Implementation of MPI on NEC's SX-4 multi-node architecture

被引：0
|
作者：
Hempel, R [1 ]
Ritzdorf, H [1 ]
Zimmerman, F [1 ]
机构：
[1] NEC Europe Ltd, Computat & Commun Res Labs, D-53757 St Augustin, Germany
来源：
RECENT ADVANCES IN PARALLEL VIRTUAL MACHINE AND MESSAGE PASSING INTERFACE | 1997年 / 1332卷
关键词：
D O I：
暂无
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
MPICH is a portable implementation of MPI, the international standard for message-passing programming. This paper describes the port of MPICH to the NEC SX-4 parallel vector-supercomputer. By fine-tuning the implementation to the underlying architecture, the message-passing performance could be greatly enhanced. Some of the performance optimizations which led to NEC's current product-level MPI library are presented. Finally, there is an outlook on future activities which will include further optimizations and functional extensions.
引用
收藏
页码：185 / 193
页数：9
相关论文
共 50 条
  • [1] Design and implementation of gang scheduler on multi-node SX-4 and SX-5 supercomputer systems
    Suzuki, K
    Yabuki, K
    [J]. NEC RESEARCH & DEVELOPMENT, 1998, 39 (04): : 396 - 401
  • [2] The MPI/SX implementation of MPI for NEC's SX-6 and other NEC platforms
    Golebiewski, M
    Ritzdorf, H
    Träff, JL
    Zimmermann, F
    [J]. NEC RESEARCH & DEVELOPMENT, 2003, 44 (01): : 69 - 74
  • [3] A multi-node MPI implementation on the CellBE processor
    Liu, Chao
    Zhang, Xingjun
    Feng, Guofu
    Feng, Jinghua
    Dong, Xiaoshe
    [J]. Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition), 2010, 38 (SUPPL. 1): : 59 - 63
  • [4] Experiences with advanced CFD algorithms on NEC SX-4
    vanderVen, H
    vanderVegt, JJW
    [J]. VECTOR AND PARALLEL PROCESSING - VECPAR'96, 1997, 1215 : 236 - 246
  • [5] Real-time visualization of large data sets on NLR's NEC SX-4
    van der Ven, H
    Schultheiss, B
    Doi, S
    Matsumoto, H
    Sugihara, K
    Takei, T
    [J]. HIGH-PERFORMANCE COMPUTING AND NETWORKING, 1998, 1401 : 397 - 402
  • [6] Partitioning and parallel development of an unstructured, adaptive flow solver on the NEC SX-4
    van der Ven, H
    van der Vegt, JJW
    [J]. PARALLEL COMPUTATIONAL FLUID DYNAMICS: RECENT DEVELOPMENTS AND ADVANCES USING PARALLEL COMPUTERS, 1998, : 149 - 156
  • [7] Parallelization of scientific applications on the SX-4 - The CSCS/SCSC-NEC joint program in application porting and development
    Ballabio, M
    Boverat, M
    Gasser, L
    Maric, D
    Haberhauer, S
    Henriet, C
    Hausammann, R
    [J]. NEC RESEARCH & DEVELOPMENT, 1998, 39 (04): : 482 - 490
  • [8] Archipelago: A Hybrid Multi-Node Campus SDN Architecture
    Brockelsby, William
    Dutta, Rudra
    [J]. 2023 26TH CONFERENCE ON INNOVATION IN CLOUDS, INTERNET AND NETWORKS AND WORKSHOPS, ICIN, 2023,
  • [9] Microtasking versus Message Passing parallelisation of the 3D-combustion code AIOLOS on the NEC SX-4
    Risio, B
    Lepper, J
    Schnell, U
    Hein, KRG
    [J]. PARALLEL COMPUTATIONAL FLUID DYNAMICS: RECENT DEVELOPMENTS AND ADVANCES USING PARALLEL COMPUTERS, 1998, : 439 - 446
  • [10] Integrated operating multi-node system for SX-Series and enhanced resource scheduler
    Miyazaki, E
    Yabuki, K
    [J]. NEC RESEARCH & DEVELOPMENT, 2003, 44 (01): : 37 - 42
12345