IBM has announced a new processor that can execute instructions from its own mainframe architecture and the widely-used Arm architecture at the same time, a significant shift aimed at making mainframes compatible with modern software ecosystems. The unnamed chip, built on a two-nanometer technology node, will include 11 high-performance cores running at more than 5.7 gigahertz, plus artificial intelligence inference accelerators for fraud detection and a dedicated data processing unit for input-output acceleration.

Why Is IBM Doing This Now?

IBM's mainframe business remains profitable and strategically important, but it faces a fundamental problem: the software world has largely moved on. The Arm ecosystem includes more than 22 million developers worldwide and supports a rapidly growing portfolio of cloud-native, artificial intelligence, analytics, infrastructure, and enterprise applications. Meanwhile, IBM's Z platform, despite its legendary reliability and security, sits outside the mainstream software targets that define modern cloud and AI infrastructure.

By enabling a single chip to run both mainframe and Arm code natively, IBM is attempting to solve a decades-old isolation problem. Existing mainframe customers are locked into their systems because core applications, decades of operational practice, and data gravity make migration expensive and risky. But those same customers increasingly want access to the broader open-source ecosystem and modern development tools that run on Arm. IBM's new chip promises to deliver both.

"The Arm ecosystem includes more than 22 million developers worldwide and supports a rapidly growing portfolio of cloud-native, AI, analytics, infrastructure, and enterprise applications," stated Meredith Stowell, Vice President for the zSystems Ecosystem at IBM.

Meredith Stowell, Vice President for the zSystems Ecosystem, IBM

What Problem Does This Solve for Enterprise Customers?

The mainframe market is small in unit terms but remains strategically important. However, the architecture has increasingly diverged from the modern software development lifecycle. Commercial application vendors have little incentive to build for mainframes when the same engineering effort can reach millions of Arm developers. This new chip represents an attempt to end the platform's historical isolation from the broader computing mainstream.

For existing IBM customers, the benefits are clear: they can continue running mission-critical mainframe workloads while gaining access to modern cloud-native applications, open-source infrastructure tools, and AI frameworks that were previously unavailable on Z systems. For IBM, the strategy offers three potential wins:

• Continuity for ISVs: Independent software vendors that currently build mainframe products and their customers can continue operating without disruption.
• Expanded software choice: Existing IBM customers gain access to the broader Arm software ecosystem, making Z a more attractive choice for organizations considering mainframe adoption.
• Resilience for more workloads: The nine-nines reliability of mainframes becomes available for a wider range of enterprise applications.

When Will This Chip Arrive?

IBM suggested the new chip will arrive in 2028. The company released its most recent generation of mainframes, the z17, in 2025 and typically delivers new models every three years. The chip therefore looks positioned to power z18 machines, IBM's next-generation mainframe platform.

This is not IBM's first attempt at dual-architecture processors. In the mid-1990s, IBM developed the PowerPC 615, a chip that could run both PowerPC and x86 code with the active instruction set architecture selected at boot. That chip was reportedly intended for Apple during the clone era but was never sold publicly.

How Will This Chip Change Enterprise Computing Strategy?

• Reduce migration risk: Organizations can gradually modernize workloads without abandoning proven mainframe infrastructure, lowering the cost and complexity of digital transformation.
• Attract new customers: Companies hesitant about mainframes due to software ecosystem limitations may reconsider, knowing they can run modern applications alongside legacy systems.
• Extend mainframe relevance: By bridging the gap between legacy and cloud-native computing, IBM positions mainframes as a hybrid platform rather than a legacy-only solution.
• Simplify operations: IT teams can manage both traditional and modern workloads on a single hardware platform, reducing operational complexity and training requirements.

The move reflects a broader reality in enterprise computing: the future is not about replacing legacy systems wholesale, but about making them interoperable with modern software ecosystems. IBM's new chip is an engineering solution to a business problem: how to keep mainframes relevant in an Arm-dominated world without abandoning the customers and applications that depend on them.