HPE has announced will become one of the first system providers to adopt AMD’s Helios rack-scale AI architecture.

In collaboration with Broadcom, HPE said it will also integrate a purpose-built HPE Juniper Networking scale-up switch into Helios to offer high-bandwidth Ethernet connectivity.

First unveiled in June 2025, AMD’s double-wide Helios AI rack features the company’s Zen 6 Epyc “Venice” CPUs, MI455X GPUs, and Pensando Vulcano NICs, delivering 2.9 exaflops of FP4 performance per rack. HPE expects to make Helios architecture available to its customers globally from 2026, the company said.

The announcement comes almost a month after HPE detailed the technical specifications of its forthcoming Cray Supercomputing GX5000 platform.

The company previously revealed that the High-Performance Computing Center of the University of Stuttgart (HLRS) had selected the GX5000 platform for its next-generation supercomputer Herder, and today disclosed that, like its predecessors, Herder will also be an AMD-powered system. Herder will comprise AMD Instinct MI430X GPUs and next-generation AMD Epyc Zen 6 CPUs when it goes live in late 2027, replacing HLRS’ current system, Hunter.

“HPE has been an exceptional long-term partner to AMD, working with us to redefine what is possible in high-performance computing,” said Dr. Lisa Su, AMD CEO. “With ‘Helios’, we’re taking that collaboration further, bringing together the full stack of AMD compute technologies and HPE’s system innovation to deliver an open, rack-scale AI platform that drives new levels of efficiency, scalability, and breakthrough performance for our customers in the AI era.”

“For more than a decade, HPE and AMD have pushed the boundaries of supercomputing, delivering multiple exascale-class systems and championing open standards that accelerate innovation,” said Antonio Neri, CEO of HPE. “With the introduction of the new AMD ‘Helios’ and our purpose-built HPE scale-up networking solution, we are providing our cloud service provider customers with faster deployments, greater flexibility, and reduced risk in how they scale AI computing in their businesses.”