HPE's mockup of what supercomputer Discovery will look like in situ (image: HPE)
HPE's mockup of what Discovery will look like in situ (image: HPE)

HPE Cray supercomputing portfolio bolstered by three new blades

Following last month’s introduction of the HPE Discovery supercomputer, based on HPE’s new Cray Supercomputing GX5000 platform, HPE has announced a trio of new compute blades designed to accelerate a variety of workloads.

The HPE Cray Supercomputing GX440n Accelerated Blade includes four Nvidia Vera CPUs and eight Nvidia GPUs. Each blade acts as a universal compute engine for mixed-precision computing, with space for 24 per compute rack. That means a staggering 192 Nvidia Rubin GPUs per rack.

Next comes the AMD-powered HPE Cray Supercomputing GX350a Accelerated Blade (note the giveaway suffix after the model number). It includes one next-generation AMD EPYC CPU, codenamed “Venice”, and four AMD Instinct MI430X GPUs. These are designed for sovereign AI and HPC, and HPE recommends the GX350 blade for customers “who desire a universal compute engine for mixed-precision computing with AMD CPUs and GPUs.”

Finally, the unsuffixed HPE Cray Supercomputing GX250 Compute Blade. “[This] blade is recommended for customers who desire to build a CPU-only partition for double-precision workloads with eight next-generation AMD EPYC, “Venice”, CPUs,” said HPE, with GPU power coming from either of the other two blades.

Up to 40 GX250 Compute Blades can be configured per compute rack, which – according to HPE – delivers “industry-leading flagship x86 CPU core density”.

AMD and Nvidia’s reaction

What does Nvidia have to say about this latest partnership? Over to Dion Harris, Senior Director, HPC, Cloud and AI Infrastructure at Nvidia.

“HPE’s next-generation AI supercomputers with Nvidia Vera Rubin are designed to supercharge scientific discovery,” he said. “[These] HPE GX5000 systems will boost simulation, analytics and AI, providing essential infrastructure to accelerate the AI industrial revolution.”

AMD’s Travis Carr, Corporate Vice President, HPC and Sovereign AI, was equally upbeat.

“The latest HPE Cray supercomputing platform reflects the deep collaboration between AMD and HPE to develop leadership technologies at the convergence of HPC and AI,” he said.

“By bringing together high-density compute blades powered by AMD EPYC CPUs and AMD Instinct GPUs, we’re helping customers tackle some of the world’s most complex scientific and AI challenges with scalable, energy-efficient solutions.

Along with the new blades, HPE announced that HPE Slingshot 400 will be available for GX5000 systems in early 2027, as will its new HPE Supercomputing Management Software.

All three blades will be available in early 2027 as well.


About The Author

Avatar photo
Tim Danton

Tim has worked in IT publishing since the days when all PCs were beige, and is editor-in-chief of the UK's PC Pro magazine. He has been writing about hardware for TechFinitive since 2023.

Read more from this author.

We take journalism seriously. To learn more on why you should trust us, head to our editorial guidelines page or meet our team.