Hybrid Parallel Programming with MPI/StarSs

被引：0
|
作者：
Labarta, Jesus [1 ,2 ]
Marjanovic, Vladimir [1 ]
Ayguade, Eduard [1 ,2 ]
Badia, Rosa M. [1 ,3 ]
Valero, Mateo [1 ,2 ]
机构：
[1] Barcelona Supercomp Ctr, Barcelona 08034, Spain
[2] Univ Politecn Cataluna, E-08028 Barcelona, Spain
[3] CSIC, Artificial Intelligence Res Inst IIIA, Madrid, Spain
来源：
APPLICATIONS, TOOLS AND TECHNIQUES ON THE ROAD TO EXASCALE COMPUTING | 2012年 / 22卷
关键词：
Parallel programming models; MPI/StarSs;
D O I：
10.3233/978-1-61499-041-3-621
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper describes how hybrid MPI/StarSs programming provides an efficient way to program future clusters of multicore nodes. The use of the programming model results in achieving overlap between communication and computation while maintaining a simple source code structure. Additional benefits include tolerance to limited bandwidth availability and tolerance to OS noise. This paper presents three different implementations of this approach due to the requirements of three different supercomputing platforms: MareNostrum, Jugene and Juropa
引用
收藏
页码：621 / 628
页数：8
相关论文
共 50 条
  • [1] Hybrid Parallel Programming with MPI and Unified Parallel C
    Dinan, James
    Balaji, Pavan
    Lusk, Ewing
    Sadayappan, P.
    Thakur, Rajeev
    PROCEEDINGS OF THE 2010 COMPUTING FRONTIERS CONFERENCE (CF 2010), 2010, : 177 - 185
  • [2] Experience with the MPI/STARSS programming model on a large production code
    Broemmel, Dirk
    Gibbon, Paul
    Garcia, Marta
    Lopez, Victor
    Marjanovic, Vladimir
    Labarta, Jesus
    PARALLEL COMPUTING: ACCELERATING COMPUTATIONAL SCIENCE AND ENGINEERING (CSE), 2014, 25 : 357 - 366
  • [3] MPI + MPI: a new hybrid approach to parallel programming with MPI plus shared memory
    Torsten Hoefler
    James Dinan
    Darius Buntinas
    Pavan Balaji
    Brian Barrett
    Ron Brightwell
    William Gropp
    Vivek Kale
    Rajeev Thakur
    Computing, 2013, 95 : 1121 - 1136
  • [4] MPI + MPI: a new hybrid approach to parallel programming with MPI plus shared memory
    Hoefler, Torsten
    Dinan, James
    Buntinas, Darius
    Balaji, Pavan
    Barrett, Brian
    Brightwell, Ron
    Gropp, William
    Kale, Vivek
    Thakur, Rajeev
    COMPUTING, 2013, 95 (12) : 1121 - 1136
  • [5] Parallel programming for OSEM reconstruction with MPI, OpenMP, and hybrid MPI-OpenMP
    Jones, MD
    Yao, RT
    2004 IEEE NUCLEAR SCIENCE SYMPOSIUM CONFERENCE RECORD, VOLS 1-7, 2004, : 3036 - 3042
  • [6] Parallel programming with interoperable MPI
    George, WL
    Hagedorn, JG
    Devaney, JE
    DR DOBBS JOURNAL, 2004, 29 (02): : 49 - 53
  • [7] Hybrid MPI plus UPC parallel programming paradigm on an SMP cluster
    Bozkus, Zeki
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2012, 20 : 1389 - 1407
  • [8] Hybrid CUDA, OpenMP, and MPI parallel programming on multicore GPU clusters
    Yang, Chao-Tung
    Huang, Chih-Lin
    Lin, Cheng-Fang
    COMPUTER PHYSICS COMMUNICATIONS, 2011, 182 (01) : 266 - 269
  • [9] Hybrid MPI-OpenMP programming for parallel OSEM PET reconstruction
    Jones, M. D.
    Yao, R.
    Bhole, C. P.
    IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2006, 53 (05) : 2752 - 2758
  • [10] Automatic Tuning of Parallel Multigrid Solvers Using OpenMP/MPI Hybrid Parallel Programming Models
    Nakajima, Kengo
    HIGH PERFORMANCE COMPUTING FOR COMPUTATIONAL SCIENCE - VECPAR 2012, 2013, 7851 : 435 - 450
12345