An Example of Porting PETSc Applications to Heterogeneous Platforms with OpenACC

被引:1
|
作者
Chuang, Pi-Yueh [1 ]
Foertter, Fernanda S. [2 ]
机构
[1] George Washington Univ, Washington, DC 20052 USA
[2] Oak Ridge Natl Lab, Oak Ridge, TN 37830 USA
关键词
OpenACC; PETSc; GPU computing;
D O I
10.1007/978-3-319-74896-2_1
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper, we document the workflow of our practice to port a PETSc application with OpenACC to a supercomputer, Titan, at Oak Ridge National Laboratory. Our experience shows a few lines of code modifications with OpenACC directives can give us a speedup of 1.34x in a PETSc-based Poisson solver (conjugate gradient method with algebraic multigrid preconditioner). This demonstrates the feasibility of enabling GPU capability in PETSc with OpenACC. We hope our work can serve as a reference to those who are interested in porting their legacy PETSc applications to modern heterogeneous platforms.
引用
收藏
页码:3 / 19
页数:17
相关论文
共 50 条
  • [1] Experiences in porting mini-applications to OpenACC and OpenMP on heterogeneous systems
    Vergara Larrea, Veronica G.
    Budiardja, Reuben D.
    Gayatri, Rahulkumar
    Daley, Christopher
    Hernandez, Oscar
    Joubert, Wayne
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2020, 32 (20):
  • [2] Porting Clondike to Heterogeneous Platforms
    Gattermayer, Josef
    Tvrdik, Pavel
    [J]. 2012 2ND IEEE INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED AND GRID COMPUTING (PDGC), 2012, : 380 - 384
  • [3] CHALLENGES IN PORTING ENTERPRISE APPLICATIONS TO MOBILE PLATFORMS
    Tisdall, Tom
    Chobharkar, Pankaj
    Kim, Dae-Kyoo
    [J]. GETMOBILE-MOBILE COMPUTING & COMMUNICATIONS REVIEW, 2018, 22 (01) : 21 - 25
  • [4] Porting and scaling OpenACC applications on massively-parallel, GPU-accelerated supercomputers
    A. Hart
    R. Ansaloni
    A. Gray
    [J]. The European Physical Journal Special Topics, 2012, 210 : 5 - 16
  • [5] Porting and scaling OpenACC applications on massively-parallel, GPU-accelerated supercomputers
    Hart, A.
    Ansaloni, R.
    Gray, A.
    [J]. EUROPEAN PHYSICAL JOURNAL-SPECIAL TOPICS, 2012, 210 (01): : 5 - 16
  • [6] Porting the COSMO dynamical core to heterogeneous platforms using STELLA Library
    Osuna, Carlos
    Fuhrer, Oliver
    Gysi, Tobias
    Schulthess, Thomas C.
    [J]. PARALLEL COMPUTING: ON THE ROAD TO EXASCALE, 2016, 27 : 637 - 646
  • [7] Streaming Applications on Heterogeneous Platforms
    Li, Zhaokui
    Fang, Jianbin
    Tang, Tao
    Chen, Xuhao
    Yang, Canqun
    [J]. NETWORK AND PARALLEL COMPUTING, 2016, 9966 : 116 - 129
  • [8] Exploration of OpenCL Heterogeneous Programming for Porting Solidification Modeling to CPU-GPU Platforms
    Halbiniak, Kamil
    Szustak, Lukasz
    Olas, Tomasz
    Wyrzykowski, Roman
    Gepner, Pawel
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2021, 33 (04):
  • [9] Porting LASG/IAP Climate System Ocean Model to Gpus Using OpenAcc
    Jiang, Jinrong
    Lin, Pengfei
    Wang, Joey
    Liu, Hailong
    Chi, Xuebin
    Hao, Huiqun
    Wang, Yuzhu
    Wang, Wu
    Zhang, Linghan
    [J]. IEEE ACCESS, 2019, 7 : 154490 - 154501
  • [10] A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc
    Wang, D.
    Wu, W.
    Winkler, F.
    Ding, W.
    Hernandez, O.
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2014, 5 (12) : 22 - 29