Highly-Ccalable, physics-informed GANs for learning solutions of stochastic PDEs

Liu Yang, Sean Treichler, Thorsten Kurth, Keno Fischer, David Barajas-Solano, Josh Romero, Valentin Churavy, Alexandre Tartakovsky, Michael Houston, Prabhat, George Karniadakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Uncertainty quantification for forward and inverse problems is a central challenge across physical and biomedical disciplines. We address this challenge for the problem of modeling subsurface flow at the Hanford Site by combining stochastic computational models with observational data using physics-informed GAN models. The geographic extent, spatial heterogeneity, and multiple correlation length scales of the Hanford Site require training a computationally intensive GAN model to thousands of dimensions. We develop a highly optimized implementation that scales to 27,500 NVIDIA Volta GPUs. We develop a hierarchical scheme based on a multi-player game-theoretic approach for exploiting domain parallelism, map discriminators and generators to multiple GPUs, and employ efficient communication schemes to ensure training stability and convergence. Our implementation scales to 4584 nodes on the Summit supercomputer with a 93.1%scaling efficiency, achieving peak and sustained half-precision. rates of 1228 PF/s and 1207 PF/s.

Original languageEnglish (US)
Title of host publicationProceedings of DLS 2019
Subtitle of host publicationDeep Learning on Supercomputers - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-11
Number of pages11
ISBN (Electronic)9781728160115
DOIs
StatePublished - Nov 2019
Externally publishedYes
Event3rd IEEE/ACM Workshop on Deep Learning on Supercomputers, DLS 2019 - Denver, United States
Duration: Nov 17 2019 → …

Publication series

NameProceedings of DLS 2019: Deep Learning on Supercomputers - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference3rd IEEE/ACM Workshop on Deep Learning on Supercomputers, DLS 2019
Country/TerritoryUnited States
CityDenver
Period11/17/19 → …

Keywords

  • Deep Learning
  • GANs
  • Stochastic PDEs

ASJC Scopus subject areas

  • Information Systems
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Highly-Ccalable, physics-informed GANs for learning solutions of stochastic PDEs'. Together they form a unique fingerprint.

Cite this