The company specializing in processor design announced Armv9, the first new Arm architecture for a decade.

The new development aims to meet the market needs of higher performance, greater security and dedicated functionality of DSP, machine learning and artificial intelligence, for l’ubiquitous computing.

The company also pointed out that the new design is based on the success of the current Armv8, which already marks a level of performance-per-watt in the state of the art, in every sector and within the sphere of computing.

The number of distributed Arm-based chips continues to accelerate, with more than 100 billion devices shipped over the last five years, underlined the processor specialist, who added that, at the current rate, 100 percent of the data shared in the world will soon be processed on Arm in

This pervasiveness also entails the increased responsibility on the part of Arm to provide better safety and performance, as well as additional new features.

The new capabilities in Armv9 will accelerate the transition from general-purpose calculation to the most specialized in each application, at a time when artificial intelligence, the Internet of Things (IoT) and 5G are having a

To address what Arm defines as today’s greatest technological challenge, protecting data, the Armv9 roadmap introduces the Arm Confidential Compute Architecture (CCA). The Confidential computing protects portions of code and data from access or modification while they are in use, even from software that has privileges, by performing the calculation in a secure hardware-based environment.

The CCA Arm will introduce the concept of dynamically created Realm, usable by all applications, in an area that is separated from both the safe and the unsafe world. For example, Arm explained, in business applications Realm can protect commercially sensitive data and code from the rest of the system while they are in use, at rest, and in transit.

Moreover, the ubiquity and range of artificial intelligence workloads require more diverse and specialized solutions. According to Arm, it is estimated that there will be more than eight billion devices assisted by the artificial intelligence in use by the mid-2020s and 90% or more of applications on the device will contain artificial intelligence elements along with interfaces based on it (e.g. voice).

To address this growing need, Arm has collaborated with Fujitsu to create Scalable Vector Extension (SVE) technology, which is the heart of Fugaku, the fastest supercomputer in the world. Based on that work, Arm has developed SVE2 for Armv9 to allow better machine learning and digital signal processing (DSP) capability in a wider range of applications.

SVE2 improves the processing capacity of 5G systems, virtual reality and increased, and machine learning workloads running locally on CPUs, such as image processing and smart home applications.

In the coming years, Arm will further expand the artificial intelligence capabilities of his technology with substantial improvements in the multiplication of the matrix within the CPU, as well as ongoing innovations in Mali GPUs and Ethos NPUs.

Armv9 will also increase the performance of the CPU. However, Arm said, as the industry moves from general-purpose computing to specialized ubiquitous computing, the annual double-digit increases in CPU performance are not sufficient.

In addition to improving specialized processing, Arm’s Total Compute design methodology will accelerate overall computing performance through system-wide hardware and software optimizations and increases in the performance of use cases.

By applying the Total Compute design principles through the entire IP portfolio of automotive solutions, clients, infrastructure and IoT, Armv9 system-wide technologies will embrace the entire range as well as improve individual areas.

In addition, Arm is developing several technologies to increase frequency, bandwidth and cache size, and reduce memory latency to maximize Armv9-based CPU performance.

Leave a Reply

Your email address will not be published.

You May Also Like
Read More


Interactive Media, developer of software for telecommunications, conversational AI and customer experience applications, has annihilated that its conversational…