Benchmarking Machine Learning in HEP

The interest on machine learning workloads in the HEP community has increased exponentially in the last years, making more and more important the need of a thorough benchmarking of the most relevant/significant workloads that are going to run on the experiments. The purpose of this project is to build a set of techniques to benchmark deep neural networks on different
hardware. By using different tools and methodologies we make several important observations and conclusions based on the performance of deep learning application running on GPUs which have different compute capabilities.