VPIC 2.0: Next Generation Particle-in-Cell Simulations

被引:37
作者
Bird, Robert [1 ]
Tan, Nigel [2 ]
Luedtke, Scott, V [1 ]
Harrell, Stephen Lien [3 ]
Taufer, Michela [2 ]
Albright, Brian [1 ]
机构
[1] Los Alamos Natl Lab, Los Alamos, NM 87545 USA
[2] Univ Tennessee, Knoxville, TN 37996 USA
[3] Univ Texas Austin, Texas Adv Comp Ctr, Austin, TX 78712 USA
关键词
Plasmas; Hardware; Physics; Libraries; Mathematical model; Shape; Layout; Simulation; portability; plasma physics; particle-in-cell; CHARGE CONSERVATION; PERFORMANCE; CODE;
D O I
10.1109/TPDS.2021.3084795
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
VPIC is a general purpose particle-in-cell simulation code for modeling plasma phenomena such as magnetic reconnection, fusion, solar weather, and laser-plasma interaction in three dimensions using large numbers of particles. VPIC's capacity in both fidelity and scale makes it particularly well-suited for plasma research on pre-exascale and exascale platforms. In this article, we demonstrate the unique challenges involved in preparing the VPIC code for operation at exascale, outlining important optimizations to make VPIC efficient on accelerators. Specifically, we show the work undertaken in adapting VPIC to exploit the portability-enabling framework Kokkos and highlight the enhancements to VPIC's modeling capabilities to achieve performance at exascale. We assess the achieved performance-portability trade-off through a suite of studies on nine different varieties of modern pre-exascale hardware. Our performance-portability study includes weak-scaling runs on three of the top ten TOP500 supercomputers, as well as a comparison of low-level system performance of hardware from four different vendors.
引用
收藏
页码:952 / 963
页数:12
相关论文
共 45 条
[1]   Multi-dimensional dynamics of stimulated Brillouin scattering in a laser speckle: Ion acoustic wave bowing, breakup, and laser-seeded two-ion-wave decay [J].
Albright, B. J. ;
Yin, L. ;
Bowers, K. J. ;
Bergen, B. .
PHYSICS OF PLASMAS, 2016, 23 (03)
[2]  
Birdsall C. K., 2004, PLASMA PHYS VIA COMP
[3]   3-D ICEPIC simulations of the relativistic klystron oscillator [J].
Blahovec Jr., Joseph D. ;
Bowers, Lester A. ;
Luginsland, John W. ;
Sasser, Gerald E. ;
Watrous, John J. .
2000, IEEE, Piscataway, NJ, United States (28)
[4]  
Bowers KJ, 2008, INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS, P32
[5]   Advances in petascale kinetic plasma simulation with VPIC and Roadrunner [J].
Bowers, K. J. ;
Albright, B. J. ;
Yin, L. ;
Daughton, W. ;
Roytershteyn, V. ;
Bergen, B. ;
Kwan, T. J. T. .
SCIDAC 2009: SCIENTIFIC DISCOVERY THROUGH ADVANCED COMPUTING, 2009, 180
[6]   Ultrahigh performance three-dimensional electromagnetic relativistic kinetic plasma simulation [J].
Bowers, K. J. ;
Albright, B. J. ;
Yin, L. ;
Bergen, B. ;
Kwan, T. J. T. .
PHYSICS OF PLASMAS, 2008, 15 (05)
[7]   PIConGPU: A Fully Relativistic Particle-in-Cell Code for a GPU Cluster [J].
Burau, Heiko ;
Widera, Renee ;
Hoenig, Wolfgang ;
Juckeland, Guido ;
Debus, Alexander ;
Kluge, Thomas ;
Schramm, Ulrich ;
Cowan, Tomas E. ;
Sauerbrey, Roland ;
Bussmann, Michael .
IEEE TRANSACTIONS ON PLASMA SCIENCE, 2010, 38 (10) :2831-2839
[8]   Electron energization and structure of the diffusion region during asymmetric reconnection [J].
Chen, Li-Jen ;
Hesse, Michael ;
Wang, Shan ;
Bessho, Naoki ;
Daughton, William .
GEOPHYSICAL RESEARCH LETTERS, 2016, 43 (06) :2405-2412
[9]   Toward performance portability of the Albany finite element analysis code using the Kokkos library [J].
Demeshko, Irina ;
Watkins, Jerry ;
Tezaur, Irina K. ;
Guba, Oksana ;
Spotz, William F. ;
Salinger, Andrew G. ;
Pawlowski, Roger P. ;
Heroux, Michael A. .
INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2019, 33 (02) :332-352
[10]   Plasma Energization in Colliding Magnetic Flux Ropes [J].
Du, Senbei ;
Guo, Fan ;
Zank, Gary P. ;
Li, Xiaocan ;
Stanier, Adam .
ASTROPHYSICAL JOURNAL, 2018, 867 (01)