In connection: Arm may not have the same desktop footprint as Intel or AMD, but when it comes to smartphones, servers, and even new MacBooks, the company's processor architecture is essentially unmatched. Despite its ubiquity, the Arm architecture has not seen massive generational upgrades since version 8, which was released back in October 2011.
However, that will change. The semiconductor company has officially presented Armv9, ushering in a new era of processor architecture that is supposed to meet the growing computing requirements in the areas of data security and artificial intelligence.
Arm CEO Simon Segars is initially focusing on the latter, saying Armv9 is the "answer" to a future "defined by AI". To directly address this inevitability, Segars claims his company must lay a foundation for "leading computing functions".
How exactly? The scalable vector extension (SVE). For those who don't know, the SVE is the technology at the heart of the world's fastest supercomputer, Fugaku. Arm teamed up with its creator Fujitsu to develop SVE2 for Armv9. In theory, SVE2 should enable next generation machine learning and digital signal processing capabilities.
As for how v9 goes about security, all you have to do is look at Arm's new Confidential Computer Architecture (CCA). The company describes the functionality of CCA as follows:
Confidential computing protects parts of code and data from being accessed or modified while in use, even from privileged software, by performing calculations in a hardware-based secure environment.
Through the CCA and so-called "dynamically created areas", Armv9 can protect confidential data from prying eyes while it is actively used, "at rest" or transferred to another location.
Last but not least, Armv9 achieves massive CPU performance increases of over 30 percent. Arm expects these enhancements to be completed in the "next two generations" of mobile and server CPUs.
Arm hopes that all these generation upgrades will get his architecture on the right track to process "100 percent of the world's shared data" at least to a certain extent – be it at the "endpoint" or somewhere in the cloud.