Our Next Step in Preparing the Cloud for 1T Intelligent Devices
By: Drew Henry, senior vice president and general manager, Infrastructure Line of Business, Arm
- Two new complete infrastructure-class platforms for faster time-to-market and optimal design points for cloud to edge applications in the era of 5G
- The Arm Neoverse N1 platform, optimized for 7nm process technology and delivering a 2.5x performance improvement on key cloud workloads
- The Arm Neoverse E1 platform, a high-efficiency throughput platform, delivering a 2.7x improvement in throughput performance over previous generations
Last October, we announced Arm Neoverse, the cloud to edge infrastructure foundation for a world of a trillion intelligent devices. Since then, momentum continued to build across our ecosystem with announcements from Huawei and HPE (the first Arm Top500 supercomputer!). Of course the AWS Graviton stunned the world and I shared my thoughts on that announcement in my last blog. These are all examples of the great work our industry is doing to address the opportunities coming with 5G and a future that foresees the promise of the IoT.
All these intelligent devices mean data consumption models are going to change over the next several years, driving a shift in the way information will be stored, processed, and managed. We are moving from an internet model that distributes video (Netflix and YouTube) to one that consumes, manages and processes information produced at the edge. When you consider these factors, and the end of Moore’s Law, the days of one size fits all computing are over. We are entering a new era driven by a greater diversity of specialized compute and the need for flexible architectures tailored to meet application specific needs.
Our two new Arm Neoverse platforms, the Neoverse N1 platform and the Neoverse E1 platform, have been developed specifically to address this new infrastructure model. Combined with Arm’s unique business model and platform enablement capabilities, we’re enabling broad innovation, extreme scale, and diverse compute solutions from our partner ecosystem.
Arm Neoverse N1: Accelerating the transformation to a scalable cloud to edge infrastructure
With the Neoverse N1 platform, we’re taking generational infrastructure-class compute performance to heights not seen in the industry today, exceeding even our own initial expectations, with a staggering +60%[i] integer performance improvement and 2.5x more performance on key cloud workloads. And to ensure our partners maximize the efficiency, performance, and area benefits of the Neoverse N1 platform, we have optimized for leading-edge 7nm process technology, allowing our partners to realize the benefits of highly advanced silicon manufacturing.
Going beyond raw compute performance, the Neoverse N1 platform was built from the ground up with infrastructure-class features including server-class virtualization, state-of-the-art RAS support, power and performance management, and system level profiling. The platform also includes a coherent mesh interconnect, industry-leading power efficiency, and a compact design approach for tighter integration, enabling scaling from 4- to 128-cores. This incredible scalability gives our partners the flexibility to build diverse compute solutions by adding accelerators or other features with their own on-chip custom silicon. All of this enables our partners to deliver solutions with lower total cost of ownership (TCO) for infrastructure customers.
For more details on the N1 platform, read our blog here.
Arm Neoverse E1: Empowering the infrastructure to meet next-generation throughput demands
The explosion of data will require more than just increased compute performance; a second important dimension is moving the data around to be processed, analyzed, filtered, and stored. As the world transitions to 5G and beyond, network infrastructure is undergoing a significant transformation.
The Neoverse E1 platform was uniquely designed to enable the transition from 4G to a more scalable 5G infrastructure with more diverse compute requirements. Featuring an intelligent design for highly-efficient data throughput, the Neoverse E1 achieves 2.7x more throughput performance, 2.4x more throughput efficiency, and over 2x more compute performance compared to our previous generations. It also delivers scalable throughput for edge to core data transport, supporting everything from a sub-35W base station all the way through to a multi-100GB router.
Thanks to our diverse software ecosystem, supporting legacy networking software stacks and leading open source software-defined networking (SDN) solutions, the entire network infrastructure is ready to take full advantage of the Neoverse E1 platform.
For more details on the E1 platform, read our blog here.
Accelerating the Arm ecosystem
Speaking of our Neoverse software ecosystem, it has never been more robust thanks to our decade-long investments, resulting in unprecedented market readiness to enable seamless deployments of Arm-based infrastructure platforms. Over the past 18 months, the momentum and collaboration in support of the Neoverse platform I have seen among the open source community and developers is like nothing I have ever experienced in my 25+ years in this industry. Kevin Ryan from my team can tell you more details around recent software ecosystem progress in his blog.
