AMD Helion reference design targets CPU dense agentic AI racks

AMD introduces Helion

AMD is bringing a new reference rack scale design to the data center ecosystem with Helion. It is a standardized, 21 inch rack reference design that will complement the Helios rack AMD revealed at OCP Global Summit last year. This year, Helion can house up to 32,768 Zen 6 cores in a CPU only deployment using the dense 256 core design available with the EPYC Venice 9996.

The rack design is standardized, based on the Open Compute Project ORv4 specification, which is slightly wider and taller than a standard IT rack. Helion is designed to support 44 OpenU trays, which are 21mm wide and 48mm tall, slightly larger than a standard EA1-310 tray. AMD says the reference design supports both air cooled and direct liquid cooled deployments. The design is also compliant with OCP DC-MHS, which OCP describes as a standard for interoperability between key elements of data center, edge, and enterprise infrastructure.

Reference design, not an AMD rack product

Although AMD has renders of the design, it will not actually sell racks. This is a reference design that AMD is contributing to OCP, and OEMs and ODMs will bring that design to market. AMD did not share partners supporting Helion during a pre briefing with the press. The company says CEO Lisa Su will announce partners during the lead keynote at the OCP Global Summit later today. AMD also did not share deployment partners, though it suggested that Helios customers will also deploy Helion racks.

Unlike Helios, which is built for AI training and inference, Helion is a more flexible rack solution primarily focused on CPUs. In a CPU only deployment, the design can hold up to 128 EPYC 9996 CPUs, bringing the 32,768 core count per rack. This configuration would likely look something like an agentic AI sandbox system, which is then connected to an inference system. This model for personal AI agents is in use today, both in Meta Muse and OpenAI Dots. Each user has a sandbox with a slice of compute from the host system, with the backbone of an inference server. Some workloads are handled on those CPU only servers, such as building software, but the heavy duty AI inference happens elsewhere.

Configurations and timing

Presumably, this is the model AMD is aiming at with Helion as hyperscalers build out CPU capacity on the back of agentic AI. However, the design is flexible, supporting up to 16 MI350P GPUs and 102 Tbps of networking, though at the cost of CPU capacity. This hybrid configuration is targeted at enterprises, says AMD, giving them an all in one rack for data management, networking, and AI usage. AMD says the Helion rack will be available starting in the first half of 2027, likely riding the wave of Zen 6 deployments that are expected to start ramping up later this year.

Sources: Tomshardware