Today, ARM is announcing the Armv9 architecture, the first major change to the architecture since Armv8 was introduced a decade ago. The company says that Armv9 is going to be used in the next 300 billion ARM chips.
The firm also said that it’s expecting 100 billion ARM devices to ship in the next five years, and that at the current rate, 100% of shared data will be processed on ARM chips, whether it’s at the endpoint or in the cloud.
Simon Segars, chief executive officer, ARM:
“As we look toward a future that will be defined by AI, we must lay a foundation of leading-edge compute that will be ready to address the unique challenges to come. Armv9 is the answer. It will be at the forefront of the next 300 billion Arm-based chips driven by the demand for pervasive specialized, secure and powerful processing built on the economics, design freedom and accessibility of general-purpose compute.”
There are two key focuses for Armv9: AI and security. By the mid-2020s, ARM says that there will be over eight billion voice-assisted devices, and 90% of applications will include AI elements. ARM teamed up with Fujitsu to create Scalable Vector Extension (SVE), and now, SVE2 is part of Armv9 for better machine learning and digital signal processing.
On the security end of things, Armv9 is getting the Arm Confidential Compute Architecture (CCA), which shields data from access while it’s in use, protecting it at the hardware level. There will also be something called Realms, which applications can use outside of secure and non-secure areas.
As for when you’ll start seeing new chips being built on the Armv9 architecture, ARM didn’t say, but it’s safe to say that it’s going to be a little while.