"HPE has announced the AMD "Helios" AI rack-scale solution, a complete rack for AI training and large-scale inferencing. This new AI rack features 72 AMD Instinct MI455X GPUs, 260 terabytes of bandwidth, and 2.9 AI exaflops of FP4 performance. HPE is also committed to open standards, and this is the first AI rack to use an Ethernet network. The new AI solution will be available worldwide in 2026."
"The new rack combines hardware, software, and network capacity in a single system. Antonio Neri, CEO of HPE, emphasizes the importance of open standards: "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.""
The Helios rack-scale solution includes 72 AMD Instinct MI455X GPUs, 260 terabytes of bandwidth, and 2.9 AI exaflops of FP4 performance. The system combines hardware, software, and network capacity in a single rack and targets AI training and large-scale inference workloads. The design follows Open Compute Project specifications and the Open Rack Wide (ORW) format with energy-efficient direct liquid cooling. HPE and AMD have partnered for over ten years and have delivered multiple exascale systems. The solution uses an Ethernet-based scale-up switch co-developed with Broadcom on the Tomahawk 6 chip and implements the Ultra Accelerator Link over Ethernet (UALoE) standard. Worldwide availability begins in 2026.
Read at Techzine Global
Unable to calculate read time
Collection
[
|
...
]