In this video, Braden Cooper, Product Marketing Manager at OSS, does a quick walkthrough of the OSS PCIe Gen 4 3U Short Depth Server (both AMD and Intel versions). The SDS has configurable motherboard options in a feature packed rugged server platform for GPU or FPGA accelerated computing, U.2/U.3 NVMe storage, and PCIe Gen 4 expansion. This functionality is delivered in a size efficient, edge-ready rugged chassis with 3U height and 20” depth. This edge optimized server can operate stand-alone as a hyperconverged PCIe Gen 4 rugged server or form the core CPU and memory resources for a scale-out, rack level, expandable and composable solution in the shallowest available racks.
This video will highlight some of the most important features of the SDS and help you determine if this system is the right fit for your AI edge application.
As described in the video, the AMD version of the rugged server can accommodate a motherboard with Dual or Single-Socket AMD EPYC™ 7003 Series Processors. This configuration features up to 7 PCIe Gen 4 x16 slots, and 16 SATA/NVMe drives and supports up to 4TB of memory.
With the Intel version, the motherboard features two Intel Scalable Processors as well as six PCIe Gen 4 x16 full-height slots (four of which are double-width), one PCIe Gen 4 x8 full-height slot and options for 8 or 16 SATA/NVMe drives. This configuration supports up to 4TB of memory. Both versions of the rugged server have a resource expanded BIOS for scale-out device enumeration and large memory mapped I/O used for GPUs and accelerators.
The two 8-drive canisters are part of what makes the SDS a unique rugged server platform for edge applications. As the video mentions, the SDS is currently being used in autonomous truck applications both in the truck and in the hub depot. The truck will pull into the depot and the canisters will be removed quickly and inserted into another SDS to quickly offload the data. New canisters can be put into the truck to get it back on the road quickly.
OSS also has customers on the military side using the SDS in mobile command shelters. The server is MIL-STD-810G tested and has many features to withstand the shock and vibration of rugged edge environments.
To watch the full video, subscribe to our YouTube channel and see the full video here. To have a member of our sales team contact you about the SDS, please contact us here.
Click the buttons below to share this blog post!
By: Jaan Mannik – Director of Commercial Sales
The term AI, or Artificial Intelligence, is everywhere nowadays and has quietly woven itself into the fabric of our daily lives. It powers the recommendations we see on streaming platforms, the navigation apps that guide us through traffic, and even the virtual assistants that answer our questions in seconds. From optimizing energy use in smart homes to predicting market shifts in finance, AI has become the invisible engine driving convenience, efficiency, and insight across industries.
In manufacturing, AI-driven robots collaborate with humans to streamline production. In agriculture, machine learning models monitor crops, forecast yields, and conserve resources. Retailers use predictive analytics to anticipate consumer needs before customers even express them. The reach of AI is no longer confined to futuristic labs, it’s in our phones, vehicles, and cities, constantly learning and adapting to serve us better.
OSS PCIe-based products deliver critical advantages for modern military sensor systems by enabling real-time data acquisition, processing, and transmission in rugged, mission-critical environments. These benefits stem from their ability to support high-bandwidth, low-latency interconnects, modular scalability, and environmental resilience, all of which are essential for today’s advanced military platforms.
Companies today are being asked to do more with data than ever before. Bigger AI models, faster insights, and workloads that don’t stay in one place, it’s a lot to keep up with. Traditional infrastructure just isn’t built for this kind of speed and flexibility.
The answer isn’t about throwing more hardware at the problem. It’s about building smarter, more agile infrastructure that adapts as demands change. And that’s where scale-out and increasingly, a blend of scale-out and scale-up come into play.