Niranjan Hasabnis, Deep Learning Software Engineer, Intel TensorFlow is an open source software library that has seen a surge of use cases in deep learning. While TensorFlow supports both CPUs and GPUs, performance on CPUs was not fully optimized, thereby delivering poor performance. In this talk we describe Intel’s efforts in optimizing TensorFlow for Intel® Xeon™ processors (code name Skylake). We also describe how deep learning framework users can leverage these optimizations and provide specific tuning tips to get the best performance on Skylake platforms.