The world of a trillion connected devices and its surge of new data compute requirements are closer than you think. Our ecosystem, business model, and technology leadership has positioned the Arm architecture to be the preferred choice in building the next-generation infrastructure. Announcing these two new platforms today is more than just the launch of new products. They represent a seminal moment of change for a market that has been deprived of choice and economic flexibility for more than 20 years.
As I mentioned, we are entering a new era of compute needs. Only Arm has a roadmap that is undaunted by the end of Moore’s Law and will deliver generational performance gains of 30% through 2021, combined with the freedom for our partners to customize and innovate based on market needs.
- Visit the Neoverse N1 and Neoverse E1 product pages for additional details
- Learn about Arm ServerReady
- Learn more about our work with developers on the Arm Infrastructure Community
Supplemental Quote Sheet:
“Cadence has collaborated closely with Arm to ensure that its full-flow digital implementation and signoff tools, the Cadence Verification Suite, and design IP are optimized for Arm’s new Neoverse N1 CPU for next-generation cloud-to-edge infrastructure,” said Dr. Anirudh Devgan, president of Cadence. “We also worked with Arm on the delivery of the Neoverse N1 System Development Platform, which is based on the Neoverse N1 CPU and Cadence IP and was implemented and verified using a full Cadence tool flow.”
“The advent of 5G and explosion in the number of intelligent devices requires cloud infrastructure to transform to a more distributed model and support new workloads. Canonical is excited to deliver open source solutions like Ubuntu Server 18.04, Charmed OpenStack, CEPH, and Charmed Distribution of Kubernetes on Arm to help drive scalable Neoverse IP and products that are tested across the widest range of clouds and systems; from public to private clouds, virtualized infrastructure and through to the edge,” said Stephan Fabel, director of Product at Canonical.
“Docker and Arm are collaborating on our shared vision for providing distributed computing solutions from cloud to edge. Docker’s industry-leading container platform including Docker Hub has become integral to the Arm software ecosystem, where tens of thousands of containerized Arm applications are already being used by developers. The Docker platform is the only solution that covers the complete container-based software development lifecycle from dev to production, accelerating the adoption of Arm Neoverse-based solutions by our collective customers,” said David Messina, EVP Strategic Alliances at Docker.
“As software and hardware combine to bring us everything from smartphones to supercomputers, from medical instruments to agricultural sensors, and from base stations to servers, the ability to deploy software and fix bugs quickly is essential when delivering new features to market,” said Brad Rydzewski, co-founder, Drone I/O. “Drone I/O looks forward to helping developers create software experiences for the Arm server and edge computing ecosystem based on next-generation Arm Neoverse platforms.”
“NGINX shares the same core idea with Arm, which is to offer lightweight, high-performing technology with no bloat and efficiency,” states Christine Puccio, VP, Global Strategic Alliances & Partnerships at NGINX. “Through our NGINX Application Platform, we're enabling partners like Arm to deliver more compute density with no sacrifice to best-of-class performance. We truly look forward to a continued collaboration with the Arm ecosystem on next-generation solutions for IoT and distributed cloud-based environments."
"We dove into the Arm datacenter ecosystem three years ago with a vision for diverse, customized hardware solutions that could be deployed in thousands of locations, from the centralized cloud to the far edge of the network. With Neoverse, Arm is delivering on that promise by pairing market-leading performance and outstanding efficiency with a vibrant ecosystem that thrives on solving big challenges," said Zac Smith, CEO at Packet.
“Rancher and Arm have partnered to create a Kubernetes-based computing platform for IoT and edge nodes. We are enthusiastic about working with the Arm ecosystem on next-generation Arm Neoverse-based solutions to deliver increased levels of performance and throughput for edge to cloud deployments,” said Sheng Liang, co-founder and CEO at Rancher Labs.
“Red Hat is committed to supporting customer choice in computing architectures, backed by our multi-architecture strategy, to help our customers drive open innovation on a wide range of processors and hardware configurations including Arm-based technologies,” said Jon Masters, Chief Arm Architect at Red Hat. “We look forward to continuing our years-long collaboration with Arm and its partners as we explore the opportunities presented by the Arm Neoverse N1 Platform, especially around hyperscale, edge and high-performance computing,” said Jon Masters, Chief Arm Architect at Red Hat.
