Arm works with IBM to deliver flexibility on mainframe | Computer Weekly

IBM has begun working with chipmaker Arm to develop what it calls dual-architecture hardware to provide flexibility when running enterprise artificial intelligence (AI) and data-intensive workloads.

Their overall goal is to combine IBM’s experience in systems reliability, security and scalability that it offers on Z-series mainframe systems with Arm’s expertise in power-efficient architectures and supporting a broad software ecosystem to build flexible and scalable computing platforms for the future.

Arm has been on a path to deliver an alternative to x86-powered servers in the datacentre. The company has introduced the Arm Agentic AI (artificial intelligence) central processor unit (CPU) which it positions as a processor that is tasked with keeping distributed AI systems operating efficiently at scale. This includes orchestrating AI accelerators, managing memory and storage, scheduling workloads and moving data across systems.

This latest collaboration appears to be focused on deliver enterprise reliability to the Arm platform. It builds on IBM’s heritage of offering coprocessors for the Z-series hardware such as the Integrated Facility for Linux, which was introduced in 2000. The mainframe manufacturer later introduced a Linux system based on the Z-series architecture, called LinuxOne, designed to let enterprise customers run Linux workloads in situ with data that resides on the mainframe system.

Christian Jacobi, chief technology officer and IBM fellow of IBM systems development, said: “This moment marks the latest step in our innovation journey for future generations of our IBM Z and LinuxOne systems, reinforcing our end-to-end system design as a powerful advantage.”

Mohamed Awad, executive vice-president of the cloud AI business unit at Arm, said: “Our collaboration with IBM builds on this progress, extending the Arm ecosystem into mission-critical enterprise environments and giving organisations greater flexibility in how they deploy and scale these workloads.”

The two companies said they are exploring how to expand virtualisation technologies that allow Arm-based software environments to operate within IBM’s enterprise computing platforms. According to IBM and Arm, this work is designed to expand software compatibility and streamline how developers and enterprises bring Arm applications into mission-critical environments. 

In the security and reliability front, the pair plan to investigate new ways to support the performance and efficiency demands of modern workloads, including AI and data-intensive applications. IBM and Arm said they will be looking at how to enable enterprise systems to recognise and execute Arm applications. 

The two companies also hope to provide a broader software ecosystems and greater flexibility in how applications are deployed and managed. IBM plans to offer new systems for its customers that incorporate Arm’s technology.

Tina Tarquinio, chief product officer of IBM Z and LinuxONE, said: “Our aim is to expand software choice and improve system performance while maintaining the reliability and security our clients expect.” 

The collaboration is seen as a signal of how enterprises may eventually deploy scalable, flexible IT infrastructure to support different types of application workload.

Patrick Moorhead, founder, CEO and chief analyst at Moor Insights & Strategy, added: “What IBM and Arm are signaling here is a meaningful step toward that future that could broaden how enterprises think about deploying and scaling modern workloads. While the full implications will take time to unfold, it’s clear this reflects a deeper level of investment in long-term platform innovation and ecosystem expansion than we typically see at this stage.”