IBM’s Next Mainframe Chip Runs Arm and IBM Z Instructions on Every Core

Unveiled at Hot Chips, the 2nm processor has 11 cores above 5.7GHz, each able to execute Arm and IBM Z instructions concurrently. It's the first chip from IBM's partnership with Arm.
IBM’s Next Mainframe Chip Runs Arm and IBM Z Instructions on Every Core
IBM’s Next Mainframe Chip Runs Arm and IBM Z Instructions on Every Core

IBM used the Hot Chips conference to unveil what it calls the first dual-architecture mainframe processor, a chip designed to run Arm software natively alongside IBM Z workloads in future IBM Z and LinuxONE systems. It’s the first processor milestone from the IBM and Arm collaboration announced in April.

Two instruction sets, one core

The chip doesn’t pair separate Arm and IBM cores. Each core is designed to execute Arm and IBM Z (or Arm and LinuxONE) instructions concurrently, so Arm-native Linux environments could run at the same time as z/OS and Linux on IBM Z on the same machine.

Built on a 2-nanometer process, the design has 11 high-performance cores running at more than 5.7GHz, AI inference accelerators aimed at in-transaction fraud detection, an on-chip data processing unit for I/O acceleration, and a large cache. IBM notes that Z and LinuxONE platforms scale to hundreds of cores and tens of terabytes of memory.

Why it matters

The pitch is software choice. Arm’s ecosystem, which IBM puts at more than 22 million developers, includes much of the cloud-native and AI software now being built. Running it natively on the mainframe would let enterprises keep those workloads next to their transaction systems and data while getting IBM’s hardware fault detection and recovery, encryption, secure key management and AI acceleration.

“By bringing Arm natively to our platform, we’re combining access to one of the industry’s fastest-growing software ecosystems with the qualities that have made IBM systems the foundation for how businesses run today,” said Christian Jacobi, CTO and IBM Fellow for IBM Systems Development. Arm’s Mohamed Awad, executive vice president for Cloud AI, said that “as AI scales, more of the computing landscape is converging on Arm.”

IBM didn’t give a ship date, and it describes the design as still in development, with the usual caveat that plans can change. For mainframe shops, the near-term step is to look at which Arm-native Linux and AI applications they’d want to run close to core systems once hardware arrives.

Subscribe for Updates

ITManagementNews Newsletter

IT management news, trends and updates.

By signing up for our newsletter you agree to receive content related to ientry.com / webpronews.com and our affiliate partners. For additional information refer to our terms of service.

Notice an error?

Help us improve our content by reporting any issues you find.

Get the WebProNews newsletter delivered to your inbox

Get the free daily newsletter read by decision makers

Subscribe
Advertise with Us

Ready to get started?

Get our media kit

Advertise with Us