Argos Ruggedized Edge System
Devices that support AI on the edge
Argos Ruggedized Edge System
Edge AI/Inference system, MIL-SPEC ready
Processing AI inference workloads (e.g., computer vision, object detection) at the edge in real time while protecting equipment from environmental hazards (temperature, dust, vibration, moisture, limited power, etc.) is a challenge.
Silicon Mechanics has designed a custom ruggedized system that supports internals similar to current-gen vehicle-borne systems for field use. Operates on limited power, in a broad temperature range, and resists dust and moisture.
Benefits
- Pre-configured for edge AI and inference workloads (computer vision, object detection, etc.).
- More cost effective than AWS options, without vendor lock-in
- Ruggedization or MIL-SPEC can be matched to customer requirements
- Supports NVIDIA A100 GPU for optimal performance
Ideal Use Cases
- Edge inference
- Computer vision
- Object detection
- Anonomous sentry
Relevant Industries
Aerospace/Defense
Security
Oil & Gas
Argos Edge Node Components
Vehicle-Borne Server
- 2U chassis
- 2x AMD EPYC 7272 w/12 cores (24 cores total)
- 256GB-6TB DDR4 memory
- 2x NVIDIA A100 80GB GPU
- 2x 480GB SAS SSDs
- 12x 12TB SAS HDDs (144TB raw)
- 10Gb fiber SFP+
- 2x 1000W (1+1 redundant) power supplies
MIL-SPEC Ruggedized Edge System
- Custom MIL-SPEC chassis
- Intel Gold 5318N 24-core 2.1GHz 150W processor
- 128GB DDR4 memory
- 1x NVIDIA A100 80GB GPU
- 2x 960GB SAS24 SED FIPS SSDs (boot)
- 3x 7.68TB SAS24 SED FIPS SSDs (23TB raw)
- 25Gb Fiber SFP+
- DC Power Supply
Supported Software & AI Frameworks
Can be deployed with containers (e.g., Kubernetes), container orchestration, HCI stack, Silicon Mechanics AI Stack, Silicon Mechanics’ Scientific Computing Stack, and support for popular frameworks.
Get a Quote
Expert Included
Our engineers are not only experts in traditional HPC and AI technologies, we also routinely build complex rack-scale solutions with today's newest innovations so that we can design and build the best solution for your unique needs.
Talk to an engineer and see how we can help solve your computing challenges today.