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

被引：14

作者：

Demeshko, Irina ^{[1
]}

Watkins, Jerry ^{[2
]}

Tezaur, Irina K. ^{[2
]}

Guba, Oksana ^{[3
]}

Spotz, William F. ^{[3
]}

Salinger, Andrew G. ^{[3
]}

Pawlowski, Roger P. ^{[4
]}

Heroux, Michael A. ^{[5
]}

机构：

[1] Los Alamos Natl Lab, Porting Albany Code Kokkos, Los Alamos, NM USA

[2] Sandia Natl Labs, Extreme Scale Data Sci & Analyt Dept, Livermore, CA USA

[3] Sandia Natl Labs, Ctr Comp Res, POB 5800, Albuquerque, NM 87185 USA

[4] Sandia Natl Labs, Multiphys Applicat Dept, POB 5800, Albuquerque, NM 87185 USA

[5] Sandia Natl Labs, POB 5800, Albuquerque, NM 87185 USA

来源：

INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS | 2019年 / 33卷 / 02期

关键词：

Performance portability; many-core programming; finite element code; climate simulations; Kokkos library; MODEL;

D O I：

10.1177/1094342017749957

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

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 article 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. 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.

引用

页码：332 / 352

页数：21

共 39 条

[31] Firedrake: Automating the Finite Element Method by Composing Abstractions [J].

Rathgeber, Florian ;

Ham, David A. ;

Mitchell, Lawrence ;

Lange, Michael ;

Luporini, Fabio ;

Mcrae, Andrew T. T. ;

Bercea, Gheorghe-Teodor ;

Markall, Graham R. ;

Kelly, Paul H. J. .

ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 2017, 43 (03)

[32] PyOP2: A High-Level Framework for Performance-Portable Simulations on Unstructured Meshes [J].

Rathgeber, Florian ;

Markall, Graham R. ;

Mitchell, Lawrence ;

Loriant, Nicolas ;

Ham, David A. ;

Bertolli, Carlo ;

Kelly, Paul H. J. .

2012 SC COMPANION: HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS (SCC), 2012, :1116-1123

[33] ALBANY: USING COMPONENT-BASED DESIGN TO DEVELOP A FLEXIBLE, GENERIC MULTIPHYSICS ANALYSIS CODE [J].

Salinger, Andrew G. ;

Bartlett, Roscoe A. ;

Bradley, Andrew M. ;

Chen, Qiushi ;

Demeshko, Irina P. ;

Gao, Xujiao ;

Hansen, Glen A. ;

Mota, Alejandro ;

Muller, Richard P. ;

Nielsen, Erik ;

Ostien, Jakob T. ;

Pawlowski, Roger P. ;

Perego, Mauro ;

Phipps, Eric T. ;

Sun, WaiChing ;

Tezaur, Irina K. .

INTERNATIONAL JOURNAL FOR MULTISCALE COMPUTATIONAL ENGINEERING, 2016, 14 (04) :415-438

[34] Aeras: A Next Generation Global Atmosphere Model [J].

Spotz, William F. ;

Smith, Thomas M. ;

Demeshko, Irina P. ;

Fike, Jeffrey A. .

INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE, ICCS 2015 COMPUTATIONAL SCIENCE AT THE GATES OF NATURE, 2015, 51 :2097-2106

[35] A stabilized assumed deformation gradient finite element formulation for strongly coupled poromechanical simulations at finite strain [J].

Sun, WaiChing ;

Ostien, Jakob T. ;

Salinger, Andrew G. .

INTERNATIONAL JOURNAL FOR NUMERICAL AND ANALYTICAL METHODS IN GEOMECHANICS, 2013, 37 (16) :2755-2788

[36] A mass and energy conserving spectral element atmospheric dynamical core on the cubed-sphere grid [J].

Taylor, M. A. ;

Edwards, J. ;

Thomas, S. ;

Nair, R. .

SCIDAC 2007: SCIENTIFIC DISCOVERY THROUGH ADVANCED COMPUTING, 2007, 78

[37]

Ullrich P. A., 2012, Tech. rep.

[38] Comparing Hardware Accelerators in Scientific Applications: A Case Study [J].

Weber, Rick ;

Gothandaraman, Akila ;

Hinde, Robert J. ;

Peterson, Gregory D. .

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2011, 22 (01) :58-68

[39] A STANDARD TEST SET FOR NUMERICAL APPROXIMATIONS TO THE SHALLOW-WATER EQUATIONS IN SPHERICAL GEOMETRY [J].

WILLIAMSON, DL ;

DRAKE, JB ;

HACK, JJ ;

JAKOB, R ;

SWARZTRAUBER, PN .

JOURNAL OF COMPUTATIONAL PHYSICS, 1992, 102 (01) :211-224

← 1 2 3 4 →