ARM processors touch 70% of the global population. From the edge to the cloud, Arm is on track to touch 100 percent of the world’s shared data. Arm has announced Armv9, its first new ARM architecture in a decade. Arm’s solution to the future needs of AI, security and specialized computing is v9 released at March 30, 2021. News highlights:
- The new Armv9 architecture will form the leading edge of the next 300 billion Arm-based chips
- Advances specialized processing built on the economics, design freedom and accessibility advantages of general-purpose compute
- Delivers greater performance, enhanced security and DSP and ML capabilities
The latest Arm architecture updates promises to deliver the power of specialized processing with the economics, design freedom, and accessibility of general-purpose computing. Armv9 is promised to be code-friendly and secure. ARM has ongoing rollout of Armv9 to enabling partners to deliver best-in-class solutions for all workloads and applications and across all markets.
Explore the New Armv9 Decade web page tries to tell the ARM vision for next ten years as ARM company turns 30 years old. 30 years ago, Arm began with a vision of deploying its processor technology everywhere computing might happen and now 180 billion Arm-based chips shipped.
Armed for the Future: Armv9 Architecture Equips Chips with AI, Security, DSP Superpowers article says that in 2021 the keywords are artificial intelligence, the cloud, and security. Arm’s new Armv9 architecture directly enhances all of these and more thanks to what might sound like a paradoxical focus on specialized computing. Focusing first on security, Arm build on their hardware-enforced TrustZone technology with the new Confidential Compute Architecture (CCA), which provides an impenetrable firewall between apps running on the same OS, as well as ensuring the safety of data in transit from Arm-based server to Arm-based handheld. So we will see this new core in everything from smart phones to servers.
The updated architecture places a focus on secure execution and compartmentalisation. In addition to security features there are signal processing enhancements. Arm CPU and NPU (neural processing unit) devices are already replacing cloud-based AI infrastructure with low-power Edge compute, but enhancements to Matrix Multiplication (a key operation for machine learning) and new Advanced SIMD instructions and Scalable Vector Extension 2 (SVE2) technology boost not only ML but also DSP, VR and AR compute performance.
Arm broadens established footholds in the cloud through partnerships with Amazon (AWS Graviton processors), Microsoft (Azure Edge), VMware, and Ampere. In Armv9: The Future of Specialized Compute blog post Arm CEO Simon Segars explains why the launch of the Armv9 architecture signals a new era for Arm and its partners. We will have to wait for some time to see the silicon with the new core to become available.
More articles on ARMv9: