Arm, global provider of compute-efficient technology for the data center environment, is announcing the next phase for its ‘Neoverse’ compute platform with the addition of two new platforms on its product roadmap. For the first time, Arm is now introducing the Arm Neoverse V1 platform, and the Neoverse N2, the second-generation N-series platform. Arm Neoverse solutions would cater to the requirements of hyperscale/cloud computing, HPC, 5G, and the edge.
Neoverse V1 supports Scalable Vector Extensions (SVE), bringing massive potential for markets such as high-performance cloud, HPC, and machine learning. The introduction of this Neoverse V1 platform is the first in the V-series. It would deliver a single-threaded performance uplift “of more than 50%” over N1, meant for applications more reliant on CPU performance and bandwidth.
SVE enables execution of single-instruction multiple dispatch (SIMD) integer, bfloat16, or floating-point instructions on wider vector units. It uses a software programming model that’s agnostic to the width of the unit. With SVE, Arm would ensure portability and longevity of the software code, along with efficient execution.
Neoverse N2 provides an a high-performing computing solution to address scale-out performance needs of applications across a range of use cases, from cloud to SmartNICs and enterprise networking, to power-constrained edge devices.
In addition, Neoverse N2 would offer “40% higher single-threaded performance, compared to Neoverse N1.” Next to that, it would retain the same level of power and area efficiency as Neoverse N1.
Industry Standards, Project Cassini
Arm sees tremendous opportunity ahead for Neoverse and its supporting software ecosystem. But, that requires industry standards and initiatives like Project Cassini which aim to deliver frictionless software developer experience. Through standards, platform security, and reference implementations, Project Cassini would enable the industry to “confidently” deploy software on Arm that will ‘just work.’
Beyond that though, Arm continues to enable foundational infrastructure software. Operating systems and hypervisors, Xen, KVM, Docker containers, and, increasingly, Kubernetes have all announced support for Arm. The projects Arm once needed to nudge along are becoming self-supported and now seeing this evolve with commercial ISV applications.
Neoverse technologies are appearing in new server and SoC designs across the infrastructure world, and software and tools support has flourished. Arm claims that developers see not only the performance and efficiency gains which Neoverse can deliver. They would also appreciate the broader design freedom and flexibility that comes with a new way of thinking about deploying infrastructure. The velocity of Neoverse has increased the pace of innovation in the infrastructure, according to Arm.
Arm has been acquired by NVIDIA this month. NVIDIA has acquired Arm from SoftBank (SBG) in a transaction valued at $40 billion. The combination brings together NVIDIA’s leading AI computing platform with Arm’s vast ecosystem. SoftBank will remain committed to Arm’s long-term success through its ownership stake in NVIDIA, expected to be under 10 percent.
As part of NVIDIA, Arm would continue to operate its open-licensing model. It would also maintain the global customer neutrality that has been foundational to its success, with 180 billion chips shipped to-date by its licensees. Arm partners would also benefit from both companies’ offerings, including NVIDIA’s numerous innovations.