Neoverse N1 makes debut in new AWS cloud instances
By Chris Bergey, SVP and GM, Infrastructure Line of Business, Arm
Many of you will remember one year ago on stage at re:Invent, Peter Desantis announced all new AWS EC2 A1 instances powered by Arm Neoverse-based AWS Graviton processors, delivering up to 45% cost savings for scale-out applications. For modern cloud datacenters, this was the realization of the benefit of bringing new, more efficient computing choices to an otherwise x86-dominated market.
Over the last 12 months, we’ve seen thousands of customers such as Ancestry.com, CBS, LG Electronics, Nielsen, SmugMug, and others across various industries leveraging the AWS EC2 A1 instances to deploy applications, like running web servers such as NGINX Plus and containerized microservices on Docker, and benefiting from a growing software ecosystem as numerous AWS services have been made available. In addition, bare metal Arm-based EC2 instances were recently made available for use cases requiring access to physical resources and low-level features which are intended to directly run on the hardware.
The fun is just beginning! Today, in his opening keynote at AWS re:Invent, CEO Andy Jassy announced the next-generation Arm Neoverse-based Graviton processor, Graviton2, which will power a new generation of instances in the AWS general purpose (M), compute optimized (C), and memory optimized (R) portfolios. The new M6g Graviton2-based instances deliver up to 40% better price performance over the Intel Xeon-based 5th generation instances, meaning these instances provide the high-performance required for demanding, compute-heavy and memory-intensive workloads. A preview of the M6g instances is available now for testing, and availability of the other instances is expected in 2020.
More specifically, these new Graviton2-based instances are the first-to-market using the Arm Neoverse N1 platform! In fact, in the development of the N1 platform, we knew that if we wanted to design a microarchitecture optimized for cloud computing, we needed to work with the cloud experts. Beginning in early phases of the N1 design, Arm engineers worked side by side with Annapurna Labs, a wholly owned AWS subsidiary responsible for building the Graviton processor family. The cloud expertise that Annapurna Labs brought to the table helped our engineering teams optimize the N1 platform design that is changing the way we think about cloud computing today.
For Arm, today’s announcement shows our deepened commitment and investment in the global internet infrastructure since the launch of Neoverse in 2018 and followed by the announcement of two new complete infrastructure-class platforms with N1 and E1. As we said then, Arm is in a unique position because we understand the implications of an evolving infrastructure, which is driven by the work that many of our ecosystem partners are doing and the solutions they are building. The new Graviton2-based instances are a perfect example of what we mean by this.
At Arm, we have a responsibility to enable our partners with the right compute for the right applications. By delivering the N1 design to partners like AWS who customize it to best fit their needs, we open doors for what cloud-optimized compute can do in powering a world of a trillion devices.
The team at Annapurna Labs set out on a journey to build great products for the next-generation cloud and Graviton2 is an important milestone towards the future of cloud computing. I, along with the entire team at Arm, am so proud to be part of the collaborative efforts across AWS, Annapurna Labs, and the Arm ecosystem as we continue to transform the infrastructure, from edge to cloud, for a world of a trillion connected devices.
Arm technology is at the heart of a computing and data revolution that is transforming the way people live and businesses operate. Our energy-efficient processor designs and software platforms have enabled advanced computing in more than 190 billion chips and our technologies securely power products from the sensor to the smartphone and the supercomputer. Together with 1,000+ technology partners we are at the forefront of designing, securing and managing all areas of AI-enhanced connected compute from the chip to the cloud.
All information is provided "as is" and without warranty or representation. This document may be shared freely, attributed and unmodified. Arm is a registered trademark of Arm Limited (or its subsidiaries). All brands or product names are the property of their respective holders. © 1995-2021 Arm Group.