“Arm’s infrastructure IP and platform enablement approach allows the ecosystem to deliver a range of solutions with just the right I/O and processor capabilities needed for a particular workload. SUSE is excited provide enterprise-grade SUSE Linux Enterprise Server for Arm subscriptions directly to customers who can benefit from the diversity of Arm Neoverse platforms from the edge to the core to the cloud. SUSE looks forward to continued collaboration with the latest Arm Neoverse product innovations that will accelerate the momentum for Arm in the infrastructure market,” said Brent Schroeder, CTO Americas, SUSE.
“Leading semiconductor and system companies rely on Synopsys tools and interface IP for their most advanced cloud, infrastructure, and networking designs,” said Deirdre Hanford, co-general manager, Synopsys Design Group. “Synopsys and Arm have been collaborating for more than 25 years to enable mutual customer success, and our latest collaboration delivers optimized support for Neoverse platforms, where our Fusion Design Platform, Verification Continuum Platform, and DesignWare Interface IP have already enabled tapeout success for early adopters of Arm’s Neoverse-N1 platform for cloud-to-edge infrastructure computing. Designers can quickly implement Neoverse N1 processor-based designs using our optimized QuickStart Implementation Kit (QIK).”
“Arm and TSMC have collaborated to develop the Arm Neoverse N1 SoC on TSMC’s industry first and leading 7nm FinFET process technology,” said Suk Lee, senior director of Design Infrastructure Management Division, TSMC. “We look forward to a continued partnership with Arm to drive the cloud-to-edge solution capabilities of Arm Neoverse ecosystem and enable our mutual customers to achieve success in 5G, AI and other evolving application areas.”
“We are excited to see Arm deliver on the Neoverse platform roadmap which spans solutions from cloud to edge. As 5G and IoT drive an increasingly distributed cloud and edge compute model, we look forward to bringing the power of ESXi to the edge on 64-bit Arm standardized platforms, and continuing to manage and secure Arm-based IoT devices with VMware Pulse IoT Center.” Mimi Spier, vice president, IoT and Edge Business Unit, VMware.
“The diversity of compute applications from hyperscale to the edge require data to be processed seamlessly among heterogeneous components. The Arm Neoverse N1 CCIX-enabled platform, combined with the Xilinx Alveo U280 CCIX-enabled accelerator card, provides an ideal foundation for smart offload and the next generation of purpose-built infrastructure solutions,” said Gaurav Singh, corporate vice president, Silicon Architecture and Verification at Xilinx.
Performance and benchmark disclaimer
This benchmark presentation made by Arm Ltd and its subsidiaries (Arm) contains forward-looking statements and information. The information contained herein is therefore provided by Arm on an "as-is" basis without warranty or liability of any kind. While Arm has made every attempt to ensure that the information contained in the benchmark presentation is accurate and reliable at the time of its publication, it cannot accept responsibility for any errors, omissions or inaccuracies or for the results obtained from the use of such information and should be used for guidance purposes only and is not intended to replace discussions with a duly appointed representative of Arm. Any results or comparisons shown are for general information purposes only and any particular data or analysis should not be interpreted as demonstrating a cause and effect relationship. Comparable performance on any performance indicator does not guarantee comparable performance on any other performance indicator.
Any forward-looking statements involve known and unknown risks, uncertainties and other factors which may cause Arm’s stated results and performance to be materially different from any future results or performance expressed or implied by the forward-looking statements.
Arm does not undertake any obligation to revise or update any forward-looking statements to reflect any event or circumstance that may arise after the date of this benchmark presentation and Arm reserves the right to revise our product offerings at any time for any reason without notice.
Any third-party statements included in the presentation are not made by Arm, but instead by such third parties themselves and Arm does not have any responsibility in connection therewith.
[i] Spec int 2017 estimate, base, rate=1
做為運算及連網革命的核心，Arm 的技術正改變著人們生活及企業運作的方式。Arm 先進的低功耗處理器設計與軟體平台，已促成 2,000 億顆晶片的先進運算，我們的技術安全地驅動包含感測器、智慧型手機甚至於超級電腦等各式應用的電子產品。Arm 攜手超過 1,000 家的技術合作夥伴，將前端的設計、安全、管理，全面應用在從晶片至雲端所有連結 AI 運算的領域。
所有資訊都「依目前情況」提供，且並不帶保證或代表性。此一文件可以自由分享，但不得修改且必須註明出處。Arm是Arm Limited(或其子公司)的商標或註冊商標。所有其他品牌或產品名稱乃為所屬個別公司之財產。© 1995-2021 Arm Group