Amazon Web Services (AWS) has announced the public availability of Amazon EC2 M6i instances, which adds x86-based computing choices to the 6th generation EC2 instance range. The new instance m6i.32xlarge has 128 vCPUs and 512 GiB of memory, which is a 33 percent increase over the biggest M5 instance, while Elastic Fabric Adapter provides a 20 percent boost in memory bandwidth per vCPU.
The EC2 M6i instances are powered by Intel’s Xeon Scalable central processor units, known as Ice Lake, and are designed to run applications that use x86 instructions. Intel’s Xeon Ice Lake is Intel’s first 10nm server chip, which is now equipped with newer AI instruction support as well as using higher speed memory with the memory controller improvements.
M6i has a 3.5 gigahertz all-core turbo frequency, which results in a 15 percent price-performance improvement over Amazon’s prior fifth-generation instances. Also similar to M5 instances, M6i instances feature a 4:1 ratio of memory to vCPU. These instances also support new Intel Advanced Vector Extensions (AVX 512) instructions for faster execution of cryptographic algorithms.
Amazon Elastic Compute Cloud (Amazon EC2) is a cloud computing service that offers safe, scalable compute power. It’s intended to make web-scale cloud computing more accessible to programmers. This houses several instances that include Compute Optimized instances (C6g, C6gn, C5), Memory-optimized instances (R5, R6g,X1), Accelerated computing instances (G4ad, P3), Storage optimized instances (H1, D2,D3) and General purpose instances (T3a, M6i, A1). Amazon explains that the “i” suffix denotes instances based on Intel processors, while “a” suffix is for AMD processors and “g” suffix for Graviton instances that use Amazon’s Arm-based architecture.
Gone are the days when Intel or Arm led to market dominance. Unlike Google and Facebook that received the X86 server processors earlier in the product cycle, AWS relied on Intel Xeon and AMD Opteron compute to run its cloud architecture.
According to AWS Chief Evangelist Danilo Poccia, the new SAP-Certified M6i instances will largely act as the new workhorses for a bunch of general-purpose computing workloads. Examples include web and application servers, containerized applications, microservices, small data stores, Microsoft Exchange, SharePoint and MySQL applications, SQL Server and PostgreSQL databases, and even some types of high-performance workloads like computational fluid dynamics.
M6i instances are built on the AWS Nitro System, a combination of dedicated hardware and lightweight hypervisor that delivers virtually all of the compute and memory resources of the host hardware to your instances, and are designed to provide a balance of compute, memory, storage, and network resources.
Customers may get up to 50 Gbps of networking speed and 40 Gbps of bandwidth to the Amazon Elastic Block Store with M6i instances, which is twice as fast as M5. They can use the 32xlarge size of the Elastic Fabric Adapter, to avail of low latency and highly scalable inter-node communication benefits.
M6 instances are now offered as on-demand purchases, savings plans, reserved instances, spot instances, dedicated instances, or dedicated hosts in the US East, US West, Frankfurt, Ireland, and Singapore regions.
Currently, M6i instances are available in nine sizes (the m6i.metal size is coming soon):
|Name||vCPUs||Memory(GiB)||Network Bandwidth(Gbps)||EBS Throughput(Gbps)|
|m6i.large||2||8||Up to 12.5||Up to 10|
|m6i.xlarge||4||16||Up to 12.5||Up to 10|
|m6i.2xlarge||8||32||Up to 12.5||Up to 10|
|m6i.4xlarge||16||64||Up to 12.5||Up to 10|