Machine learning applications are rapidly expanding across a growing number of end markets, at the edge, in the cloud, or a hybrid of both. Xilinx provides machine learning inference solutions including the development stacks and hardware platforms for deploying advanced and efficient neural networks, algorithms and applications.
The reVISION Stack targets a wide range of vision guided machine learning applications.
Lowest latency and highest performance per watt. Up to 6x better than GPUs.
Xilinx Deep Neural Network (xfDNN) library is highly optimized for building deep learning inference applications. Designed for maximum compute efficiency at 16-bit and 8-bit integer data types.
Xilinx BLAS (xfBLAS) library is based on the level-3 Basic Linear Algebra Subprograms contains a General Matrix Multiply (GEMM) function with optimized performance at 16-bit and 8-bit integer data types. It supports matrices of any size.
Documentation, Resources, Papers, Tutorials for Edge InferenceLearn More
Documentation, Resources, Papers, Tutorials for Cloud InferenceLearn More
Enabling the use of Xilinx technologies for academic teaching and researchLearn More