation Xeon with AMX can also meet the inference performance needs of large language models (LLMs) below 20 billion parameters, making it cost-effective and sustainable to run on a generic infrastructure.
What Intel and AWS offer
More broadly, Intel and AWS offer users a variety of product options to best meet their workload, performance, and cost needs, along with the ease and flexibility to meet future digital infrastructure needs.
About AWS Instances: M7i-flex and M7i instances are available in the following AWS Regions: US East (Ohio), US East (N. Virginia), US West (Oregon) ed Europa (Irlanda). M7i-flex instances offer: The easiest way to achieve price and performance benefits for most general purpose workloads.
Design to easily run general purpose workloads including web and application servers, virtual desktops, batch processing, microservices, databases and business applications. Up to 19% higher price/performance than M6i instances.
What else do M7i instances offer? Benefits in terms of price/performance ratio for major workloads, such as large database and application servers, server per gaming, CPU-based machine learning and video streaming. Larger instance sizes (up to 192 vCPUs and 768 GB of memory).
New integrated accelerators that offer greater efficiency in offloading and accelerating data operations, optimizing performance for database, encryption and compression, and queue management workloads. Up to 15% higher price/performance than M6i instances.