IBM Teams Up With Arm To Run Arm Workloads On IBM Z Mainframes (networkworld.com) 26
IBM and Arm are teaming up to let Arm-based software run on IBM Z mainframes. Network World reports: The two companies plan to work on three things: building virtualization tools so Arm software can run on IBM platforms; making sure Arm applications meet the security and data residency rules that regulated industries must follow; and creating common technology layers so enterprises have more software options across both platforms, IBM said in a statement.
IBM has not said whether the virtualization work will happen at the hypervisor level, through its existing PR/SM partitioning technology, or via containers -- a question enterprise architects will need answered before they can assess the collaboration's practical value. IBM described the effort as serving enterprises that run regulated workloads and cannot simply move them to the cloud, the statement said. IBM mainframe customers have largely missed out on the efficiency and price-performance gains Arm has already delivered in the cloud. "Arm says close to half of all compute shipped to top hyperscalers in 2025 runs on Arm chips, with AWS, Google, and Microsoft deploying their own Arm silicon through Graviton, Axion, and Cobalt, respectively," reports Network World.
That gap is precisely what IBM and Arm's collaboration intends to address. "This is a mainframe adjacency play," says Rachita Rao, senior analyst at Everest Group. "The intent is to extend IBM Z and LinuxONE environments by enabling Arm-compatible workloads to run closer to systems of record. While hyperscalers use Arm to lower their own internal power costs and pass savings to cloud-native tenants, IBM is targeting the sovereign and air-gapped market."
IBM has not said whether the virtualization work will happen at the hypervisor level, through its existing PR/SM partitioning technology, or via containers -- a question enterprise architects will need answered before they can assess the collaboration's practical value. IBM described the effort as serving enterprises that run regulated workloads and cannot simply move them to the cloud, the statement said. IBM mainframe customers have largely missed out on the efficiency and price-performance gains Arm has already delivered in the cloud. "Arm says close to half of all compute shipped to top hyperscalers in 2025 runs on Arm chips, with AWS, Google, and Microsoft deploying their own Arm silicon through Graviton, Axion, and Cobalt, respectively," reports Network World.
That gap is precisely what IBM and Arm's collaboration intends to address. "This is a mainframe adjacency play," says Rachita Rao, senior analyst at Everest Group. "The intent is to extend IBM Z and LinuxONE environments by enabling Arm-compatible workloads to run closer to systems of record. While hyperscalers use Arm to lower their own internal power costs and pass savings to cloud-native tenants, IBM is targeting the sovereign and air-gapped market."
Only on Mondays and Wednesdays (Score:4, Funny)
IBM Teams Up With Arm To Run Arm Workloads On IBM Z Mainframes
Tuesdays and Thursdays will be Leg days. :-)
Sounds like the lights might be going out on POWER (Score:2)
I have to wonder if this is a first step to abandoning POWER. I can see IBM wanting to get out of the game of trying to build performance competitive CPUs they don't have many outside customers for any longer.
Especially when they could put commodity designs in their shiny black boxes and still charge super premium prices for them.
Re: (Score:2)
I'm wondering the same thing. Mainframe CPUs have a niche, and then x86/ARM/RISC-V have them. Unless IBM finds a way to get POWER out there and keep it competitive, it might be something that IBM may wind up doing, transitioning the apps that were on P and i to Z or PC.
Hopefully not, but who knows.
what Power's good for (Score:1)
If you read around forums you'll see that the main uses for Power are things like medical records (EPIC), databases (Oracle), school records etc. So basically the tier below where mainframes are used (banks, airlines, insurance companies). All of this stuff runs on Linux too, just not quite as well, but much cheaper and easier to find qualified administrators on Linux than AIX. And of course "i" (fka AS/400) is super weird, finding anyone who was born after the JFK assassination who knows "i" is almost impo
Re: (Score:2)
Heh I love AS/400 machines. They’re so alien when you compare them to anything PC like.
Re: (Score:2)
"Alien compared to PC" is a good phrase for AS/400.
