High-Performance TensorFlow on Intel Xeon Using NGraph

Compiler techniques to speed-up deep learning have seen a lot of recent research activity. The article is about Intel's nGraph and provides comparisons to Google's XLA:

https://www.tensorflow.org/performance/xla/

Amazon and University of Washington have NNVM:

https://aws.amazon.com/blogs/machine-learning/introducing-nn...

And there's University of Illinois's DLVM:

https://arxiv.org/abs/1711.03016