MPI Applications on Grids: A Topology Aware Approach

被引:0
|
作者
Coti, Camille [1 ]
Herault, Thomas [1 ]
Cappello, Franck [1 ]
机构
[1] INRIA, F-91893 Orsay, France
关键词
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Porting on grids complex MPI applications involving collective communications requires significant program modification, usually dedicated to a single grid structure. The difficulty comes from the mismatch between programs organizations and grid structures: 1) large grids are hierarchical structures aggregating parallel machines through an interconnection network, decided at runtime and 2) the MPI standard does not currently provide any specific information for topology-aware applications, so almost all MPI applications have been developed following a non-hierarchical and non-flexible vision. In this paper, we propose a generic programming method and a modification of the MPI runtime environment to make MPI applications topology aware. In contrary to previous approaches, topology requirements for the application are given to the grid scheduling system. which exposes the compatible allocated topology to the application.
引用
下载
收藏
页码:466 / 477
页数:12
相关论文
共 50 条
  • [1] Topology-Aware Rank Reordering for MPI Collectives
    Mirsadeghi, Seyed H.
    Afsahi, Ahmad
    2016 IEEE 30TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2016, : 1759 - 1768
  • [2] Hybrid preemptive scheduling of MPI applications on the Grids
    Bouteiller, A
    Botiziane, HL
    Herault, T
    Lemarinier, P
    Cappello, F
    FIFTH IEEE/ACM INTERNATIONAL WORKSHOP ON GRID COMPUTING, PROCEEDINGS, 2004, : 130 - 137
  • [3] QCG-OMPI: MPI applications on grids
    Agullo, Emmanuel
    Coti, Camille
    Herault, Thomas
    Langou, Julien
    Peyronnet, Sylvain
    Rezmerita, Ala
    Cappello, Franck
    Dongarra, Jack
    FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2011, 27 (04): : 357 - 369
  • [4] MPI-ACC: Accelerator-Aware MPI for Scientific Applications
    Aji, Ashwin M.
    Panwar, Lokendra S.
    Ji, Feng
    Murthy, Karthik
    Chabbi, Milind
    Balaji, Pavan
    Bisset, Keith R.
    Dinan, James
    Feng, Wu-chun
    Mellor-Crummey, John
    Ma, Xiaosong
    Thakur, Rajeev
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2016, 27 (05) : 1401 - 1414
  • [5] Multi-core and Network Aware MPI Topology Functions
    Rashti, Mohammad Javad
    Green, Jonathan
    Balaji, Pavan
    Afsahi, Ahmad
    Gropp, William
    RECENT ADVANCES IN THE MESSAGE PASSING INTERFACE, 2011, 6960 : 50 - +
  • [6] Portable Topology-Aware MPI-I/O
    Latham, Rob
    Bautista-Gomez, Leonardo
    Balaji, Pavan
    2017 IEEE 23RD INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS (ICPADS), 2017, : 710 - 719
  • [7] An MPI interface for application and hardware aware Cartesian topology optimization
    Niethammer, Christoph
    Rabenseifner, Rolf
    EUROMPI'19: PROCEEDINGS OF THE 26TH EUROPEAN MPI USERS' GROUP MEETING, 2019,
  • [8] Topology-Aware Strategy for MPI-IO Operations in Clusters
    Liu, Weifeng
    Zhou, Jie
    Guo, Meng
    JOURNAL OF OPTIMIZATION, 2018, 2018
  • [9] Dynamic and adaptive topology-aware load balancing for Grids
    Barkallah, Haitham
    Gzara, Mariem
    Ben Abdallah, Hanene
    2014 IEEE 17TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE), 2014, : 1679 - 1684
  • [10] A Cost-Aware Resource Selection Approach for Data-intensive Applications in Grids
    Liu, Wei
    Shi, Feiyan
    Li, Hongfeng
    Xu, Zhihao
    2ND INTERNATIONAL SYMPOSIUM ON COMPUTER NETWORK AND MULTIMEDIA TECHNOLOGY (CNMT 2010), VOLS 1 AND 2, 2010, : 182 - 185