Uptime, granular control of user processes, the ability to compile CL (Control Language, somewhat akin to bash scripting) into native code, dual-abstraction making portability from the smallest to the largest a simple operation of copying the binary to the new machine, I could go on.
Re: (Score:3)
I'd hate to see IBM i die off, it's an operating system like nothing else at that level, i.e. competing with Windows/Linux/Unix.
But you can't run it on x86 or Arm because the OS is designed for the architecture. Mind you, they re-wrote the abstraction layer when they moved from the original CISC CPU systems to RISC. Nobody had to recompile any application software. On the gripping hand, the OS was designed first and then the hardware, to satisfy the requirements of OS400. So I'm not sure if they *could* por
Re: (Score:2)
Maybe Power needs to leave IBM and be completely in the hands of the OpenPOWER Foundation. Speaking of which, is that still an active part of the Linux Foundation?
But I still don't see its niche, though. RISC-V is completely open and royalty-free, so that anybody in the world w/ the competence can develop one. Arm Holdings has the model that anybody can license it under either an "architectural license" or other types: only that they have to be paid upfront for membership, and then be paid according to
Re: (Score:3)
Problem is that the only viable market for mainframe are current mainframe customers, who are so change averse that if you even hint at breaking compatibility they will be triggered to start evaluating *all* their options if they are faced with a potential migration anyway.
IBM may love the idea of shuttering their in-house stuff in favor of massively cheap commodity stuff, but they would absolutely no longer command mainframe margins.
Re: (Score:2)
Re: Sounds like the lights might be going out on P (Score:2)
They did, but it's never too late to cheapen how they're current stuff is produced.
Still, I think they know all too well that mainframe is "stuck" doing it the way they always have done it.
Re: (Score:2)
They're not averse to change, they're averse to risk. Banks, insurance, airlines. They can't afford risk.
And they're generally quite smart when it comes to calculating risks to their business. They've figured out that there's nothing else that can do the job for the same price.
well (Score:1)
IBM's mainframes don't run on Power. They have their own CPU architecture going back 62 years. Power is used on mini-computers (running AS/400 nka "i"), workstations and servers. That said the most recent Power chip was a warmed over iteration of the previous one and the days that Power could contend for the world title of most powerful CPU are long gone.
The z business is similar to a lot of enterprise software businesses where you are never getting any new labels (i.e., new customers who are not related to
Re: (Score:2)
Wish you weren’t posting AC so more people saw this.
Re: (Score:2)
You beat me to it. One thing I've been wondering - all these power saving technological advancements that Arm has made over the decades, and which x86 too has discovered to an extent - was it impossible to implement in Power? What is it - a bloated instruction set?
I do think it would be tragic if Power went away. I'd rather see it as another option out there alongside Arm and RISC-V
What are they calling it? (Score:2)
IBM System z Facility Using Cost-effective Kit Integrated Transactions?
Not the first IBM Dual ISA design - PowerPC 615 (Score:3, Interesting)
A fun stroll down memory late is revisiting the PowerPC 615 design that never made it to market. A chip able to execute both PowerPC and x86 instructions.
a few dredged up stories:
https://www.cpushack.com/CIC/announce/1995/PowerPC615.html
https://www.halfhill.com/byte/1995-11_cover3.html
https://www.theregister.com/1998/10/01/microsoft_killed_the_powerpc/
This isn't to cast doubt that this mash up between Z and Arm won't be delivered.
Re:Not the first IBM Dual ISA design - PowerPC 615 (Score:4)
But why? (Score:2)
Re: But why? (Score:2)
Yep, banks, airlines, and retail are all irrelevant.
Psst. They don't buy it for the compute. They buy it for the crypto card and security.
Re: (Score:2)
Don't forget nine nines of uptime.
Or hot-swapping CPU and memory modules in the unlikely event of failure.
Re: (Score:2)
Re:But why? (Score:4, Informative)
ROTFLMAO (Score:2)
Oh, all mainframes are obsolete, they're so 20th century.... /s