IBM releases a new mainframe built for the age of AI
IBM releases the latest version of the Mainframe -hardware with new updates intended to speed up the AI acceptance.
The hardware and consultancy firm announced IBM Z17 on Monday, the latest version of the Mainframe computer hardware. This fully encrypted mainframe is powered by an IBM Telum II processor and is designed for more than 250 AI -USE Cases, says the company, including AI agents and generative AI.
Mainframes may seem old hat, but they are used today by 71% of the Fortune 500 companies, By one source. In 2024, the Mainframe market was worth $ 5.3 billion, according to Market Research Future of the consultancy.
The Z17 can process 450 billion inference activities in one day, an increase of 50% compared to its predecessor, the IBM Z16, which was released in 2022 and ran on the original Tellum processor of the company. The system is designed to fully integrate with other hardware, software and open-source tools.
Tina Tarquinio, VP of product management and design for IBM Z, TechCrunch said that this Mainframe -upgrade has been in the making for five years – well before the current AI Frenzy who started with the release of OpenAi’s Chatgpt in November 2022.
IBM spent more than 2,000 research hours to get feedback from more than 100 customers while building the Z17, Tarquinio said. She finds it interesting to see that, now, five years later, the feedback with which they were tailored to where the market went.
“It was wild knowing that we introduce an AI accelerator, and then, especially in the later half of 2022, all changes in the industry with regard to AI,” Tarquinio told WAN. “It was really exciting. I think the biggest point has been [that] We don’t know what we don’t know about what’s coming, right? So the possibilities are really unlimited in terms of what AI can help us. “
The Z17 is set to adapt and meet where the AI market heads, Tarquinio said. The mainframe supports 48 IBM Spyre AI Accelerator chips in release, with the plan to bring that number to 96 within 12 months.
“We intentionally build in the headroom,” Tarquinio said. “We intentionally build in AI Agility. So if new models are introduced, [we’re] Make sure we have built in the headroom for larger, larger models – models that may need more local memory to talk to each other. We have built that in because we know that it is really the approach that will change, right? The new models will come and go. ‘
Tarquinio said that one of the highlights of this latest hardware, although she joked, it was as if it was asked to choose her favorite child that the Z17 is more energy efficient than its predecessor and supposedly competitors too.
“On-chip we increase the AI gear by seven and a half times, but that is five and a half times less energy than you should do, such as multimodel on another type of accelerator or platform in the industry,” Tarquinio said.
The Z17 mainframes are generally available on 8 June.
