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

This content will become publicly available on February 14, 2020

Title: Harnessing billions of tasks for a scalable portable hydrodynamic simulation of the merger of two stars

Abstract

We propose a highly scalable demonstration of a portable asynchronous many-task programming model and runtime system applied to a grid-based adaptive mesh refinement hydrodynamic simulation of a double white dwarf merger with 14 levels of refinement that spans 17 orders of magnitude in astrophysical densities. The code uses the portable C++ parallel programming model that is embodied in the HPX library and being incorporated into the ISO C++ standard. The model reflects a significant shift from existing bulk synchronous parallel programming models under consideration for exascale systems. Through the use of the Futurization technique, seemingly sequential code is transformed into wait-free asynchronous tasks. We demonstrate the potential of our model by showing results from strong scaling runs on National Energy Research Scientific Computing Center’s Cori system (658,784 Intel Knight’s Landing cores) that achieve a parallel efficiency of 96.8% using billions of asynchronous tasks.

Authors:
 [1];  [2];  [3];  [4]; ORCiD logo [5];  [6];  [7];  [8];  [9];  [8];  [8];  [8];  [9];  [10];  [8]
  1. Univ. of Erlangen-Nuremberg (FAU), Bavaria (Germany)
  2. NVIDIA, Santa Clara, CA (United States)
  3. Univ. of Oregon, Eugene, OR (United States)
  4. National Supercomputing Centre, Lugano (Switzerland)
  5. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  6. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  7. GSI-Helmholtzzentrum fur Schwerionenforschung, Darmstadt (Germany)
  8. Louisiana State Univ., Baton Rouge, LA (United States)
  9. Univ. of Stuttgart, Baden-Württemberg (Germany)
  10. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
Contributing Org.:
The STE||AR Group
OSTI Identifier:
1524389
Report Number(s):
LA-UR-17-31311
Journal ID: ISSN 1094-3420
Grant/Contract Number:  
89233218CNA000001; AC02-05CH11231; SC0008638; SC0008714; AC52-07NA27344
Resource Type:
Accepted Manuscript
Journal Name:
International Journal of High Performance Computing Applications
Additional Journal Information:
Journal Name: International Journal of High Performance Computing Applications; Journal ID: ISSN 1094-3420
Publisher:
SAGE
Country of Publication:
United States
Language:
English
Subject:
parallel runtime; binary star merger; asynchronous tasks; HPX; C++

Citation Formats

Heller, Thomas, Lelbach, Bryce Adelstein, Huck, Kevin A., Biddiscombe, John, Grubel, Patricia, Koniges, Alice E., Kretz, Matthias, Marcello, Dominic, Pfander, David, Serio, Adrian, Frank, Juhan, Clayton, Geoffrey C., Pflüger, Dirk, Eder, David, and Kaiser, Hartmut. Harnessing billions of tasks for a scalable portable hydrodynamic simulation of the merger of two stars. United States: N. p., 2019. Web. doi:10.1177/1094342018819744.
Heller, Thomas, Lelbach, Bryce Adelstein, Huck, Kevin A., Biddiscombe, John, Grubel, Patricia, Koniges, Alice E., Kretz, Matthias, Marcello, Dominic, Pfander, David, Serio, Adrian, Frank, Juhan, Clayton, Geoffrey C., Pflüger, Dirk, Eder, David, & Kaiser, Hartmut. Harnessing billions of tasks for a scalable portable hydrodynamic simulation of the merger of two stars. United States. doi:10.1177/1094342018819744.
Heller, Thomas, Lelbach, Bryce Adelstein, Huck, Kevin A., Biddiscombe, John, Grubel, Patricia, Koniges, Alice E., Kretz, Matthias, Marcello, Dominic, Pfander, David, Serio, Adrian, Frank, Juhan, Clayton, Geoffrey C., Pflüger, Dirk, Eder, David, and Kaiser, Hartmut. Thu . "Harnessing billions of tasks for a scalable portable hydrodynamic simulation of the merger of two stars". United States. doi:10.1177/1094342018819744.
@article{osti_1524389,
title = {Harnessing billions of tasks for a scalable portable hydrodynamic simulation of the merger of two stars},
author = {Heller, Thomas and Lelbach, Bryce Adelstein and Huck, Kevin A. and Biddiscombe, John and Grubel, Patricia and Koniges, Alice E. and Kretz, Matthias and Marcello, Dominic and Pfander, David and Serio, Adrian and Frank, Juhan and Clayton, Geoffrey C. and Pflüger, Dirk and Eder, David and Kaiser, Hartmut},
abstractNote = {We propose a highly scalable demonstration of a portable asynchronous many-task programming model and runtime system applied to a grid-based adaptive mesh refinement hydrodynamic simulation of a double white dwarf merger with 14 levels of refinement that spans 17 orders of magnitude in astrophysical densities. The code uses the portable C++ parallel programming model that is embodied in the HPX library and being incorporated into the ISO C++ standard. The model reflects a significant shift from existing bulk synchronous parallel programming models under consideration for exascale systems. Through the use of the Futurization technique, seemingly sequential code is transformed into wait-free asynchronous tasks. We demonstrate the potential of our model by showing results from strong scaling runs on National Energy Research Scientific Computing Center’s Cori system (658,784 Intel Knight’s Landing cores) that achieve a parallel efficiency of 96.8% using billions of asynchronous tasks.},
doi = {10.1177/1094342018819744},
journal = {International Journal of High Performance Computing Applications},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {2}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on February 14, 2020
Publisher's Version of Record

Save / Share: