Intel® MKL-DNN is an open source, performance-enhancing library for accelerating deep learning frameworks like like Caffe* and Theano* on Intel® Architecture.
clDNN is an open source performance library for deep learning applications that accelerates inference on Intel® Processor Graphics.
Intel® Machine Learning Scaling Library (Intel® MLSL) provides efficient implementation of communication patterns used in deep learning.
Intel® Data Analytics Acceleration Library (Intel® DAAL) is a highly optimized library of computationally intensive routines for Intel® architecture-based platforms that helps speed big data analytics.
BigDL* is an open-source distributed deep learning library that can run directly on top of existing Intel® Xeon® processor-based Apache Spark* or Apache Hadoop* clusters. It leverages Intel® Math Kernel Library (Intel® MKL) to enable comprehensive support for deep learning on frameworks including Caffe* and Torch*.