Aitech integrates RedHawk Linux to Jetson-powered supercomputers
Two Nvidia Jetson TX2-based small form factor supercomputers have been introduced by Aitech. The military-grade A176 Cyclone and the industrial-focused A177 Twister enhance real-time computing for mission-critical applications with RedHawk Linux real time operating system (RTOS).
The combination of Jetson TX2 and the advanced development environment of RedHawk Linux are increase the power-to-performance ratio, explains Aitech.
“Guaranteeing real-time processor performance, low process-dispatch latencies and minimal process run-time jitter are challenging in a real-time operating environment,” said Dan Mor, GPGPU and HPEC product line manager at Aitech. He adds: “Using NVIDIA’s CUDA driver, combined with Concurrent Real-Time’s RedHawk Linux distribution, we can overcome many of these computing obstacles.”
Incorporating the Linux RedHawk RTOS into the Jetson artificial intelligence (AI) platform, helps advance real-time computing power. It offers field-proven, open-source Linux technology, advanced GUI debugging and analysis tools, and multi-core architecture support, to support high performance embedded computing (HPEC) systems.
RedHawk is also beneficial for complex embedded projects such as intelligent devices, advanced robotic systems and other autonomous applications. It has low latency, high determinism and debugging tools to support emerging Jetson-based products.
The compact A176 Cyclone is a military-grade, fanless, conduction-cooled, rugged general purpose graphics processing unit (GPGPU) small form factor (SFF) supercomputer that measures only 5.0 square inches (3225 square mm), while providing 1TFLOP of parallel processing, drawing less than 17W and weighing less than 2.2lbs (1kg).
It has multiple hardware I/O and software options (1553, ARINC 429, camera link/HD-SDI or composite frame grabbers) as well as internal microSD storage. The able to scale to more complex, compute intensive applications, enables fast integration that saves development time and money.
The A177 has the same functionality as the A176, but is designed for less rugged industrial environments. It handles complex computational requirements, such as managing multiple data and video streams and can also reach 1TFLOPS, while consuming only 17W. It weighs the same as the A176.
The two low-cost, low-power, size, weight and power (SWaP) -optimised) SFF GPGPUs use CUDA, deep learning acceleration capabilities and the real-time Linux software to ensure hard real-time performance, while several demanding embedded applications are running.
Typical uses include high data throughput and processing, such as image and data manipulation, application of digital filters, image and frame object edge detection, image recognition and data analysis, in a number of military (A176) and industrial (A177) applications.