Arm beefs up Arm Neoverse infrastructure platform

Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Watch here.

Arm has beefed up its Arm Neoverse product roadmap for processor designs that will fuel computing infrastructure across a variety of technologies into the future.

The roadmap features the addition of Arm Neoverse V2, codenamed Demeter, for years into the future. Neoverse V2 is the latest Arm core targeted at providing leadership in per-thread performance for the cloud, hyperscale, and high-performance computing workloads, said Arm CEO Rene Haas, during an online press event today.

“The demand for data is insatiable, from 5G to the cloud to smart cities,” said Chris Bergey, senior vice president of the Infrastructure Line of Business at Arm, in a blog post. “As a society we want more
autonomy, information to fuel our decisions and habits, and connection – to people, stories, and

Industry leaders across cloud, 5G, HPC and edge said during the event they have chosen Arm Neoverse as the compute foundation for the next generation infrastructure solutions. Nvidia executives talked about how they’re using Arm as part of their three-chip strategy — for central processing units, graphics processing units, and data processing units — with products such as the upcoming Grace CPU. Arm has its V-series, N-series, and E-series chip designs coming for various data-centric roles. N-series has been adopted by at least 20 chip companies for future chips, said Arm executive Dermot O’Driscoll.

To address these demands, the cloud infrastructure of tomorrow will need to handle the coming data
explosion and the effective processing of evermore complex workloads, Arm said, all while increasing power efficiency and minimizing carbon footprint. It’s why the industry is increasingly looking to the
performance, power efficiency, specialized processing and workload acceleration enabled by Arm
Neoverse to redefine and transform the world’s computing infrastructure.


MetaBeat 2022

MetaBeat will bring together thought leaders to give guidance on how metaverse technology will transform the way all industries communicate and do business on October 4 in San Francisco, CA.

Register Here

Building what’s needed, not just what’s next

Arm’s roadmap for years ahead.

To date, the Neoverse compute portfolio has enabled partners to adopt Arm-based solutions at a
rapid pace to address ever-changing customer and market needs. And today Arm shared new
additions to the Neoverse roadmap that are rooted in scalable efficiency and technology leadership,
while reinforcing commitment to support partners to continue their rapid pace of innovation.

Arm said hyperscale and HPC customers have said they needed to further push cloud workload performance without requiring more power and area. The response is the Neoverse V2 Platform
(Demeter) featuring the newest V-series core and the widely deployed Arm CMN-700 mesh interconnect. Neoverse V2 will deliver market-leading integer performance for cloud and HPC workloads and introduces several Armv9 architectural security enhancements.

Arm has multiple partners with designs based on Neoverse V2 in progress, one of which is Nvidia which is leveraging V2 as the compute foundation for their Grace datacenter CPU. Grace will combine the power efficiency of V2 with the power efficiency of LPDDR5X memory to deliver two times performance per watt over servers powered by traditional architectures. O’Driscoll noted Nvidia has already said Grace is coming in 2023.

In addition, as part of Arm’s ongoing investment in efficient performance and efficient throughput, the company’s next-generation N-Series product is in development and will be available to partners in 2023. This next N-Series CPU will deliver generational increases in both performance and efficiency over the efficiency of N2.

VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.