{"id":3443,"date":"2017-05-01T09:15:15","date_gmt":"2017-05-01T16:15:15","guid":{"rendered":"https:\/\/aitechsystems.com\/?p=3443"},"modified":"2023-03-16T10:22:12","modified_gmt":"2023-03-16T08:22:12","slug":"news-a176-jetson-tx2","status":"publish","type":"post","link":"https:\/\/aitechsystems.com\/news-a176-jetson-tx2\/","title":{"rendered":"Increased Data Intelligence in New Rugged GPGPU System Provides Critical Real-Time Image Recognition"},"content":{"rendered":"
<\/p>\n
Technical highlights:<\/strong><\/p>\n Chatsworth<\/strong>, Calif., May 2017 <\/strong>\u2013 Military intelligence now has access to enhanced data and imaging processing through Aitech Defense Systems\u2019 next generation A176, a\u00a0rugged GPGPU\u00a0system that incorporates the\u00a0NVIDIA Jetson TX2<\/a><\/span> system-on-module (SoM).<\/p>\n Building on the company\u2019s field-proven A176 Cyclone GPGPU supercomputer launched in 2016, Aitech\u2019s latest high-performance embedded computer (HPEC) uses the Jetson TX2 to provide twice the performance of its predecessor, or run at more than twice the power efficiency, while drawing less than 7.5 watts of power.<\/p>\n The new A176 features the same fanless, conduction-cooled design and measures only 25.5 cubic inches for high performance in a small form factor (SFF) HPEC system.<\/p>\n \u201cWith the increased power to performance ratio that the Jetson TX2 infuses into our next generation A176 GPGPU, we believe the use of deep learning in embedded computing is poised to grow exponentially,\u201d said Dan Mor, product line manager, Aitech Defense Systems. \u201cThe industry hasn\u2019t seen this type of processing in a compact form factor to date \u2013 it\u2019s truly redefining what is possible.\u201d<\/p>\n In addition to incorporating the new NVIDIA Jetson TX2 module, the unit now supports more hardware I\/O and software options (1553, ARINC 429, Camera Link Frame Grabber), allowing even faster integration to save development time and money.<\/p>\n The internal microSD storage enables more design flexibility to scale the supercomputer to more complex compute-intensive applications. This includes data convolutions and transpositions, image and data manipulation, application of digital filters, image and frame object edge detection, and image recognition and data analysis.<\/p>\n\n