Network to advance AI in embedded systems

With innovations like the NVIDIA Xavier-based A178 Thunder AI System, Aitech is demonstrating its support by bringing to market some of the most powerful, most compact GPGPU processing systems for the defense market.

“Joining the NVIDIA Partner Network means we can continue to expand our efforts in delivering best-in-class AI at the edge solutions across multiple industries,” said Dan Mor, GPGPU and HPEC Product Line Manager at Aitech. “With our expertise in mission-critical, rugged electronics, Aitech is bringing this powerful processing capability to a wide range of military, defense and space applications.”

The A178 system features 512 CUDA cores, twice as many as Jetson TX2-based systems, as well as 64 of NVIDIA’s new Tensor Cores, which amplify the matrix processing of large data sets by enabling higher levels of computation with lower power consumption. The new AI system can handle up to 32 TOPS (trillion operations per second) to provide local processing of high volumes of data closest to system sensors. This represents a 10x increase over initial testing of prior generations of GPGPU-based systems.

Weighing less than 5.5lbs and measuring only 8.5x3.2x6.8”, the rugged A178 Thunder is SWaP-optimized and ideal for a number of military and defense applications, such as distributed computing and signal processing in next-generation autonomous vehicles as well as surveillance, targeting and EW systems.

The A178 is supported by the EV178, Aitech’s evaluation board that allows embedded engineers to quickly develop and port AI applications to the new high-performance, rugged Xavier-based AI system.