Chatsworth, Calif. – September 12, 2026 -- Aitech has unveiled the 3U VPX C530 and SOSA-aligned U-C5300 GPGPU boards, delivering up to 9,728 CUDA cores, 304 Tensor Cores and 76 ray-tracing cores for defense and aerospace platforms. The rugged AI accelerators produce up to 35.8 TFLOPS of FP32 compute performance and 576 GB/s of memory bandwidth, targeting real-time AI inference at the tactical edge.
New boards replace prior-generation GPGPU configurations without increasing size, weight or power
The C530 and U-C5300 succeed Aitech's previous rugged GPU line, giving system integrators and mission computer manufacturers higher AI inference throughput and enhanced graphics performance within the same SWaP envelope. Both boards support PCIe Gen4 connectivity, CUDA software tools, and Windows and Linux operating systems.
U-C5300 aligns with SOSA standard for open-architecture defense programs
As adoption of the SOSA Technical Standard and OpenVPX architectures expands across U.S. Department of War and allied programs, the U-C5300 is designed to meet interoperability requirements and simplify integration from development through deployment. The C530 offers the same architectural upgrade without SOSA alignment, suited for compute-intensive applications such as unmanned vehicles, ISR and targeting systems.
Boards target five defense application categories from ground vehicles to electronic warfare
Aitech positions the C530 and U-C5300 for autonomous navigation and sensor fusion in ground mobile vehicles, real-time EO/IR video analytics for airborne platforms, combat management AI and radar processing for naval systems, AI-based signal classification for electronic warfare, and object detection and tracking for unmanned aircraft systems.
"By bringing NVIDIA RTX Ada performance to rugged VPX architectures, the C530 and U-C5300 enable faster AI inference, real-time analytics and greater mission autonomy while supporting the long lifecycles, open standards and software continuity that defense programs require,