IBM Unveils Latest Mainframe Hardware with AI Acceleration Capabilities

A New Era for Mainframes

IBM is releasing the latest version of its mainframe hardware, the IBM z17, designed to accelerate AI adoption. The fully encrypted mainframe is powered by an IBM Telum II processor and is designed for more than 250 AI use cases, including AI agents and generative AI.

Mainframes: Still a Vital Component of Business Infrastructure

Mainframes might seem like old hat, but they’re used by 71% of Fortune 500 companies today, according to one source. In 2024, the mainframe market was worth an estimated $5.3 billion, per consulting firm Market Research Future.

Key Features of the z17 Mainframe

The z17 can process 450 billion inference operations in a day, a 50% increase over its predecessor, the IBM z16. The system is designed to be able to fully integrate with other hardware, software, and open-source tools. The mainframe will support 48 IBM Spyre AI accelerator chips upon release, with the plan to bring that number up to 96 within 12 months.

Design and Development

Tina Tarquinio, VP of product management and design for IBM Z, said that this mainframe upgrade has been in the works for five years. The company spent over 2,000 research hours getting feedback from over 100 customers, which aligned with the current AI frenzy. Tarquinio believes that the mainframe’s design will adapt and accommodate where the AI market heads.

Energy Efficiency

The z17 is more energy-efficient than its predecessor and competitors, according to Tarquinio. The on-chip AI acceleration is seven and a half times more efficient than other accelerators or platforms in the industry.

Conclusion

The IBM z17 represents a significant step forward in mainframe technology, with a focus on AI acceleration and energy efficiency. As the AI market continues to evolve, the z17 is designed to adapt and accommodate new models and use cases.

FAQs

Q: What is the IBM z17 mainframe?

A: The IBM z17 is the latest version of IBM’s mainframe hardware, designed to accelerate AI adoption.

Q: What is the main purpose of the z17 mainframe?

A: The z17 is designed for more than 250 AI use cases, including AI agents and generative AI.

Q: How does the z17 compare to its predecessor?

A: The z17 can process 450 billion inference operations in a day, a 50% increase over the IBM z16.

Q: What is the energy efficiency of the z17 mainframe?

A: The on-chip AI acceleration is seven and a half times more efficient than other accelerators or platforms in the industry.

Q: When will the z17 mainframes become generally available?

A: The z17 mainframes will become generally available on June 8.