
IBM unveiled a mainframe chip that runs both Arm and Z workloads on the same cores.
It switches between instruction sets in nanoseconds.
This is the first dual-architecture mainframe processor ever built.
What happened
IBM announced a next-generation mainframe processor that can natively execute both its own instruction set and Arm's, switching between the two in nanoseconds. It is the first dual-architecture mainframe processor ever built.
Why it matters
This lets enterprises run Arm-native Linux software, including AI frameworks, alongside z/OS transaction workloads that anchor banks, insurers, and governments. It may be the most consequential change to mainframe architecture in decades.
What to watch
The chip will power the next generation of IBM Z and LinuxONE systems, with IBM's chief product officer calling it one of the most powerful commercially available dual-architecture processors.
Ask the AI about this article →
IBM's announcement at Hot Chips marks a shift in mainframe design, which has traditionally been locked into proprietary architecture. By supporting Arm natively, the new chip opens the door to a vast ecosystem of Arm-native Linux software, including AI frameworks that are increasingly central to modern infrastructure. This could reduce the need for separate systems, letting banks and governments run modern AI alongside their core transaction processing on the same hardware.
The dual-architecture capability, switching in nanoseconds, suggests that mixed workloads can be handled without significant performance penalties. The company's chief product officer emphasized the processor's power and commercial availability, positioning it as a major step for IBM's mainframe line. The focus on Arm is notable, as it reflects the growing influence of Arm-based chips in data centers, a trend that IBM is now embracing.
The move may signal a broader strategy to make mainframes more adaptable to the changing software landscape, particularly as AI becomes more embedded in enterprise operations. Whether this will convince existing users to upgrade remains to be seen, but the technical foundation appears designed to bridge the gap between legacy z/OS and modern cloud-native workloads.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Israeli startup DataAgent Ltd
SK Hynix presented a custom HBM concept at SEMICON Taiwan 2026, where compute functions are placed in the base…

Taoyuan is positioning itself as a northern hub for AI data centers (AIDC), citing the Tatan area and an LNG c…

The U.S. Department of Defense announced on August 31 that it has deployed ChatGPT Mil, a customized version o…

Nvidia reported earnings that were both remarkable and boring, reflecting its focus on avoiding a consolidated…

Anthropic has agreed to a $35bn cloud-computing contract with Lambda, a Nvidia-backed cloud provider
