As AI applications increase their demand for computing power, CPUs, GPUs and dedicated acceleration chips can all work together to enhance system computing power through heterogeneous computing. We collectively call them XPU. Intel continues to add new features to enhance AI computing in newly launched CPUs and GPUs, such as Intel® Deep Learning Boost, Intel® Advanced Matrix Extensions, and Intel® Xe Matrix Extensions technologies. These new features can greatly accelerate AI training and reasoning performance. In order to make it easier for users to use these hardware features, Intel also launched the Intel® AI Analytics Toolkit software toolkit, which includes AI framework and middleware optimized for new hardware features for users to use for free. Among them, there are AI framework performance enhancement tools provided in the form of plug-ins such as Intel Extension® for Tensorflow*/Pytorch*/Scikit-learn*.