- HPE reveals rack-scale system containing 81,920 CPU cores
- AMD Venice Processors Power HPE’s Next-Generation Cray Infrastructure
- A 42U rack offers unprecedented levels of computing density
During its recent HPE Discover 2026 event, the company revealed new Cray GX5000 hardware featuring next-generation AMD EPYC Venice processors, with specifications that push server density far beyond current deployments.
The system combines multiple compute blades, liquid cooling infrastructure, networking hardware and memory resources within a single 42U rack configuration.
HPE revealed a Cray GX5000 configuration designed to offer up to 81,920 CPU cores in one rack.
Dense computing architecture increases rack capacity
The HPE Cray GX5000 platform follows the AMD EPYC 9965, a 192-core processor that represented one of AMD’s highest core count server CPUs before Venice arrived.
While the EPYC 9965 increased density at the processor level, the Venice-based system takes a broader approach by combining multiple CPUs, memory resources, and cooling infrastructure within a single chassis.
At the center of the system is the HPE Cray GX250a compute blade, which houses eight AMD EPYC Venice processors.
The compute blade incorporates power delivery, liquid cooling channels, memory subsystems, storage devices and networking components within a compact design.
HPE claimed that a fully loaded rack can offer 81,920 CPU cores, although exact processor configurations were not disclosed.
Depending on rack specifications, the system uses 80 multi-node motherboards and can support up to 1.28 PB of RAM.
Each Venice processor connects to 16 memory channels, creating substantial memory bandwidth for large-scale computing workloads.
The memory modules themselves are liquid cooled and appear to use standard DIMM form factors.
Photos from the event showed local Samsung E1.S EDSSF SSDs mounted on several cold processor plates.
HPE representatives indicated that these drives serve as high-speed temporary storage for temporary data processing tasks.
The installed DRAM modules, storage devices, and node IDs suggest that the hardware shown was operational and not a non-functional demo unit.
That distinction is significant because previous demonstrations in Venice seemed closer to prototype systems than production-ready implementations.
Venice CPUs and Networks Define the Platform
The rack incorporates Slingshot 400 networking hardware, and HPE indicates future support for Slingshot 800 technology.
Network modules are mounted inside side modules connected to processors through dedicated interfaces designed for high-bandwidth communications.
The front-facing network layout also simplifies cable management by changing the way optical connections are routed throughout the rack.
HPE also demonstrated a refrigerant distribution unit capable of handling 1.6 MW of cooling capacity for large facilities.
These cooling requirements reflect the increasing power densities associated with modern high-performance computing infrastructure and increasingly complex CPU designs.
Artificial intelligence tools, scientific simulations, engineering analyses, and large LLM implementations are among the workloads that require this level of computational density.
The company did not reveal detailed specifications for AMD’s unannounced Venice processors, although available figures suggest unusually high core counts.
Calculations based on the stated 81,920-core rack capacity imply that processor densities exceed current EPYC generations by a substantial margin.
Although AMD has not released specifications or performance figures for the Venice, the projected core density of the HPE system has led to speculation that the processor could become one of the most powerful x86 CPUs produced.
A lot could change before the official launch, but the Cray GX5000 platform indicates that AMD and HPE are looking for greater computing density within the same rack space.
Via ServeTheHome
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds.
