The world's first supercomputer on a module, Jetson TX1 is capable of delivering the performance and power efficiency needed for the latest visual computing applications. It's built around the revolutionary NVIDIA Maxwell architecture with 256 CUDA cores delivering over 1 TeraFLOPs of performance. 64-bit CPUs, 4K video endcode and decode capabilities, and a camera interface capable of 1400 MPix/s make this the best system for embedded deep learning, computer vision, graphics, and GPU computing.

The Jetson SDK supports the latest drivers, libraries, and APIs.

• cuDNN is a CUDA-accelerated library for deep learning. It's compatible with many industry-standard deep learning frameworks for both training and inference, including Caffe, Theano, and Torch.
• VisionWorks is a CUDA-accelerated library and framework for computer vision. It is an implementation of the OpenVX 1.0.1 specification with additional NVIDIA extensions.
• Jetson TX1 supports the latest graphics drivers and APIs, including OpenGL 4.5, OpenGL ES 3.1, and Vulkan.
• This module is built around an NVIDIA Maxwell processor, which means full support for NVIDIA CUDA 7.0. CUDA turns the GPU into a general-purpose graphics processor unit (GPGPU), giving developers access to tremendous parallel performance and power efficiency.