Comparison of Graphcore IPUs and Nvidia GPUs for cosmology applications



Abstract

This paper represents the first investigation of the suitability and performance of Graphcore Intelligence Processing Units (IPUs) for deep learning applications in cosmology. It presents the benchmark between a Nvidia V100 GPU and a Graphcore MK1 (GC2) IPU on three cosmological use cases: a classical deep neural network and a Bayesian neural network (BNN) for galaxy shape estimation, and a generative network for galaxy images production. The results suggest that IPUs could be a potential avenue to address the increasing computation needs in cosmology.



Paper

The paper can be found here: https://arxiv.org/abs/2106.02465.



Blog post and Video

This work was done with the help of people from Graphcore and they wrote a blog post (click here) and edited the video on the left to summarize and present this work.



Presentation at the IN2P3/IRFU Machine Learning workshop

I aso presented this work at the IN2P3/IRFU Machine Learning workshop. The slides are available here and the video on the left is the recording of the presentation.