skip to main content

DOE PAGESDOE PAGES

This content will become publicly available on February 5, 2019

Title: Toward performance portability of the Albany finite element analysis code using the Kokkos library

Performance portability on heterogeneous high-performance computing (HPC) systems is a major challenge faced today by code developers: parallel code needs to be executed correctly as well as with high performance on machines with different architectures, operating systems, and software libraries. The finite element method (FEM) is a popular and flexible method for discretizing partial differential equations arising in a wide variety of scientific, engineering, and industrial applications that require HPC. This paper presents some preliminary results pertaining to our development of a performance portable implementation of the FEM-based Albany code. Performance portability is achieved using the Kokkos library. We present performance results for the Aeras global atmosphere dynamical core module in Albany. Finally, numerical experiments show that our single code implementation gives reasonable performance across three multicore/many-core architectures: NVIDIA General Processing Units (GPU’s), Intel Xeon Phis, and multicore CPUs.
Authors:
 [1] ;  [2] ;  [2] ;  [3] ;  [3] ;  [3] ;  [3] ;  [3]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  2. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  3. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Publication Date:
Report Number(s):
SAND-2017-8843J
Journal ID: ISSN 1094-3420; 656341
Grant/Contract Number:
NA0003525
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
Research Org:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Sandia National Lab. (SNL-CA), Livermore, CA (United States); Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org:
USDOE National Nuclear Security Administration (NNSA); SNL Laboratory Directed Research and Development (LDRD) Program; USDOE Office of Science (SC), Biological and Environmental Research (BER) (SC-23)
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; performance portability; many-core programming; finite element code; climate simulations; Kokkos library
OSTI Identifier:
1421623

Demeshko, Irina, Watkins, Jerry, Tezaur, Irina K., Guba, Oksana, Spotz, William F., Salinger, Andrew G., Pawlowski, Roger P., and Heroux, Michael A.. Toward performance portability of the Albany finite element analysis code using the Kokkos library. United States: N. p., Web. doi:10.1177/1094342017749957.
Demeshko, Irina, Watkins, Jerry, Tezaur, Irina K., Guba, Oksana, Spotz, William F., Salinger, Andrew G., Pawlowski, Roger P., & Heroux, Michael A.. Toward performance portability of the Albany finite element analysis code using the Kokkos library. United States. doi:10.1177/1094342017749957.
Demeshko, Irina, Watkins, Jerry, Tezaur, Irina K., Guba, Oksana, Spotz, William F., Salinger, Andrew G., Pawlowski, Roger P., and Heroux, Michael A.. 2018. "Toward performance portability of the Albany finite element analysis code using the Kokkos library". United States. doi:10.1177/1094342017749957.
@article{osti_1421623,
title = {Toward performance portability of the Albany finite element analysis code using the Kokkos library},
author = {Demeshko, Irina and Watkins, Jerry and Tezaur, Irina K. and Guba, Oksana and Spotz, William F. and Salinger, Andrew G. and Pawlowski, Roger P. and Heroux, Michael A.},
abstractNote = {Performance portability on heterogeneous high-performance computing (HPC) systems is a major challenge faced today by code developers: parallel code needs to be executed correctly as well as with high performance on machines with different architectures, operating systems, and software libraries. The finite element method (FEM) is a popular and flexible method for discretizing partial differential equations arising in a wide variety of scientific, engineering, and industrial applications that require HPC. This paper presents some preliminary results pertaining to our development of a performance portable implementation of the FEM-based Albany code. Performance portability is achieved using the Kokkos library. We present performance results for the Aeras global atmosphere dynamical core module in Albany. Finally, numerical experiments show that our single code implementation gives reasonable performance across three multicore/many-core architectures: NVIDIA General Processing Units (GPU’s), Intel Xeon Phis, and multicore CPUs.},
doi = {10.1177/1094342017749957},
journal = {International Journal of High Performance Computing Applications},
number = ,
volume = ,
place = {United States},
year = {2018},
month = {2}
}