CosmoFlow: Using Deep Learning to Learn the Universe at Scale
This work addresses the high computational cost of applying deep learning to cosmology, enabling more efficient large-scale simulations for researchers in astrophysics and physics.
The authors tackled the computational challenge of using deep learning for cosmological parameter prediction by developing CosmoFlow, a scalable application that achieved 3.5 Pflop/s performance on 8192 nodes with 77% parallel efficiency, enabling unprecedented accuracy in predicting parameters like Ω_M, σ_8, and n_s from 3D dark matter data.
Deep learning is a promising tool to determine the physical model that describes our universe. To handle the considerable computational cost of this problem, we present CosmoFlow: a highly scalable deep learning application built on top of the TensorFlow framework. CosmoFlow uses efficient implementations of 3D convolution and pooling primitives, together with improvements in threading for many element-wise operations, to improve training performance on Intel(C) Xeon Phi(TM) processors. We also utilize the Cray PE Machine Learning Plugin for efficient scaling to multiple nodes. We demonstrate fully synchronous data-parallel training on 8192 nodes of Cori with 77% parallel efficiency, achieving 3.5 Pflop/s sustained performance. To our knowledge, this is the first large-scale science application of the TensorFlow framework at supercomputer scale with fully-synchronous training. These enhancements enable us to process large 3D dark matter distribution and predict the cosmological parameters $Ω_M$, $σ_8$ and n$_s$ with unprecedented accuracy.