Ninf and PM: Communication libraries for global computing and high-performance cluster computing

被引:1
|
作者
Sato, M
Tezuka, H
Hori, A
Ishikawa, Y
Sekiguchi, S
Nakada, H
Matsuoka, S
Nagashima, U
机构
[1] Real World Comp Partnership, Tsukuba, Ibaraki 305, Japan
[2] Electrotech Lab, Ibaraki, Osaka 305, Japan
[3] Tokyo Inst Technol, Meguro Ku, Tokyo 152, Japan
[4] Ochanomizu Univ, Bunkyo Ku, Tokyo 112, Japan
关键词
global computing; remote procedure call; cluster computing; gigabit LAN; user-level communication protocol; high-performance computing;
D O I
10.1016/S0167-739X(97)00036-8
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper presents two advanced communication libraries, Ninf and PM. Ninf is an ongoing global network wide computing infrastructure project which allows users to access computational resources including hardware, software and scientific data distributed across a wide area network. Computational resources are shared as Ninf remote libraries executable at a remote Ninf server. Users can build an application by calling the libraries with the Ninf Remote Procedure Call. In order to facilitate location transparency and network-wide parallelism, Ninf metaserver maintains global resource information regarding computational server and databases, allocating and scheduling coarse-grained computation for global load balancing. PM is a high-performance communication library for workstation clusters connected with Myrinet gigabit LAN card, which has a dedicated processor and on-board memory to handle a communication protocol. In order to obtain high-performance communication and support a multi-user environment, we co-designed PM, an operating system realized by a daemon process, and the run-time routine for a programming language. Several unique features, e.g., network context switching and modified ACK/NACK flow control algorithm have been developed for PM. PM for the Suns has a speed of 20 mu s round trip for a user-level 8 bytes message and 38.6 Mbytes/s bandwidth for an 8 Kbytes message. Copyright (C) 1998 Elsevier Science B.V.
引用
收藏
页码:349 / 359
页数:11
相关论文
共 50 条
  • [1] Device level communication libraries for high-performance computing in Java']Java
    Taboada, Guillermo L.
    Tourino, Juan
    Doallo, Ramon
    Shafi, Aamir
    Baker, Mark
    Carpenter, Bryan
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2011, 23 (18): : 2382 - 2403
  • [2] Teaching high-performance computing on a high-performance cluster
    Bernreuther, M
    Brenk, M
    Bungartz, HJ
    Mundani, RP
    Muntean, IL
    [J]. COMPUTATIONAL SCIENCE - ICCS 2005, PT 2, 2005, 3515 : 1 - 9
  • [3] Cluster computing: A high-performance contender
    Baker, M
    Buyya, R
    Hyde, D
    [J]. COMPUTER, 1999, 32 (07) : 79 - +
  • [4] Plug-and-play cluster computing: High-performance computing for the mainstream
    Dauger, DE
    Decyk, VK
    [J]. COMPUTING IN SCIENCE & ENGINEERING, 2005, 7 (02) : 27 - 33
  • [5] Design and Performance Measurement of a High-Performance Computing Cluster
    George, Kiran
    Venugopal, Vivek
    [J]. 2012 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE (I2MTC), 2012, : 2531 - 2536
  • [6] Madeleine II:: a portable and efficient communication library for high-performance cluster computing
    Aumage, O
    Bougé, L
    Méhaut, JF
    Namyst, R
    [J]. PARALLEL COMPUTING, 2002, 28 (04) : 607 - 626
  • [7] Madeleine II:: a portable and efficient communication library for high-performance cluster computing
    Aumage, O
    Bougé, L
    Denis, A
    Méhaut, JF
    Mercier, G
    Namyst, R
    Prylli, L
    [J]. CLUSTER 2000: IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING, PROCEEDINGS, 2000, : 78 - 87
  • [8] A Survey of Communication Performance Models for High-Performance Computing
    Rico-Gallego, Juan A.
    Diaz-Martin, Juan C.
    Manumachu, Ravi Reddy
    Lastovetsky, Alexey L.
    [J]. ACM COMPUTING SURVEYS, 2019, 51 (06) : 1 - 36
  • [9] Virtual Machine Aware Communication Libraries for High Performance Computing
    Huang, Wei
    Koop, Matthew J.
    Gao, Qi
    Panda, Dhabaleswar K.
    [J]. 2007 ACM/IEEE SC07 CONFERENCE, 2010, : 228 - 239
  • [10] Building a high-performance computing cluster using FreeBSD
    Davis, B
    AuYeung, M
    Green, G
    Lee, C
    [J]. USENIX ASSOCIATION PROCEEDINGS OF BSDCON '03, 2003, : 35 - 46