Accelerating the next generation cloud-to-edge infrastructure

Ten years ago, Arm set its sights on deploying its compute-efficient technology in the data centre with a vision towards a changing landscape that would require a new approach to infrastructure compute.

Chris Bergey, SVP and GM, Infrastructure Line of Business, Arm, writes:

That decade-long effort to lay the groundwork for a more efficient infrastructure was realised when we announced Arm Neoverse, a new compute platform that would deliver 30% year-over-year performance improvements through 2021. The unveiling of our first two platforms, Neoverse N1 and E1, was significant and important. Not only because Neoverse N1 shattered our performance target by nearly 2x to deliver 60% more performance when compared to Arm’s Cortex-A72 CPU, but because we were beginning to see real demand for more choice and flexibility in this rapidly evolving space.

Now more than ever, Arm is focused on partnering with our ecosystem to understand the problems they are trying to solve, and delivering the high-performance, secure platforms needed to enable the infrastructure of tomorrow.

The velocity of Arm Neoverse 

Neoverse N1 solutions are the first steps towards a new infrastructure, and are now powering innovations from supercomputers to increasing deployments in the world’s largest data centers, and all the way to the edge.

To accelerate this infrastructure transformation and enable new levels of innovation, we are announcing the next phase for Neoverse with the addition of two new platforms on our product roadmap. For the first time today, we are introducing the Arm Neoverse V1 platform, and the Neoverse N2, our second-generation N-series platform.
 

(Image removed)

 

Ultimate performance: Neoverse V1 platform introduces SVE

The introduction of Neoverse V1 platform is the first in the V-series and delivers a single-threaded performance uplift of more than 50%[1] over N1, our fastest for applications more reliant on CPU performance and bandwidth. Importantly, Neoverse V1 supports Scalable Vector Extensions (SVE), bringing massive potential for markets such as high-performance cloud, HPC, and machine learning.

SVE enables execution of SIMD integer, bfloat16, or floating-point instructions on wider vector units using a software programming model that’s agnostic to the width of the unit. With SVE, we are ensuring portability and longevity of the software code, along with efficient execution.

Read more on the benefits of SVE in this blog by Brent Gorda.

Doubling down: Neoverse N2 platform delivers scalable performance

In an expanding market, we hear from our partners often that scalability is key. Neoverse N2 enables this by providing an even higher-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 offers 40%[1] higher single-threaded performance, compared to Neoverse N1, and retains the same level of power and area efficiency as Neoverse N1.

The building blocks for innovation and software that “just works”

One of our key goals is to provide partners the building blocks they need for continued innovation and design flexibility. Critical to this mission are our chip-level interfaces, which provide the opportunity to design system-level solutions. Our investment in both CCIX and CXL ensures our ecosystem can deliver relevant technology quickly and efficiently. Now not only are we providing leading edge cores, we are enabling partner solutions with fast fabric and high core count scalability.

In addition to our interconnect technologies, we see tremendous opportunity ahead for Neoverse and its supporting software ecosystem. But, that requires industry standards and initiatives like Project Cassini which aim to deliver a frictionless software developer experience. Through standards, platform security, and reference implementations, Project Cassini enables the industry to confidently deploy software on Arm that will “just work” (don’t miss Arm DevSummit in a few weeks for new details on this!).

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 we once needed to nudge along are becoming self-supported and we’re seeing this evolve even further with commercial ISV applications.

Tip of the iceberg

A lot has happened in just the year I’ve been at Arm. Neoverse technologies are appearing in new server and SoC designs across the infrastructure world, and software and tools support has flourished. Developers see not only the performance and efficiency gains that Neoverse can deliver, but the broader design freedom and flexibility that comes with a new way of thinking about deploying infrastructure.

Based on that collaboration and hard work, I’m excited about what our ecosystem partners will be able to achieve in the future. The velocity of Neoverse has increased the pace of innovation in the infrastructure. What amazing things can we achieve together in the coming years?

[1] Uplift is based on IPC assuming constant process and frequency.



Read more

Looking for something specific?