IBM releases the latest version of its mainframe hardware, which includes new updates to accelerate AI adoption.
The latest version of IBM’s Z-mainframe, IBM z17, is powered by an IBM Telum II processor and is designed for more than 250 AI use cases. The goal is to help companies with their AI ambitions and to make z17 work seamlessly with existing infrastructure and open source tools.
Evolves with the Market
Mainframes may seem outdated, but they are still used by 71 percent of Fortune 500 companies, writes TechCrunch. The mainframe market was estimated to be worth $5.3 billion in 2024. “This upgrade has been in the works for five years. So even before the current AI craze began with the release of OpenAI’s ChatGPT in 2022,” says VP product manager and design for IBM Z, Tina Tarquino.
Faster and more efficient
A key advantage is energy efficiency. IBM claims that the z17 performs AI tasks up to 7.5 times faster than its predecessor. Additionally, it uses five times less energy than competing systems for comparable AI workloads. Tarquinio: “On-chip, we increase AI acceleration by seven and a half times. This way, we need five and a half times less energy than on another type of accelerator or platform.”
The mainframe is set to adapt and accommodate the direction in which the AI market is moving, says Tarquinio. It will support 48 IBM Spyre AI accelerator chips at release. The plan is to increase that number to 96 within 12 months.
IBM z17 will be generally available from June 8.
read also