Embedded computing products are everywhere. In drones whirring overhead. On wrists tracking heartbeats and incoming tweets. On walls regulating the temperature of homes.
These devices are useful in their own ways, but they aren’t particularly powerful.
At NVIDIA, we’re focused on the tough challenges. And this week at Embedded World, just outside Munich in Nuremburg, Germany, we showcased partners who are using our tools where space, weight and power constraints are the norm.
By unlocking the power of the GPU for embedded applications, we’re helping developers bring computer vision to drones, artificial intelligence to robots, and a host of other sophisticated applications that can sense, interpret and respond to the world around us.
We married our embedded processors to a platform that puts power and efficiency at the fingertips of developers.
In the case of our Jetson TK1 development kit, we offer the same GPU architecture that powers some of the world’s fastest supercomputers. This provides a fully functional accelerated computing platform to quickly develop and deploy compute-intensive systems for computer vision, robotics, medicine and more.
GE’s new Mini COM Express module uses the Tegra K1 processor to deliver 326 GFLOPS of performance—while consuming less than 10 watts of power. Compact in size and made rugged for harsh environments, the module targets commercial, aerospace and military applications for everything from industrial process automation to medical imaging to sensor processing.
Concurrent Technologies’ new AdvancedMC module is fitted with up to four Tegra K1 processors for 1.3 TFLOPS of performance on a board that roughly takes up the area of a postcard. It’s designed for applications such as transcoding, image analysis and encryption, where server-based equipment is otherwise impractical to use.
And SECO’s new COM-Express Type 6 compact module is based on the Tegra K1 mobile processor.
Our booth included a real-time analysis of the distribution of people visiting us, with SECO and SmartEye. Parrot showed a computer vision tech demo that models in fine detail the environment it observes.
Find out more about our latest offerings in embedded computing here.