- Arm marks a fresh start for the world’s computing infrastructure with additions to its Arm Neoverse roadmap, including Neoverse V2 (codenamed “Demeter”).
- Neoverse V2 is the latest ARM core aimed at delivering leading-edge per-thread performance for cloud, hyperscale, and HPC workloads
- Industry leaders across cloud, 5G, HPC and edge choose Arm Neoverse as the compute foundation for their next-generation infrastructure solutions
The demand for data is insatiable, from 5G to the cloud to smart cities. As a society, we want more autonomy, information to drive our choices and habits, and connection—to people, stories, and experiences.
To meet these demands, tomorrow’s cloud infrastructure must handle the coming data explosion and effectively process increasingly complex workloads…while increasing energy efficiency and minimizing the carbon footprint. That’s why the industry is increasingly turning to the performance, power efficiency, specialized processing and workload acceleration enabled by Arm Neoverse to redefine and transform the world’s computing infrastructure.
Build what’s needed, not just what’s next
To date, Neoverse’s compute portfolio has enabled our partners to rapidly adopt Arm-based solutions to meet ever-changing customer and market needs. and today we are sharing new additions to the Neoverse roadmap built on scalable efficiency and technology leadership, while reaffirming our commitment to helping our partners continue their high pace of innovation.
We’ve heard from our Hyperscale and HPC customers that they need to keep increasing the performance of cloud workloads without requiring more power and space. Our answer is this Neoverse V2 platform (“Demeter”) with our latest V-series core and widely used ARM CMN-700 mesh interconnect. Neoverse V2 will deliver market-leading integer performance for cloud and HPC workloads and will introduce multiple security improvements to the ARMv9 architecture.
Today we already have several partners whose designs are based on Neoverse V2, including Nvidia, which uses V2 as the computational basis for their Grace data center CPU. Grace will combine the power efficiency of V2 with the power efficiency of LPDDR5X memory to deliver twice the performance per watt of servers powered by traditional architectures.
Additionally, as part of our ongoing investments in efficient performance and throughput, our next-generation N-Series product is in development and will be available to partners in 2023. This next N series The CPU will deliver generational gains in both performance and efficiency over the market-leading efficiency of N2.
Our E series CPUs are extremely versatile in terms of data plane processing, 5G RAN, edge networking and accelerators to name a few. To support this diversity, we deliver the Neoverse E2 platform, which combines the Cortex-A510 CPU with the scalable Neoverse CMN-700 and N2 system backplane. This enables the best of cloud technology in constrained applications: a scalable choice of core counts, SystemReady compatibility, and PCIe, CXL, IO, and interfaces. We are currently defining the next generation E-Series platforms.
Neoverse platforms are purpose-built to cover the full spectrum of accelerated infrastructure solutions. Specialized processing is the answer to reducing workload power consumption and meeting the increased compute demands of modern workloads. But you can’t do that with cores alone.
Cloud native software runs on ARM
We’ve long been leaders in the open source software community in optimizing full-stack solutions to run on Arm. You’ve heard us talk about Arm SystemReady and enabling a world of software that “just works”. From the architecture and IP to the libraries, runtimes and compilers, we got the maximum performance by using the full spectrum of infrastructure software.
Applications born in the cloud are based on microservices that communicate via APIs and take advantage of many modern software development tools and techniques, including containers and continuous delivery technologies with DevOps and agile methodologies.
With all major cloud providers offering Arm-based instances, we work with our cloud partners to optimize cloud-native software infrastructure, frameworks, and workloads. This includes contributions to widely used projects such as Kubernetes, Istio, and several CI/CD tools to provide native builds for the ARM architecture. We’ve enhanced machine learning frameworks like TensorFlow and cloud software workloads like open source databases, big data and analytics, and media processing. This work is done in collaboration with developers who contribute to open source communities so that all end users can build their next generation applications on Arm.
The strength of the Arm software ecosystem combined with the power of Neoverse platforms and leading high-performance fabrics such as AMBA CHI, UCIe and CXL give Arm partners a powerful recipe for building custom solutions from cloud to edge.
No other technology provider offers the combination of speed, breadth and technological innovation that enables our robust ecosystem of partners and developers to move quickly and build the systems of tomorrow.
Tailored solutions from cloud to edge
Arm Neoverse-based platforms are redefining what’s possible in cloud computing, delivering market-leading scalable efficiencies and allowing our partners the freedom to innovate across all areas of infrastructure. As a result, since its launch in 2018, we’ve seen rapid adoption of Neoverse as today all major public clouds offer instances powered by Neoverse.
In 5G RAN and wireless infrastructure, Arm offers leading performance with reduced power consumption and higher throughput, resulting in key TCO advantages. This allows our partners to customize products for applications and use cases ranging from small cells, macro cells to private networks. Through the Arm 5G Solutions Lab, we partner with leaders in the 5G ecosystem such as Dish Wireless, Google Cloud, Marvell, NXP and Vodafone to accelerate end-to-end 5G networks on Arm.
And with the launch of the 11th Gen Ampere Altra-based HPEProliant platform and initiatives like VMware’s Project Monterey, Red Hat supporting OpenShift on Arm, and SAP HANA moving their cloud infrastructure to Arm-powered AWS Graviton, we’re moving into more traditional businesses.
The future of computing infrastructure on arm
With more than 230 billion Arm-based chips shipped by our partners, we have the world’s largest computing footprint and a unique understanding of the entire computing spectrum. The next era of computing infrastructure technology rests on Arm’s performance and efficiency DNA, and with today’s additions to the Neoverse roadmap, we’re poised to deliver it.