Picture for Adam Grygielski

Adam Grygielski

Applying the Roofline model for Deep Learning performance optimizations

Add code
Sep 23, 2020
Jacek Czaja, Michal Gallus, Joanna Wozna, Adam Grygielski, Luo Tao
Figure 1 for Applying the Roofline model for Deep Learning performance optimizations
Figure 2 for Applying the Roofline model for Deep Learning performance optimizations
Figure 3 for Applying the Roofline model for Deep Learning performance optimizations
Figure 4 for Applying the Roofline model for Deep Learning performance optimizations

In this paper We present a methodology for creating Roofline models automatically for Non-Unified Memory Access (NUMA) using Intel Xeon as an example. Finally, we present an evaluation of highly efficient deep learning primitives as implemented in the Intel oneDNN Library.

* oneDNN library analysis with roofline model 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon