OSS presents new transportable compute server for edge AI applications at SC21

OSS presents new transportable compute server for edge AI applications at SC21

One Stop Systems (OSS) has unveiled a new artificial intelligence (AI) Transportable compute server at the SC21 international conference for high-performance computing in Missouri last week.

Dubbed Rigel Edge Supercomputer, the machine is reportedly the first to use the Nvidia HGX A100 4-GPU platform in conjunction with the latest Nvidia NVLink GPU interconnect (as opposed to traditional PCI Express GPUs).

OSS said Rigel features up to 800 Gbps networking capabilities via up to four Nvidia ConnectX-6 200Gb/s InfiniBand adapters, 64 TB of NVMe flash storage, 24 core AMD EPYC 7002 processors, and an advanced OSS PCIe Gen 4 bridging a direct interconnection between these critical components.

Rigel also includes a secure, unified management and control module that supports Redfish industry-standard specifications with a unified interface to manage system resources, as well as externally attached OSS expansion options such as additional GPUs, networking, I/O, and NVMe storage.

Designed for edge applications in relatively restricted spaces, such as the equipment bay of autonomous vehicles or mobile command centers, Rigel’s air-cooled solution measures 25.6” of depth, which can fit in one-half of 4U rack space.

OSS also confirmed that the liquid-cooled version of Rigel will reduce that size to one-half of 3U rack space.

In addition to space requirements, AI transportable applications differ from traditional edge infrastructure as they need to meet military-specification requirements for shock and vibration, redundancy, operating temperature ranges, altitude ranges, and uninterrupted power.

“Virtually all AI edge compute platforms on the market today do not integrate and optimize datacenter-class computing with compact, rugged form factors,” explained OSS president and CEO David Raun.

To help meet these stringent standards, Rigel supports a flexible power subsystem including both single and three-phase AC and DC inputs, thus enabling deployment in a wide range of ground station and vehicle-supplied power applications.

“As our most compact and powerful AI Transportable compute server, we believe the Rigel Edge Supercomputer will transform the use of real-time AI for the most demanding vehicle, maritime, and aerospace applications at the edge,” Raun concluded.

The release of Rigel comes months after OSS demonstrated a long-range visual observation system at the Sea-Air-Space 2021 (SAS) conference in August.

Article Topics

 |   |   |   | 


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Featured Edge Computing Company

Edge Ecosystem Videos

Machine learning at the Edge


Latest News