Aitech will integrate the NVIDIA IGX Thor platform into its S-A2300 Commercial Off-The-Shelf (COTS) AI Supercomputer and future designs to expand edge AI capabilities for critical space missions.
The integration positions the company to deliver deployable, mission-ready space computing systems engineered for harsh operational environments. A rugged computing specialist with more than 40 years of experience delivering high-performance solutions for mission-critical applications, Aitech previously supplied one of the first General-Purpose Graphics Processing Units (GPGPUs) to fly in space. The company now has access to IGX Thor evaluation boards and modules, enabling rapid design, system integration, and hardware-in-the-loop testing.
Dan Mor, Director of Customer Solutions at Aitech, stated, “Aitech is at the forefront of the AI revolution, delivering the most powerful, reliable and future-ready technologies available. By integrating IGX Thor into our space-proven, rugged AI systems, Aitech is uniquely positioned to help transition advanced AI from terrestrial industrial spaces to the harsh environments of orbit.”
As an early adopter of the NVIDIA Jetson AGX Orin platform, Aitech developed space-based AI compute solutions currently supporting missions for NASA, Sidus Space, and other organizations. The S-A2300 COTS AI Supercomputer leverages the NVIDIA Jetson AGX Orin Industrial system-on-module and is designed specifically for Low Earth Orbit (LEO) missions, combining AI compute density with resilience against radiation and extreme environmental conditions.
The current S-A2300 system features up to 2,048 CUDA® cores and 64 Tensor cores, delivering as much as 248 TOPS for advanced AI workloads. It also includes two scalable NVIDIA Deep Learning Accelerator (NVDLA) engines designed to simplify integration and improve portability through standardized deep-learning inference acceleration. The architecture is optimized for space-based applications including real-time image processing, autonomous navigation, climate monitoring, and space-debris tracking.
The addition of the IGX Thor platform is expected to further expand the system’s AI processing capabilities with up to 5,581 FP4 TFLOPS of AI compute for real-time inference, alongside 400 GbE connectivity via the NVIDIA® ConnectX®-7 SmartNIC. A Functional Safety Island (FSI) within the Thor system-on-chip also enables safety functions through the IGX software stack to support reliable operation in mission-critical environments.
By utilizing IGX Thor evaluation hardware, Aitech aims to accelerate development cycles from concept to validation, reducing time-to-market for critical space and autonomous missions. The combination of the IGX Thor platform and Aitech’s rugged AI systems is intended to support the next generation of space-based intelligence and autonomous operations.
