IBM Introduces the Spyre Accelerator for Commercial Availability

IBM (NYSE: IBM) today announced the upcoming general availability of the IBM Spyre Accelerator, an AI accelerator enabling low-latency inferencing to support generative and agentic AI use cases while prioritizing the security and resilience of core workloads. Earlier this year, IBM announced the Spyre Accelerator would be available in IBM z17, LinuxONE 5, and Power11 systems. Spyre will be generally available on October 28 for IBM z17 and LinuxONE 5 systems, and in early December for Power11 servers.

Why this matters

Today’s IT landscape is shifting from traditional logic workflows to agentic AI inferencing. AI agents require low-latency inference and real-time system responsiveness. IBM recognized the need for mainframes and servers to run AI models alongside demanding enterprise workloads without compromising throughput. Clients need AI inferencing hardware that supports generative and agentic AI while maintaining the security and resilience of core data, transactions, and applications. The accelerator also helps clients keep mission-critical data on-prem to mitigate risk while improving operational and energy efficiency.

Click to enlarge

The Spyre Accelerator reflects IBM’s research-to-product pipeline, combining innovation from the IBM Research AI Hardware Center with enterprise-grade development from IBM Infrastructure. Initially introduced as a prototype chip, Spyre was refined through cluster deployments at IBM’s Yorktown Heights campus and collaboration with partners like the University at Albany’s Center for Emerging Artificial Intelligence Systems.

“One of our key priorities has been advancing infrastructure to meet the demands of new and emerging AI workloads,” said Barry Baker, COO, IBM Infrastructure & GM, IBM Systems. “With the Spyre Accelerator, we’re extending the capabilities of our systems to support multimodel AI — including generative and agentic AI. This innovation positions clients to scale their AI-enabled mission-critical workloads with uncompromising security, resilience, and efficiency, while unlocking the value of their enterprise data.”

“We launched the IBM Research AI Hardware Center in 2019 with a mission to meet the rising computational demands of AI,” said Mukesh Khare, GM of IBM Semiconductors and VP of Hybrid Cloud, IBM. “Now, amid increasing demand for advanced AI capabilities, we’re proud to see the first chip from the Center enter commercialization.”

Use cases and platform details

For IBM clients, Spyre offers fast, secured processing with on-prem AI acceleration—allowing businesses to leverage AI at scale while keeping data on IBM Z, LinuxONE and Power systems. In mainframe environments, coupled with the Telum II processor for IBM Z and LinuxONE, Spyre provides enhanced security, low latency, and high transaction-rate processing power. Businesses can scale multiple AI models to power predictive use cases such as advanced fraud detection and retail automation.

On IBM Power-based servers, Spyre customers can use a catalog of AI services to enable end-to-end AI for enterprise workflows. Clients can install AI services from the catalog with one click. Spyre for Power, together with an on-chip accelerator (MMA), accelerates data conversion for generative AI to deliver high throughput for deep process integrations. With a prompt size of 128, it enables the ingestion of millions of documents per hour for knowledge-base integration—supporting large-scale generative AI workflows while emphasizing security, scalability, and energy efficiency.

For more information, see the official IBM announcement.