White Paper

w w w. m r c y. c o m WHITE PAPER 6 Lockheed's Lightening-II (F-35) is a fifth generation fighter that is looking to AI to aid its integrated avionics, fused sensor displays that combine information from on and off-board sensors to increase the pilot's situational awareness and improve target identification and weapon delivery. HPEC applications are rugged, miniaturized and optimized for the best performance per watt of power and per unit of volume. A typical defense program evolves from concept to production in 3-5 years and may be deployed for decades. Considerable time (years) is spent optimizing the software to make the most efficient use of the hardware, minimizing its size, weight and power (SWaP). An opportunity to remove a processing blade for example, from a HPEC system, may reduce the consumed power by 100-200 watts, while also saving pounds of weight and creating a smaller footprint. The hardware challenge for deploying AI capability at the tactical edge pivots around making data center technology sufficiently small, light and power-efficient. Additionally, these processing resources should be rugged for survivability and run cool for reliability. For system integrity, trust and security must be built-in and for critical mission, effector actuation determinism and inherent flight safety-worthiness have to be both demonstrated and provable. AI hardware made rugged, smaller and cooler As the number of AI applications grow, they will no longer be restrained to the data center. As big processing capability is made smaller, uses less power and is made rugged, AI applications will increasingly power smarter, more capable military platforms and missions. Many of these physical enablers already exist. Modern electronic packaging technology is able to shrink compute architectures though system-in-package and wafer stacking techniques to reduce system volume. High-performance cooling systems efficiently remove the heat generated from these miniaturized systems for reliable, full-throttle deterministic processing. Rugged fabrication techniques enable even the most powerful data center CPU and GPGPU processors and accelerators to be robustly soldered to their substrate regardless of their native interconnects. Electronic packaging technology has come of age to enable data center like capabilities to be shrunk to smaller form-factors, including OpenVPX; the most widely adopted and supported rugged high-performance open system compute architecture for defense programs. Another white paper in this series describes in detail how data center hardware is miniaturized, made rugged and cooled using new fabrication and packaging technologies. AI made secure and trusted AI algorithms create a neural network, which may be thought of as a computer data representation of our brains. This neural network is trained using data to make it "intelligent". In the case of defense AI systems, the data used for training is often sensitive or classified. Ultimately, the neural network could contain a brain equivalent to someone who has been trained on all military intelligence, assets, strategies, personnel, and anything else known collectively by military and intelligence agencies. Although we are not at this stage, we are marching in that direction. There are already AI trained brains that contain vast amounts of information or AI derived information that is highly restricted. Secure embedded AI processing system building blocks. Embedded rugged AI processing blades, compliant to the 3U OpenVPX open system architrure (ANSI/VITA 65) are available as air, conduction or liquid cooled blades for deployment on the ground, in the air, in and under the sea. Secure embedded AI processing system building blocks. Embedded rugged AI processing blades in various deployable packages are compliant to the 6U OpenVPX open system architrure (ANSI/ VITA 65). At about a tenth of the size of a data center server these blades are powered with the same processors and may be air or liquid cooled.

• Cover