Internet of Things
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
L
ast 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. 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 specialised 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 per cent integer performance improvement and 2.5x more performance
on key cloud workloads. And to ensure our partners maximise the efficiency, performance, and area benefits of the Neoverse N1 platform, we have optimised for leading-edge 7nm process technology, allowing our partners to realise 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 virtualisation, 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.
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, analysed, 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.
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 per cent through 2021, combined with the freedom for our partners to customise and innovate based on market needs.
www.arm.com 32 March 2019 Components in Electronics
www.cieonline.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52
