论文标题
应用车顶线模型进行深度学习绩效优化
Applying the Roofline model for Deep Learning performance optimizations
论文作者
论文摘要
在本文中，我们提出了一种使用Intel Xeon自动创建屋顶线模型（NUMA）的方法。最后，我们介绍了Intel Onednn库中实现的高效深度学习原始素的评估。
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.
