MIL Rugged Scalable SFF AI Compute System
MIL rugged SFF AI compute systems for the rugged edge.
With AI inference performance up to 6.6 PetaOPS, data fabric speeds of over 150GB/s and advanced PCIe switching features, these scalable systems bring the power of the datacenter to rugged environments.
Products & Services
PCle Gen 5 3U Short Depth Server
One Stop Systems
he Gen 5 SDS is a hyperconverged datacenter class server that supports configurations of up to 5 of the worlds most powerful GPUs, 16 of the fastest NVMe solid state storage devices, the lowest latency, highest bandwidth PCIe scale-out expansion systems, the highest performance SAN & NAS storage software, extreme 400Gbps networking solutions and the most secure advanced system management, monitoring and control. This allows a single short-depth server platform to bring the compute power of the datacenter to the rugged edge to perform many missions, from high-performance AI inference of up to 35 simultaneous AI workloads, high-speed transportable data recorder/logger with hot-swap drive packs with up to 1 petabyte capacity, or a rugged SAN or NAS data storage unit.
Rigel Edge Supercomputer
One Stop Systems
The Rigel Edge Supercomputer brings the power of NVIDIA HGX A100 SXM GPUs to the rugged edge. The HGX A100 4-GPU backplane delivers 78 teraFLOPS of FP64 HPC performance using third generation NVLINK technology. The GPUs are integrated with OSS PCIe Gen 4.0 expansion technology to take advantage of the latest AMD 3rd Gen EPYC processors while offering four PCIe Gen 4.0 x16 expansion slots for high speed network interconnect, NVMe storage, or FPGA sensor capture. The optimized PCIe architecture enables maximum data throughput, avoiding bandwidth bottlenecks. Rigel’s lightweight, rugged, thermally optimized and compact design bring the power of the datacenter to the rugged edge—whether airborne, marine, or terrestrial.
Description
The Cernis small form factor (SFF) NVIDIA Jetson Orin with integrated PCI Express 4.0 switch fabric forms the keystone of an expandable edge AI mission computing system to handle today’s highest end AI applications including sensor fusion, natural language processing, autonomy, situational awareness, and signal intelligence in a SWaP optimized package. While Cernis is a powerful AI mission computer on its own, its real power is unleashed when Cernis is accompanied by up to 24 of the Donati line of NVIDIA Jetson Orin AGX mission computers using an OSS PCIe fabric* to form the lowest latency, highest speed mission compute system. The Cernis/Donati scalable compute system is built from the ground up to tackle multiple performance hungry AI applications in harsh vehicle environments. With AI inference performance up to 6.6 PetaOPS, data fabric speeds of over 150GB/s and advanced PCIe switching features, the Cernis/Donati scalable AI SFF compute system brings the power of the datacenter to the rugged edge.
