skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: 167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation

Abstract

An artificial intelligence system called MENNDL, which used 25,200 NVIDIA Volta GPUs on Oak Ridge National Laboratory's Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity towards nanofabricating materials automatically. MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.

Authors:
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
OSTI Identifier:
1503996
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 18) - Dallas, Texas, United States of America - 11/11/2018 5:00:00 AM-11/16/2018 5:00:00 AM
Country of Publication:
United States
Language:
English

Citation Formats

Patton, Robert M., Johnston, Travis, Young, Steven R., Schuman, Catherine D., March, Don, Potok, Thomas E., Rose, Derek, Lim, Seung-Hwan, Karnowski, Thomas, Ziatdinov, Maxim A., and Kalinin, Sergei V. 167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation. United States: N. p., 2018. Web. doi:10.1109/SC.2018.00053.
Patton, Robert M., Johnston, Travis, Young, Steven R., Schuman, Catherine D., March, Don, Potok, Thomas E., Rose, Derek, Lim, Seung-Hwan, Karnowski, Thomas, Ziatdinov, Maxim A., & Kalinin, Sergei V. 167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation. United States. doi:10.1109/SC.2018.00053.
Patton, Robert M., Johnston, Travis, Young, Steven R., Schuman, Catherine D., March, Don, Potok, Thomas E., Rose, Derek, Lim, Seung-Hwan, Karnowski, Thomas, Ziatdinov, Maxim A., and Kalinin, Sergei V. Thu . "167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation". United States. doi:10.1109/SC.2018.00053. https://www.osti.gov/servlets/purl/1503996.
@article{osti_1503996,
title = {167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation},
author = {Patton, Robert M. and Johnston, Travis and Young, Steven R. and Schuman, Catherine D. and March, Don and Potok, Thomas E. and Rose, Derek and Lim, Seung-Hwan and Karnowski, Thomas and Ziatdinov, Maxim A. and Kalinin, Sergei V.},
abstractNote = {An artificial intelligence system called MENNDL, which used 25,200 NVIDIA Volta GPUs on Oak Ridge National Laboratory's Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity towards nanofabricating materials automatically. MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.},
doi = {10.1109/SC.2018.00053},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2018},
month = {11}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: