Comparison of Graphcore IPUs and Nvidia GPUsfor cosmology applications
arXiv:2106.02465
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.
arXiv comment11 pages, 4 figures
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Auto-Encoding Variational Bayes
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- NICE: Non-linear Independent Components Estimation
- Weight Uncertainty in Neural Networks
- Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
- LSST Science Book, Version 2.0
- Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
- Euclid Imaging Consortium Science Book
- Fink, a new generation of broker for the LSST community
- Dissecting the Graphcore IPU Architecture via Microbenchmarking
- Deep Generative Models for Galaxy Image Simulations
- Deblending galaxies with Variational Autoencoders: a joint multi-band, multi-instrument approach
- Studying the potential of Graphcore IPUs for applications in Particle Physics