‹ Back to Video Series: Artificial Intelligence and Machine Learning Track

Accelerate Machine Learning Software on Intel® Architecture

  • Overview
  • Resources

Speaker: Ananth Sankaranarayanan, Intel

In this talk, we present the details of the optimization and characterization of Intel® Distribution for Caffe* and the support of new deep learning convolutional neural network primitives in the Intel® Math Kernel Library. We present performance data for deep learning training for image recognition that achieves greater than 24 times speedup performance with an Intel® Xeon Phi™ processor 7250 when compared to Caffe*. In addition, we present performance data that shows training time is further reduced by 40 times the speedup with a 128-node Intel® Xeon Phi™ processor cluster over Intel® Omni-Path Architecture (Intel® OPA).