MESH: MEssaging and ScHeduling for fine-grain parallel processing on commodity platforms

被引:0
|
作者
Boosten, M [1 ]
Dobinson, RW [1 ]
van der Stok, PDV [1 ]
机构
[1] CERN, European Lab Particle Phys, CH-1211 Geneva 23, Switzerland
关键词
fine-grain; massively parallel processing; commodity; real-time; fault-tolerance;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
MESH is a tight integration of a user-level thread scheduler and a zero-copy messaging system that enables efficient fine-grain parallel processing on commodity platforms with efficient support for fault-tolerance. We present the techniques used to deliver most of the performance of the underlying communication hardware to a multi-threaded application level, while introducing little CPU overhead. This is demonstrated by a performance analysis of a MESH implementation requiring only off-the-shelf products: PCs, running the Linux operating system, equipped with Fast and Gigabit Ethernet network interface cards.
引用
收藏
页码:1716 / 1722
页数:7
相关论文
共 50 条
  • [1] FINE-GRAIN SCHEDULING
    MASSALIN, H
    PU, C
    WORKSHOP ON EXPERIENCES WITH DISTRIBUTED AND MULTIPROCESSOR SYSTEMS, 1989, : 91 - 104
  • [2] Pine-grain parallel processing on commodity platforms
    Boosten, M
    Dobinson, RW
    van der Stok, PDV
    ARCHITECTURES, LANGUAGES AND TECHNIQUES FOR CONCURRENT SYSTEMS, 1999, 57 : 263 - 276
  • [3] Inverter reduction algorithm for super fine-grain parallel processing
    NTT Information and Communication, Systems Lab, Yokosuka-shi, Japan
    IEICE Trans Fund Electron Commun Comput Sci, 1600, 3 (487-493):
  • [4] Inverter reduction algorithm for super fine-grain parallel processing
    Ito, H
    Nagami, K
    Shiozawa, T
    Nakamura, Y
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1997, E80A (03) : 487 - 493
  • [6] A FINE-GRAIN PARALLEL IMPLEMENTATION OF PARLOG
    PAPADOPOULOS, GA
    LECTURE NOTES IN COMPUTER SCIENCE, 1989, 352 : 313 - 327
  • [7] DIGITAL CONTROLLER STRUCTURES FOR FINE-GRAIN AND MEDIUM-GRAIN PARALLEL PROCESSING ARCHITECTURES
    DEOLIVEIRA, MCF
    FLEMING, PJ
    INTERNATIONAL JOURNAL OF CONTROL, 1991, 54 (06) : 1413 - 1437
  • [8] Flexible Architectural Support for Fine-Grain Scheduling
    Sanchez, Daniel
    Yoo, Richard M.
    Kozyrakis, Christos
    ACM SIGPLAN NOTICES, 2010, 45 (03) : 311 - 322
  • [9] Fine-grain instruction scheduling for low energy
    Xu, W
    Parikh, A
    Kandemir, M
    Irwin, MJ
    2002 IEEE WORKSHOP ON SIGNAL PROCESSING SYSTEMS, 2002, : 258 - 263
  • [10] Flexible Architectural Support for Fine-Grain Scheduling
    Sanchez, Daniel
    Yoo, Richard M.
    Kozyrakis, Christos
    ASPLOS XV: FIFTEENTH INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS, 2010, : 311 - 322