miniGAN: A Generative Adversarial Network proxy application WBS 2.2.6.08 ECP-2.1.3 (Q3 FY2020 Milestone Report) (V.1.0)

Technical Report · Wed Jul 01 04:00:00 EDT 2020

DOI:https://doi.org/10.2172/1763585· OSTI ID:1763585

Ellis, John Austin ^[1]

---

1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

In order to support the machine learning co-design needs of ECP applications in current and future DOE HPC hardware, we have developed a generative adversarial network (GAN) proxy application, miniGAN, that has been released through the ECP proxy application suite. The proxy application is representative of the needs of ExaLearn's target applications, specifically the Cosmoflow and ExaGAN cosmology applications and the ExaWind energy application. The proxy application also demonstrates the first use of performance portable kernels within widely-used machine learning frameworks: PyTorch (Facebook) and Horovod (Uber). We provide performance scaling results for similar workloads to ExaGAN and a profile of individual GAN training components.

• Research Organization: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); USDOE National Nuclear Security Administration (NNSA)
• Contributing Organization: Oak Ridge National Lab (ORNL)
• DOE Contract Number: AC04-94AL85000; NA0003525; AC05-00OR22725
• OSTI ID: 1763585
• Report Number(s): SAND--2020-6768R; 687089
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING